Image fusion method and device, camera equipment and storage medium

文档序号：172757 发布日期：2021-10-29 浏览：23次中文

阅读说明：本技术 图像融合方法、装置、摄像设备及存储介质 (Image fusion method and device, camera equipment and storage medium ) 是由马士杰杜斌雷永敢于 2020-04-24 设计创作，主要内容包括：本申请公开了一种图像融合方法、装置、摄像设备及存储介质,属于图像处理技术领域。所述方法包括：获取摄像设备在未经过红外补光的情况下采集的第一图像和在经过红外补光的情况下采集的第二图像。若第一图像是摄像设备在曝光时长大于曝光时长阈值的长曝光模式下采集的,调整第一图像和/或第二图像的融合加权系数,得到第一图像的第一融合加权系数和第二图像的第二融合加权系数,第一融合加权系数与第二融合加权系数的差值大于第一差值阈值。基于第一融合加权系数和第二融合加权系数,将第一图像和第二图像进行图像融合,得到融合图像。如此得到的融合图像会更倾向于第一图像和第二图像中质量更好的图像,提高了融合图像的图像质量。(The application discloses an image fusion method and device, camera equipment and a storage medium, and belongs to the technical field of image processing. The method comprises the following steps: the method comprises the steps of acquiring a first image acquired by the camera device without infrared supplementary lighting and a second image acquired by the camera device with infrared supplementary lighting. If the first image is acquired by the camera equipment in a long exposure mode with exposure time greater than the exposure time threshold, the fusion weighting coefficient of the first image and/or the second image is adjusted to obtain a first fusion weighting coefficient of the first image and a second fusion weighting coefficient of the second image, and the difference value between the first fusion weighting coefficient and the second fusion weighting coefficient is greater than the first difference threshold. And carrying out image fusion on the first image and the second image based on the first fusion weighting coefficient and the second fusion weighting coefficient to obtain a fusion image. The obtained fusion image is more inclined to the image with better quality in the first image and the second image, and the image quality of the fusion image is improved.)

1. An image fusion method is applied to an image pickup device, and comprises the following steps:

acquiring a first image and a second image, wherein the first image is acquired by the camera device without infrared supplementary lighting, and the second image is acquired by the camera device with infrared supplementary lighting;

if the first image is acquired by the camera device in a long exposure mode, adjusting a fusion weighting coefficient of the first image and/or the second image to obtain a first fusion weighting coefficient of the first image and a second fusion weighting coefficient of the second image, wherein the difference value between the first fusion weighting coefficient and the second fusion weighting coefficient is greater than a first difference threshold value, and the exposure duration in the long exposure mode is greater than an exposure duration threshold value;

and carrying out image fusion on the first image and the second image based on the first fusion weighting coefficient and the second fusion weighting coefficient to obtain a fused image.

2. The method of claim 1, wherein the adjusting the fusion weighting factor of the first image and/or the second image if the first image is captured by the camera device in a long exposure mode comprises:

if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object;

in the case that the second image includes the moving object, decreasing a fusion weighting coefficient of the first image and/or increasing a fusion weighting coefficient of the second image, the first fusion weighting coefficient being smaller than the second fusion weighting coefficient.

3. The method of claim 1, wherein the adjusting the fusion weighting factor of the first image and/or the second image if the first image is captured by the camera device in a long exposure mode comprises:

if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object;

in the case that the second image does not include the moving object, increasing the fusion weighting coefficient of the first image and/or decreasing the fusion weighting coefficient of the second image, the first fusion weighting coefficient being greater than the second fusion weighting coefficient.

4. The method of claim 1, wherein the method further comprises:

determining the external illumination intensity for multiple times;

comparing the currently determined external illumination intensity with an illumination intensity threshold value every time the external illumination intensity is determined, and recording a comparison result, wherein the illumination intensity threshold value comprises a first illumination intensity threshold value and/or a second intensity threshold value;

and entering the long exposure mode if the outside illumination intensity is determined to be continuously lower than the first illumination intensity threshold according to the recorded comparison result.

5. The method of claim 4, wherein the ambient light intensity is determined by:

determining target shooting parameters, wherein the difference value between the brightness value of the image acquired by the shooting equipment under the target shooting parameters and the expected brightness value is smaller than or equal to a second difference threshold value;

determining corresponding illumination intensity from a specified mapping relation based on the target shooting parameters, wherein the specified mapping relation is used for indicating the corresponding relation between the shooting parameters and the illumination intensity;

determining the determined illumination intensity as the ambient illumination intensity.

6. The method of claim 5, wherein determining target imaging parameters comprises:

determining the current camera shooting parameters as reference camera shooting parameters;

acquiring an image based on the reference camera parameters;

if the difference value between the brightness value of the acquired image and the expected brightness value is larger than the second difference threshold value, adjusting the current shooting parameters of the shooting equipment;

determining the adjusted shooting parameters as the reference shooting parameters, and continuously returning to the step of acquiring images based on the reference shooting parameters;

and determining the shooting parameters corresponding to the currently acquired image as the target shooting parameters until the difference between the brightness value of the acquired image and the expected brightness value is less than or equal to the second difference threshold.

7. The method of claim 4, wherein the long exposure mode includes at least one exposure duration, and wherein entering the long exposure mode includes:

adjusting the gain of the camera equipment to be a first gain, wherein the first gain is a gain which enables the noise of the collected image to be smaller than a noise threshold value;

and increasing the exposure time of the camera equipment to obtain one exposure time in the long exposure mode.

8. The method according to claim 7, wherein after the increasing the exposure time period of the image pickup apparatus, further comprising:

under the condition that the brightness value of the image acquired based on the increased exposure time length and the first gain is smaller than a desired brightness value and the difference between the brightness value of the image acquired based on the increased exposure time length and the first gain and the desired brightness value is larger than a second difference threshold value, continuing to increase the exposure time length of the camera equipment to obtain another exposure time length in the long exposure mode; alternatively, the first and second electrodes may be,

and under the condition that the brightness value of the image acquired based on the increased exposure time length and the first gain is greater than the expected brightness value and the difference between the brightness value of the image acquired based on the increased exposure time length and the first gain and the expected brightness value is greater than the second difference threshold, reducing the exposure time length of the camera equipment to obtain another exposure time length in the long exposure mode.

9. The method of claim 4, wherein the method further comprises:

and if the external illumination intensity is determined to be continuously higher than the second illumination intensity threshold value according to the recorded comparison result and the external illumination intensity is currently in the long exposure mode, exiting the long exposure mode.

10. The method of claim 9, wherein said exiting said long exposure mode comprises:

adjusting the current exposure duration of the camera equipment to a specified exposure duration, wherein the specified exposure duration is less than or equal to the exposure duration threshold;

and adjusting the current gain of the camera equipment.

11. An image fusion apparatus, characterized in that the apparatus comprises:

the first image sensor is used for acquiring a first image, and the first image is acquired under the condition that infrared supplementary lighting is not performed;

the second image sensor is used for acquiring a second image, and the second image is acquired under the condition of infrared supplementary lighting;

a processor for performing image fusion on the first image acquired by the first image sensor and the second image acquired by the second image sensor according to the method of claim 1 to obtain a fused image.

12. The apparatus of claim 11, wherein the processor is to:

if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object;

13. The apparatus of claim 11, wherein the processor is to:

if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object;

14. An image pickup apparatus comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus, the memory stores a computer program, and the processor executes the program stored in the memory to implement the steps of the method according to any one of claims 1 to 10.

15. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 10.

Technical Field

The present application relates to the field of image processing technologies, and in particular, to an image fusion method and apparatus, an image capturing device, and a storage medium.

Background

As the application of images in various fields is more and more extensive, the quality requirements of users on the images are higher and higher. However, in an environment with low illumination intensity, because the exposure duration of the camera device is limited by the frame rate, the brightness of the acquired image can only be increased by increasing the gain, and in this case, the first image acquired by the camera device without infrared fill light is usually blurred and has high noise, which results in poor image quality and may not meet the user's requirements. Therefore, in the related art, while the first image is collected, the camera device may further collect a second image subjected to infrared supplementary lighting, and the second image and the first image are subjected to image fusion to obtain a fused image.

However, under the condition that the external illumination intensity is extremely low, because the light supplement is not performed and the exposure time of the camera device is limited by the frame rate, the first image acquired by the camera device is still blurred and has high noise, so that the fused image obtained after the image fusion processing is unclear, and the quality of the obtained fused image is poor.

Disclosure of Invention

The application provides an image fusion method and device, camera equipment and a storage medium, which can solve the problem of poor image quality of fused images in the prior art under the condition of extremely low illumination intensity. The technical scheme is as follows:

in one aspect, an image fusion method is provided, and the method includes:

and carrying out image fusion on the first image and the second image based on the first fusion weighting coefficient and the second fusion weighting coefficient to obtain a fused image.

In a possible implementation manner of the present application, if the first image is acquired by the image capturing apparatus in a long exposure mode, adjusting a fusion weighting coefficient of the first image and/or the second image includes:

if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object;

In one possible implementation manner of the present application, the method further includes:

determining the external illumination intensity for multiple times;

In one possible implementation manner of the present application, the ambient light intensity is determined as follows:

determining the determined illumination intensity as the ambient illumination intensity.

In one possible implementation manner of the present application, the determining target imaging parameters includes:

determining the current camera shooting parameters as reference camera shooting parameters;

acquiring an image based on the reference camera parameters;

determining the adjusted shooting parameters as the reference shooting parameters, and continuously returning to the step of acquiring images based on the reference shooting parameters;

In a possible implementation manner of the present application, the long exposure mode includes at least one exposure duration, and the entering the long exposure mode includes:

adjusting the gain of the camera equipment to be a first gain, wherein the first gain is a gain which enables the noise of the collected image to be smaller than a noise threshold value;

and increasing the exposure time of the camera equipment to obtain one exposure time in the long exposure mode.

In one possible implementation manner of the present application, after increasing the exposure time period of the image capturing apparatus, the method further includes:

In one possible implementation manner of the present application, the method further includes:

In a possible implementation manner of the present application, the exiting the long exposure mode includes:

adjusting the current exposure duration of the camera equipment to a specified exposure duration, wherein the specified exposure duration is less than or equal to the exposure duration threshold;

and adjusting the current gain of the camera equipment.

In another aspect, an image fusion apparatus is provided, the apparatus including:

the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a first image and a second image, the first image is acquired by the camera device without infrared supplementary lighting, and the second image is acquired by the camera device after infrared supplementary lighting;

an adjusting module, configured to adjust a fusion weighting coefficient of the first image and/or the second image if the first image is acquired by the image capturing device in a long exposure mode, to obtain a first fusion weighting coefficient of the first image and a second fusion weighting coefficient of the second image, where a difference between the first fusion weighting coefficient and the second fusion weighting coefficient is greater than a first difference threshold, and an exposure duration in the long exposure mode is greater than an exposure duration threshold;

and the image fusion module is used for carrying out image fusion on the first image and the second image based on the first fusion weighting coefficient and the second fusion weighting coefficient to obtain a fusion image.

In one possible implementation manner of the present application, the adjusting module is configured to:

if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object;

In one possible implementation manner of the present application, the adjusting module is configured to:

if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object;

In one possible implementation manner of the present application, the obtaining module is further configured to:

determining the external illumination intensity for multiple times;

In one possible implementation manner of the present application, the ambient light intensity is determined as follows:

determining the determined illumination intensity as the ambient illumination intensity.

In one possible implementation manner of the present application, the obtaining module is further configured to:

determining the current camera shooting parameters as reference camera shooting parameters;

acquiring an image based on the reference camera parameters;

determining the adjusted shooting parameters as the reference shooting parameters, and continuously returning to the step of acquiring images based on the reference shooting parameters;

In a possible implementation manner of the present application, the long exposure mode includes at least one exposure duration, and the obtaining module is further configured to:

adjusting the gain of the camera equipment to be a first gain, wherein the first gain is a gain which enables the noise of the collected image to be smaller than a noise threshold value;

and increasing the exposure time of the camera equipment to obtain one exposure time in the long exposure mode.

In one possible implementation manner of the present application, the obtaining module is further configured to:

adjusting the current exposure duration of the camera equipment to a specified exposure duration, wherein the specified exposure duration is less than or equal to the exposure duration threshold;

and adjusting the current gain of the camera equipment.

In another aspect, an image fusion apparatus is provided, the apparatus including:

the first image sensor is used for acquiring a first image, and the first image is acquired under the condition that infrared supplementary lighting is not performed;

the second image sensor is used for acquiring a second image, and the second image is acquired under the condition of infrared supplementary lighting;

and the processor is used for adjusting the fusion weighting coefficient of the first image and/or the second image to obtain a first fusion weighting coefficient of the first image and a second fusion weighting coefficient of the second image if the first image is acquired by the camera equipment in the long exposure mode, wherein the difference value between the first fusion weighting coefficient and the second fusion weighting coefficient is greater than a first difference threshold value, and the exposure duration in the long exposure mode is greater than an exposure duration threshold value. And carrying out image fusion on the first image and the second image based on the first fusion weighting coefficient and the second fusion weighting coefficient to obtain a fusion image.

In one possible implementation manner of the present application, the processor is configured to:

if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object;

In one possible implementation manner of the present application, the processor is configured to:

if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object;

In one possible implementation manner of the present application, the processor is further configured to:

determining the external illumination intensity for multiple times;

In one possible implementation manner of the present application, the processor determines the ambient light intensity by:

determining the determined illumination intensity as the ambient illumination intensity.

In one possible implementation manner of the present application, the processor is configured to:

determining the current camera shooting parameters as reference camera shooting parameters;

acquiring an image based on the reference camera parameters;

determining the adjusted shooting parameters as the reference shooting parameters, and continuously returning to the step of acquiring images based on the reference shooting parameters;

In one possible implementation manner of the present application, the processor is configured to:

the long exposure mode comprises at least one exposure duration, and the gain of the camera equipment is adjusted to be a first gain, wherein the first gain is a gain which enables the noise of the acquired image to be smaller than a noise threshold value;

and increasing the exposure time of the camera equipment to obtain one exposure time in the long exposure mode.

In one possible implementation manner of the present application, the processor is further configured to:

In one possible implementation manner of the present application, the processor is configured to:

adjusting the current exposure duration of the camera equipment to a specified exposure duration, wherein the specified exposure duration is less than or equal to the exposure duration threshold;

and adjusting the current gain of the camera equipment.

In another aspect, an image capturing apparatus is provided, where the image capturing apparatus includes a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete mutual communication through the communication bus, the memory is used to store a computer program, and the processor is used to execute the program stored in the memory to implement the steps of the image fusion method.

In another aspect, a computer-readable storage medium is provided, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the image fusion method described above.

In another aspect, a computer program product is provided comprising instructions which, when run on a computer, cause the computer to perform the steps of the image fusion method described above.

The technical scheme provided by the application can at least bring the following beneficial effects:

the method comprises the steps of acquiring a first image and a second image, wherein the first image and the second image are acquired by a camera device, the first image is acquired without infrared supplementary lighting, and the second image is acquired with infrared supplementary lighting. If the first image is acquired by the image pickup device in the long exposure mode with the exposure duration being greater than the exposure duration threshold, since the image acquired in the long exposure mode may be relatively clear and may also cause a smear problem, the fusion weighting coefficients of the first image and the second image may be respectively adjusted according to different practical situations, or only the fusion weighting coefficient of the first image may be adjusted, or only the fusion weighting coefficient of the second image may be adjusted, so as to obtain the first fusion weighting coefficient of the first image and the second fusion weighting coefficient of the second image. In order to make the resulting fused image closer to the image with better image quality of the first image and the second image, the difference between the first fusion weighting coefficient and the second fusion weighting coefficient may be made larger than the first difference threshold, i.e., the first fusion weighting coefficient and the second fusion weighting coefficient are made to differ greatly. Then, the first image and the second image are subjected to image fusion based on the obtained first fusion weighting coefficient and the second fusion weighting coefficient, so that the obtained fusion image is more inclined to the image with better quality in the first image and the second image, and the image quality of the fusion image is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a flow diagram illustrating an image fusion method according to an exemplary embodiment;

FIG. 2 is a flow diagram illustrating an adjustment of imaging parameters according to an exemplary embodiment;

FIG. 3 is a flow chart illustrating a method of image fusion according to another exemplary embodiment;

FIG. 4 is a schematic diagram illustrating a configuration of an image fusion apparatus according to an exemplary embodiment;

FIG. 5 is a schematic diagram illustrating a configuration of an image fusion apparatus according to another exemplary embodiment;

fig. 6 is a schematic configuration diagram of an image pickup apparatus according to an exemplary embodiment.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

Before explaining the image fusion method provided by the embodiment of the present application in detail, an execution subject of the image fusion method provided by the embodiment of the present application is introduced.

The execution subject of the image fusion method provided by the embodiment of the application can be the camera equipment. The camera device can comprise a camera and a processor, wherein the camera is used for collecting images, and the processor is used for processing the images collected by the camera.

As an example, the image capturing apparatus may be a binocular camera, and the binocular camera may include two cameras for capturing two images, one being a first image captured by the first image sensor without infrared light supplement, i.e., a visible light image, and the other being a second image captured by the second image sensor with infrared light supplement, i.e., an infrared image. Then, the processor performs image fusion processing on the first image and the second image, so that a fused image with higher image quality can be obtained. The first image sensor is a visible light image sensor, and the second image sensor is an infrared image sensor.

It will be understood by those skilled in the art that the above-described imaging apparatus is merely exemplary, and other existing or future terminals or servers may be included within the scope of the present application, as applicable, and are hereby incorporated by reference.

After the implementation environment provided by the embodiment of the present application is introduced, a detailed explanation is next given to the image fusion method provided by the embodiment of the present application.

Fig. 1 is a flowchart illustrating an image fusion method according to an exemplary embodiment, which is applied to the above-described image capturing apparatus. Referring to fig. 1, the method may include the following steps:

step 101: the method comprises the steps of acquiring a first image and a second image, wherein the first image is acquired by the camera device without infrared supplementary lighting, and the second image is acquired by the camera device with infrared supplementary lighting.

The first image collected by the camera device without infrared supplementary lighting can be a visible light image, the first image is collected without any supplementary lighting device, and the first image can include color information and brightness information.

The second image acquired by the camera device under the condition of infrared light supplement can be an infrared image, the second image is acquired under the condition that an infrared light supplement device carries out infrared light supplement, and the second image can include brightness information but does not include color information.

As an example, the camera device may capture images in real time through two cameras, and the first image and the second image are typically captured simultaneously.

In implementation, in the process of acquiring an image, since the external illumination intensity is extremely low, the acquired image may be blurred, and therefore, the camera device needs to be adjusted to enter the long exposure mode or exit the long exposure mode according to the external illumination intensity, so as to acquire a clearer image in the corresponding mode.

And the exposure time length in the long exposure mode is greater than the exposure time length threshold value. The exposure duration threshold may be set by a user according to actual needs, or may be set by default by the image pickup device, which is not limited in the embodiment of the present application. For example, the exposure duration threshold may be 66 ms.

In implementation, the external illumination intensity may be determined for multiple times, and each time the external illumination intensity is determined, the currently determined external illumination intensity is compared with the illumination intensity threshold, and the comparison result is recorded. Wherein the illumination intensity threshold may be a first illumination intensity threshold and/or a second illumination intensity threshold. And if the external illumination intensity is determined to be continuously lower than the first illumination intensity threshold value according to the recorded comparison result, entering a long exposure mode.

It should be noted that, both the first illumination intensity threshold and the second illumination intensity threshold may be set by a user according to actual needs, and may be adjusted according to actual situations, or may be set by default by the image capturing apparatus, which is not limited in this embodiment of the application. In addition, the second illumination intensity threshold value can be smaller than the first illumination intensity threshold value, so that the image quality of the first image acquired in the non-long exposure mode can be better. For example, the first illumination intensity threshold may be 0.2Lx and the second illumination intensity threshold may be 0.08 Lx.

As an example, the first illumination intensity threshold may be set based on big data or experience. Illustratively, the setting can be based on the imaging effect of the first image captured by the camera device under different illumination intensities, and if the illumination intensity is lower than the first illumination intensity threshold, the noise of the captured first image is large and the smear in the first image is poor, which has great influence on the image quality of the first image, and long exposure is needed to improve the image quality, and the first illumination intensity threshold is set to control the noise and the smear within an acceptable range.

Similarly, the second illumination intensity threshold may also be set according to big data or experience, and for example, may be set according to an imaging effect of the first image acquired by the image capturing apparatus under different illumination intensities, and if the illumination intensity is extremely low illumination intensity but higher than the second illumination intensity threshold, under the condition of not performing long exposure, the noise of the acquired first image is small and the smear in the first image is small, so that the image quality of the first image is good, and the long exposure mode may be exited.

In addition, the first and second illumination intensity thresholds may be set differently depending on the configuration of the image pickup apparatus, for example, the image sensor or the aperture.

That is to say, in the process of acquiring an image without infrared supplementary lighting, the external illumination intensity may be determined for multiple times, and the magnitude relationship between the currently determined external illumination intensity and the first illumination intensity threshold value is determined every time the external illumination intensity is determined, or the magnitude relationship between the currently determined external illumination intensity and the second illumination intensity threshold value is determined, or the magnitude relationship between the currently determined external illumination intensity and the first illumination intensity threshold value and the second illumination intensity threshold value is determined, and the comparison result is recorded, so that the comparison result may be recorded for multiple times. If it is determined from the recorded comparison results that the external illumination intensity is continuously lower than the first illumination intensity threshold, it can be considered that the external environment is continuously in a relatively dark state, and the image quality of the acquired image is poor under such a condition, so that the long exposure mode can be entered.

In practice, the ambient light intensity may be determined as follows:

and determining target shooting parameters, wherein the difference value between the brightness value of the image acquired by the shooting equipment under the target shooting parameters and the expected brightness value is smaller than or equal to a second difference threshold value. And determining corresponding illumination intensity from the specified mapping relation based on the target shooting parameters, wherein the specified mapping relation is used for indicating the corresponding relation between the shooting parameters and the illumination intensity, and the determined illumination intensity is determined as the external illumination intensity.

The imaging parameters of the imaging apparatus may include at least an exposure time length and a gain.

As an example, the image capturing parameters may also include the size of an aperture of a lens of the image capturing apparatus and the sensitivity of an image sensor for different image capturing apparatuses.

The specified mapping relation can be stored in the imaging device in advance, and is obtained by analyzing the historical image, the historical external illumination intensity and the historical imaging parameter.

It should be noted that the second difference threshold may be set by a user according to an actual requirement, or may be set by default by the image capturing apparatus, which is not limited in this embodiment of the application. For example, the second difference threshold may be 2.

It should be noted that the desired brightness value may be set by a user according to actual needs, or may be set by default by the image capturing apparatus, which is not limited in this embodiment of the application. For example, the desired brightness value may be 10, and the value of 10 is merely an example and may be used to indicate the degree of brightness. In an implementation, the desired luminance value may also be 200cd/m2, etc.

As an example, the desired luminance value is a luminance value of an image that can make the quality and effect of the image better. The previously stored specified mapping relationship indicates a correspondence relationship between different image pickup parameters and illumination intensity in a case where the luminance of an image is made to reach a desired luminance. That is, at a certain illumination intensity in the designated mapping relationship, the brightness of the image acquired using the imaging parameter corresponding to the certain illumination intensity is close to the desired brightness. Therefore, the ambient light intensity can be determined by the target imaging parameter that makes the luminance value of the image close to the desired luminance value. In addition, the process of adjusting the brightness of the image from the non-close to the expected brightness to the close to the expected brightness is very fast, and in the process, the brightness of the image does not reach the expected brightness, and if the external illumination intensity is determined by using the image pickup parameters in the secondary process, the determined external illumination intensity may be inaccurate. Therefore, it is necessary to determine the ambient light intensity using target imaging parameters that cause the brightness of an image captured by the imaging apparatus to reach a desired brightness.

That is to say, in the process of determining the external illumination intensity, a target image capturing parameter that enables the brightness of an image captured by the image capturing apparatus to be close to the desired brightness may be determined, then the illumination intensity corresponding to the target image capturing parameter is determined from the pre-stored correspondence between the image capturing parameter and the illumination intensity based on the target image capturing parameter, and the determined illumination intensity is determined as the external illumination intensity.

In an implementation, determining the target imaging parameter may include: and determining the current camera shooting parameters as reference camera shooting parameters, and acquiring images based on the reference camera shooting parameters. And if the difference value between the brightness value of the acquired image and the expected brightness value is larger than a second difference threshold value, adjusting the current shooting parameters of the shooting equipment. And determining the adjusted shooting parameters as reference shooting parameters, and continuously returning to the step of acquiring images based on the reference shooting parameters until the difference value between the brightness value of the acquired images and the expected brightness value is less than or equal to a second difference threshold value, and determining the shooting parameters corresponding to the currently acquired images as target shooting parameters.

That is, the current imaging parameter of the imaging apparatus may be determined as a reference imaging parameter, an image is acquired based on the reference imaging parameter, the brightness value of the acquired image is compared with the expected brightness value, if the difference between the brightness value of the acquired image and the expected brightness value is large, it may be considered that the brightness of the acquired image does not reach the required expected brightness, the current imaging parameter of the imaging apparatus may be readjusted, the adjusted imaging parameter is determined as the reference imaging parameter, the image is continuously acquired based on the reference imaging parameter, the brightness value of the acquired image is continuously compared with the expected brightness value, if the brightness does not reach the expected brightness, the current imaging parameter is continuously adjusted until the brightness value of the acquired image is closer to the expected brightness value, that is, the brightness of the acquired image reaches the required expected brightness, the shooting parameters corresponding to the currently acquired image can be determined as target shooting parameters.

In some embodiments, if the difference between the brightness value of the acquired image and the expected brightness value is greater than the second difference threshold, it may be considered that the brightness of the acquired image is far different from the expected brightness and does not meet the expectation of the brightness of the image, and therefore, the current shooting parameter of the shooting device needs to be adjusted to make the brightness of the acquired image meet the user requirement, and further determine the target shooting parameter.

As an example, if the difference between the brightness value of the captured image and the desired brightness value is greater than the second difference threshold and the brightness value of the captured image is less than the desired brightness value, the brightness of the captured image may be considered to be low, and the exposure time period and/or the gain may be increased. Illustratively, only the exposure time period may be increased, only the gain may be increased, or both the exposure time period and the gain may be increased.

As another example, if the difference between the brightness value of the captured image and the desired brightness value is greater than the second difference threshold, and the brightness value of the captured image is greater than the desired brightness value, the brightness of the captured image may be considered to be higher, and the exposure time period and/or the gain may be reduced. Illustratively, only the exposure time period may be reduced, or only the gain may be reduced, or both the exposure time period and the gain may be reduced.

In implementation, after the target image capturing parameters are determined, the ambient light intensity may be determined according to the target image capturing parameters.

As an example, assume that the ambient light intensity may be represented by 0-10, where 0 represents the highest ambient light intensity, 10 represents the lowest ambient light intensity, and 0-10 may correspond to a set of imaging parameters, respectively. After the target shooting parameter is determined, the external illumination intensity corresponding to the target shooting parameter can be determined according to the corresponding relationship between the pre-stored shooting parameter and the external illumination intensity.

As another example, the correspondence relationship between the imaging parameter range and the outside light intensity may be stored in advance in the imaging apparatus in the form of a specified mapping relationship. Assuming that the ambient light intensity can be represented by 0-10, 0 represents the highest ambient light intensity, 10 represents the lowest ambient light intensity, and 0-10 can correspond to a set of imaging parameter ranges, respectively. After the target shooting parameter is determined, according to the corresponding relationship between the pre-stored shooting parameter and the external illumination intensity, the shooting parameter range to which the target shooting parameter belongs is determined, and then the external illumination intensity corresponding to the shooting parameter range is determined as the external illumination intensity corresponding to the target shooting parameter.

In implementation, in the process of determining the external illumination intensity according to the target parameter for multiple times, each time the external illumination intensity is determined, the currently determined external illumination intensity may be compared with the first illumination intensity threshold, and the comparison result is recorded. Illustratively, assuming that the first illumination intensity threshold is 0.08Lx and the ambient illumination intensity determined at a time is 0.06Lx, the comparison may be recorded as the ambient illumination intensity being less than the first illumination intensity threshold.

In practice, determining that the ambient light intensity is continuously lower than the first light intensity threshold according to the recorded comparison result may include the following determination methods:

the first judgment mode is as follows: and in the first time period, the comparison result recorded every time is that the outside illumination intensity is smaller than a first illumination intensity threshold value.

The first duration may be set by a user according to actual needs, or may be set by default by the image capturing device, which is not limited in the embodiment of the present application. For example, the first duration may be 5 seconds.

That is, if the ambient light intensity is determined to be less than the first light intensity threshold each time during the first time period, the ambient environment may be considered to be continuously at an extremely low light intensity for the first time period, and thus, this condition may be determined as the ambient light intensity being continuously below the first light intensity threshold.

In this implementation manner, in the process of comparing the external light intensity with the first light intensity threshold and recording the comparison result, the number of times that the external light intensity is smaller than the first light intensity threshold may be counted as the comparison result, and every time the external light intensity is recorded as being smaller than the first light intensity threshold, the number of times that the external light intensity is smaller than the first light intensity threshold is added by 1 as the counted comparison result.

For example, if the determined ambient light intensity is 0.07, the comparison result may be recorded as that the ambient light intensity is smaller than the first light intensity threshold, and 1 is added to the number of times that the statistical comparison result is that the ambient light intensity is smaller than the first light intensity threshold, so as to obtain the current statistical comparison result that the number of times that the ambient light intensity is smaller than the first light intensity threshold is 1.

The second judgment method is as follows: and in the second time period, the comparison results recorded for M times are that the external illumination intensity is not less than the first illumination intensity threshold value, and the comparison results recorded for other times are that the external illumination intensity is less than the first illumination intensity threshold value.

The second duration may be set by a user according to actual needs, or may be set by default by the image capturing apparatus, which is not limited in the embodiment of the present application. For example, the second time period may be 6 seconds.

It should be noted that the first time period and the second time period may be the same or different, and this is not limited in this embodiment of the application.

The M is a positive integer greater than 0, and may be set by a user according to an actual requirement or may be set by default by the image capturing apparatus, which is not limited in the embodiment of the present application. As an example, the value of M may be set to be relatively small, for example, M may be 1.

That is, if the determined ambient light intensity is not less than the first light intensity threshold M times and every other determined ambient light intensity is less than the first light intensity threshold in the second time period, it may be considered that the ambient environment is at an extremely low light intensity most of the time in the second time period, and is only at a light intensity higher than the first light intensity threshold at a certain moment, which may be a case where the light is suddenly turned on and then turned off, the duration is very short and may be ignored, and therefore, it may be determined that the ambient light intensity is continuously lower than the first light intensity threshold.

The third judgment mode is as follows: and in N continuous times, the comparison result recorded each time is that the external illumination intensity is smaller than the first illumination intensity threshold value.

N is a positive integer greater than 0, and N may be set by a user according to an actual requirement, or may be set by default by the image capturing apparatus, which is not limited in the embodiment of the present application. For example, N may be 20.

That is, if the ambient light intensity determined each time is less than the first light intensity threshold value for N consecutive times, it may be considered that the ambient light intensity continues to be at an extremely low light intensity for the N consecutive times, and thus it may be determined that the ambient light intensity continues to be lower than the first light intensity threshold value.

The fourth judgment method: within the continuous N times, the comparison results recorded for K times are that the external illumination intensity is not less than the first illumination intensity threshold value, and the comparison results recorded for other times are that the external illumination intensity is less than the first illumination intensity threshold value.

The K is a positive integer greater than 0, and may be set by a user according to actual needs, or may be set by default by the image capturing apparatus, which is not limited in the embodiment of the present application. As an example, the value of K may be set to be smaller, for example, K may be 2.

That is, if K times of determined external illumination intensities are not less than the first illumination intensity threshold within N consecutive times, and every other determined external illumination intensity is less than the first illumination intensity threshold, it may be considered that the N times of consecutive external environments are mostly at an extremely low illumination intensity, and only K times of the N times of the determined external environments are at an illumination intensity higher than the first illumination intensity threshold, which may be a case where the light is suddenly turned on and then turned off, the duration is very short and can be ignored, and therefore, it may be determined that the external illumination intensity is continuously lower than the first illumination intensity threshold.

In implementation, if it is determined that the external illumination intensity is continuously lower than the first illumination intensity threshold, it may be considered that the external environment is continuously at an extremely low illumination intensity, and the illumination is seriously insufficient, so that a long exposure mode needs to be entered to improve the image quality of the acquired image.

In an implementation, the long exposure mode may include at least one exposure duration, and the specific implementation of entering the long exposure mode may include: the gain of the image pickup apparatus is adjusted to a first gain which is a gain such that noise of the captured image is smaller than a noise threshold. And increasing the exposure time of the camera equipment to obtain one exposure time in the long exposure mode.

It should be noted that the first gain may be set by a user according to big data or experience, or may be set by default by the image capturing apparatus, which is not limited in this embodiment of the application. For example, the first gain may be 38 dB.

It should be noted that the noise threshold may be set by a user according to big data or experience, or may be set by default by the imaging apparatus, which is not limited in the embodiment of the present application. For example, the noise threshold may be 2 dB.

That is to say, after entering the long exposure mode, since the noise of the image acquired by the image capturing apparatus under the first gain is smaller than the noise threshold, the gain of the image capturing apparatus may be first adjusted to the first gain, and then the exposure duration may be increased to obtain an exposure duration under the long exposure mode, where the exposure duration is greater than the exposure duration threshold.

In an implementation, after increasing the exposure time period of the image pickup apparatus, the method further includes: and under the condition that the brightness value of the image acquired based on the increased exposure time length and the first gain is smaller than the expected brightness value and the difference value between the brightness value of the image acquired based on the increased exposure time length and the first gain and the expected brightness value is larger than a second difference threshold value, continuing to increase the exposure time length of the camera equipment to obtain another exposure time length in the long exposure mode. Or, in the case that the brightness value of the image acquired based on the increased exposure time length and the first gain is greater than the desired brightness value, and the difference between the brightness value of the image acquired based on the increased exposure time length and the first gain and the desired brightness value is greater than the second difference threshold, the exposure time length of the image pickup apparatus is reduced, and another exposure time length in the long exposure mode is obtained.

That is to say, after the exposure time length is increased, an image needs to be acquired based on the increased exposure time length and the first gain, the acquired image and the brightness value are compared with the expected brightness value, and if the difference between the brightness value of the acquired image and the expected brightness value is greater than the second difference threshold, it is described that the difference between the brightness of the acquired image and the expected brightness is large, so that it is described that the adjustment of the exposure time length is not enough, the brightness of the image does not reach the expected brightness, and the exposure time length of the image pickup apparatus needs to be adjusted.

As an example, in a case where a difference between a brightness value of an image acquired based on the increased exposure time period and the first gain and a desired brightness value is greater than a second difference threshold, if the brightness value of the image acquired based on the increased exposure time period and the first gain is less than the desired brightness value, it may be considered that the brightness of the acquired image is low, and it is necessary to continue to increase the exposure time period of the image pickup apparatus to obtain another exposure time period in the long exposure mode.

As another example, in a case where a difference between a luminance value of an image acquired based on the increased exposure time period and the first gain and a desired luminance value is greater than a second difference threshold, if the luminance value of the image acquired based on the increased exposure time period and the first gain is greater than the desired luminance value, it may be considered that the luminance of the acquired image is high, and the exposure time period of the image pickup apparatus needs to be reduced to obtain another exposure time period in the long exposure mode.

In implementation, after the exposure time of the image pickup apparatus is adjusted, an image may be acquired based on the adjusted exposure time and the first gain, if a difference between a brightness value of the acquired image and an expected brightness value is greater than a second difference threshold, it is described that the brightness of the currently acquired image does not meet a requirement of the expected brightness, the adjustment of the exposure time is not enough, the exposure time may be continuously adjusted until the difference between the brightness value of the acquired image and the expected brightness value is less than or equal to the second difference threshold, it may be considered that the brightness of the currently acquired image reaches an expected value, the external illumination intensity may be determined according to the current exposure time and the first gain, the determined external illumination intensity is compared with the second illumination intensity threshold, and a comparison result is recorded.

That is, in the long exposure mode, it is still necessary to continuously adjust the exposure duration, determine the external illumination intensity for multiple times, record the comparison result, determine the relationship between the external illumination intensity and the second illumination intensity threshold according to the recorded comparison result, and determine whether the image capturing apparatus exits from the long exposure mode or continues to be in the long exposure mode.

And further, if the external illumination intensity is determined to be continuously higher than the second illumination intensity threshold value according to the recorded comparison result and the external illumination intensity is currently in the long exposure mode, exiting the long exposure mode.

That is, if it is determined that the external illumination intensity is continuously higher than the second illumination intensity threshold according to the recorded comparison result, it may be determined that the external environment is continuously in the condition of higher illumination intensity, and a long exposure time is not required, and if the external environment is currently in the long exposure mode, the long exposure mode may be exited.

It should be noted that the method for determining whether the external illumination intensity is continuously higher than the second illumination intensity threshold is the same as the method for determining that the external illumination intensity is continuously lower than the first illumination intensity threshold in the foregoing embodiment, and specific implementation manners may refer to relevant descriptions of the foregoing embodiment, and are not described herein again in this embodiment of the application.

In some embodiments, exiting the long exposure mode may include: and adjusting the current exposure time of the camera equipment to a specified exposure time, wherein the specified exposure time is less than or equal to an exposure time threshold. And adjusting the current gain of the camera device.

The specified exposure duration may be set by a user according to actual needs, or may be set by default by the image pickup apparatus, which is not limited in the embodiment of the present application. For example, the specified exposure time period may be 60 ms.

That is, exiting the long exposure mode indicates that the current external illumination intensity is sufficient, and the gain can be increased without increasing the exposure duration. Because the quality of the image acquired by the camera under the specified exposure duration is higher, the current exposure duration of the camera can be adjusted to the specified exposure duration, and then the current gain of the camera is increased to be larger than the first gain.

As one example, the adjusted gain may be greater than a gain that minimizes noise of the acquired image.

In implementation, after the current gain of the image capturing apparatus is increased, an image needs to be acquired based on the specified exposure time and the increased gain, and the brightness value of the acquired image is compared with the expected brightness value, if the difference between the brightness value of the acquired image and the expected brightness value is greater than the second difference threshold, it is indicated that the adjustment of the gain is not enough, the brightness of the image does not reach the expected value, and the gain of the image capturing apparatus needs to be continuously adjusted.

As an example, in the case that the difference between the brightness value of the image acquired based on the increased gain and the specified exposure time period and the expected brightness value is greater than the second difference threshold, if the brightness value of the image acquired based on the increased gain and the specified exposure time period is less than the expected brightness value, it may be considered that the brightness of the acquired image is low, and it is necessary to continue to increase the current gain of the image capturing apparatus until the brightness of the acquired image reaches the expected brightness.

As another example, in a case where a difference between a brightness value of an image acquired based on the increased gain and the specified exposure time period and a desired brightness value is greater than a second difference threshold value, if the brightness value of the image acquired based on the increased gain and the specified exposure time period is greater than the desired brightness value, it may be considered that the brightness of the acquired image is high, and the current gain of the image capturing apparatus needs to be reduced until the brightness of the acquired image reaches the desired brightness.

In implementation, after the gain of the image pickup apparatus is adjusted, an image may be acquired based on the adjusted gain and the specified exposure time, if a difference between a brightness value of the acquired image and an expected brightness value is greater than a second difference threshold, it is indicated that the brightness of the currently acquired image does not meet the requirement of the expected brightness, the adjustment of the gain is not enough, the gain may be continuously adjusted until the difference between the brightness value of the acquired image and the expected brightness value is less than or equal to the second difference threshold, it may be considered that the brightness of the currently acquired image reaches the expected brightness, the external illumination intensity may be determined according to the current gain and the specified exposure time, the determined external illumination intensity is compared with the first illumination intensity threshold, and a comparison result is recorded.

That is, after exiting the long exposure mode, it is still necessary to continuously adjust the gain, determine the external illumination intensity for multiple times, record the comparison result, determine the relationship between the external illumination intensity and the first illumination intensity threshold according to the recorded comparison result, and determine whether the image capturing apparatus enters the long exposure mode or continues to be in the current mode.

In other embodiments, if the ambient light intensity is continuously above the second light intensity threshold, the current exposure time may be less than the exposure time threshold. Thus, exiting the long exposure mode includes: keeping the current exposure time length and the gain unchanged, acquiring an image based on the current exposure time length and the gain, and then adjusting the exposure time length and the gain according to the acquired image.

It should be noted that, after exiting the long exposure mode, in the process of increasing the gain, if the gain is increased to the second gain, the brightness of the image acquired based on the second gain and the current exposure time still does not reach the desired brightness, because the noise of the image acquired under the second gain is already large, the gain may not be increased any more, at this time, if the current exposure time is less than the exposure time threshold, the exposure time may be increased until the exposure time is equal to the exposure time threshold, and then the image is continuously acquired for determination.

And if the gain is greater than the second gain, the noise of the acquired image is greater, and the influence on the quality of the image is very great, so that the upper limit of the adjustment of the gain can be controlled to be not greater than the second gain as much as possible.

It should be noted that the second gain may be set by a user according to experience and big data, or may be set by default by the image capturing apparatus, which is not limited in the embodiment of the present application. For example, the second gain may be 50 dB.

By continuously adjusting the shooting parameters of the shooting equipment in the mode, images under different shooting parameters can be collected at different moments, and then a first image which is the same moment as a second image can be obtained.

For example, referring to fig. 2, the step of adjusting the image capturing parameters of the image capturing apparatus may be described as first acquiring the ambient light intensity a plurality of times, and then determining the magnitude relationship between the ambient light intensity and the light intensity threshold. If the external illumination intensity is determined to be continuously lower than the first illumination intensity threshold value, entering a long exposure mode, adjusting the gain to be the first gain, and increasing the exposure duration; and if the external illumination intensity is determined to be continuously higher than the second illumination intensity threshold value, exiting the long exposure mode if the external illumination intensity is currently in the long exposure mode, fixing the exposure duration as the specified exposure duration, and adjusting the gain.

Step 102: if the first image is acquired by the camera equipment in the long exposure mode, the fusion weighting coefficient of the first image and/or the second image is adjusted to obtain a first fusion weighting coefficient of the first image and a second fusion weighting coefficient of the second image, the difference value between the first fusion weighting coefficient and the second fusion weighting coefficient is larger than a first difference threshold value, and the exposure duration in the long exposure mode is larger than an exposure duration threshold value.

The fusion weighting coefficient of the first image and the second image may be set by a user in advance according to actual needs, or may be set by default by the image capturing apparatus, which is not limited in the embodiment of the present application.

The first difference threshold may be set by a user according to actual needs, or may be set by default by the image capturing device, which is not limited in the embodiment of the present application. For example, the first difference threshold may be 5.

Although the first image collected in the long exposure mode includes color, the lower frame rate affects the display effect of the image, and the detail information in the image may be unclear, while the second image has no color, but the detail information is clearer and the frame rate is higher, therefore, the first image and the second image can be fused, the obtained fused image not only can retain the clear detail information on the second image, but also contains color on the first image, the information amount is richer, and in addition, the frame rate of the fused image is higher, thereby avoiding the display effect being affected by image jam.

In implementation, since image acquisition and image fusion are performed in real time, it can be determined whether the first image is acquired in the long exposure mode according to the current imaging parameters of the imaging device. If the first image is captured by the camera device in the long exposure mode, the first image captured in the long exposure mode may be relatively clear, and a smear problem may also occur. Therefore, according to different practical situations, if the first image and the second image need to be subjected to image fusion, the fusion weighting coefficients of the first image and the second image may be respectively adjusted, or only the fusion weighting coefficient of the first image may be adjusted, or only the fusion weighting coefficient of the second image may be adjusted, so as to obtain the first fusion weighting coefficient of the first image and the second fusion weighting coefficient of the second image, and make the difference between the first fusion weighting coefficient and the second fusion weighting coefficient larger, so that image fusion may be performed according to practical needs, so that the fused image is more inclined to the image with better image quality in the first image and the second image, and the image quality of the fused image may be improved.

Under the condition of low illumination intensity, in the process of collecting images through the camera device, images with low frame rate and low noise can be shot by adopting a long exposure mode, and if no moving object is included in the images, the shot images are clearer. However, if a moving object exists in the image, the moving object in the image will have a smear phenomenon of motion blur, resulting in a blurred image. Therefore, it is possible to determine how to adjust the fusion weighting coefficients of the first image and the second image according to whether or not a moving object is included in the second image.

In some embodiments, if the first image is captured by the imaging device in the long exposure mode, it is determined whether the second image includes a moving object. In case the second image comprises a moving object, the fusion weighting coefficient of the first image is decreased and/or the fusion weighting coefficient of the second image is increased, the first fusion weighting coefficient being smaller than the second fusion weighting coefficient.

That is, if the first image is captured in the long exposure mode, it may be determined whether a moving object exists in the second image that has the same capture time as the first image, and if the second image includes the moving object, it may be considered that the smear problem in the first image is serious, and the first image is blurred, so the fusion weighting coefficient of the first image may be decreased and the fusion weighting coefficient of the second image may be increased, or only the fusion weighting coefficient of the first image is decreased, or only the fusion weighting coefficient of the second image is increased, so that the first fusion weighting coefficient is smaller than the second fusion weighting coefficient, that is, the fusion image is more inclined to the second image, the smear problem in the fusion image is reduced, and the sharpness of the fusion image is improved.

In implementation, whether the second image includes a moving object may be determined by means of depth learning, background modeling, image motion detection, and the like.

In other embodiments, if the first image is captured by the camera device in the long exposure mode, it is determined whether the second image includes a moving object. In case the second image does not comprise moving objects, the fusion weighting factor of the first image is increased and/or the fusion weighting factor of the second image is decreased, the first fusion weighting factor being larger than the second fusion weighting factor.

That is, if the first image is captured in the long exposure mode, it may be determined whether a moving object exists in the second image with the same capture time as the first image, and if the moving object is not included in the second image, it is determined that the first image does not include the moving object, and the first image is relatively clear, so the fusion weighting coefficient of the first image may be increased and the fusion weighting coefficient of the second image may be decreased, or only the fusion weighting coefficient of the first image is increased, or only the fusion weighting coefficient of the second image is decreased, so that the first fusion weighting coefficient is greater than the second fusion weighting coefficient, that is, the fusion image is more inclined to the first image, so that the fusion image can reflect the actual situation, and the sharpness of the fusion image is improved.

Further, if the first image is not acquired in the long exposure mode, the smear problem may not be generated in the first image, and in this case, it may be determined whether the second image includes a moving object, the fusion weighting coefficient of the first image is directly increased, and/or the fusion weighting coefficient of the second image is decreased, so that the first fusion weighting coefficient is greater than the second fusion weighting coefficient, and thus, the obtained fusion image is more inclined to the first image, and the external situation can be reflected more truly.

Illustratively, referring to fig. 3, the step of adjusting the fusion weighting coefficients of the first image and the second image may be described as: acquiring a second image, judging whether the first image is acquired in a long exposure mode, if so, judging whether the second image comprises a moving object, and if the second image comprises the moving object, adjusting to enable the first fusion weighting coefficient to be smaller than the second fusion weighting coefficient; if the second image does not include the moving object, the first fusion weighting coefficient can be adjusted to be larger than the second fusion weighting coefficient; if the first image is not acquired in the long exposure mode, the first fusion weighting coefficient may be adjusted to be greater than the second fusion weighting coefficient.

Step 103: and carrying out image fusion on the first image and the second image based on the first fusion weighting coefficient and the second fusion weighting coefficient to obtain a fusion image.

In some embodiments, the pixel value of each pixel point in the first image may be directly multiplied by the first fusion weighting coefficient to obtain a third image, then the pixel value of each pixel point in the second image is multiplied by the second fusion weighting coefficient to obtain a fourth image, and then the third image and the fourth image are superimposed to obtain a fusion image.

In other embodiments, the first image may be color-separated from the luminance image to obtain a color image and a luminance image, the luminance image may be multiplied by the first blending weighting factor to obtain a first luminance image, and the second image may be multiplied by the second blending weighting factor to obtain a second luminance image. And superposing the first brightness image and the second brightness image to obtain a third brightness image, and fusing the third brightness image and the color image to obtain a fused image.

As an example, if the second image includes a moving object, a first motion region of the moving object in the first image and a second motion region of the moving object in the second image may be determined by motion detection, and the first motion region is multiplied by the first fusion weighting coefficient and/or the second motion region is multiplied by the second fusion weighting coefficient during image fusion. And, multiplying the other region in the first image than the first motion region by the fusion weighting coefficient of the first image, and multiplying the other region in the second image than the second motion region by the fusion weighting coefficient of the second image. And then, carrying out image superposition based on the multiplied data to obtain a fused image.

In the process of image fusion, the second image is required to be used as a reference. That is, if the first image is acquired in the long exposure mode, only 1 frame is acquired in 1s, and 15 frames are acquired in 1s for the second image, the 1 frame first image and the 15 frames second image may be respectively subjected to image fusion to obtain 15 frames of fused images.

For example, referring to fig. 3, after the first fusion weighting coefficient and the second fusion weighting coefficient are adjusted, the first image and the second image are image-fused according to the first fusion weighting coefficient and the second fusion weighting coefficient, so as to obtain a fused image.

In the embodiment of the application, a first image and a second image acquired by a camera device are acquired, the first image is acquired without infrared supplementary lighting, and the second image is acquired with infrared supplementary lighting. If the first image is acquired by the image pickup device in the long exposure mode with the exposure duration being greater than the exposure duration threshold, since the image acquired in the long exposure mode may be relatively clear and may also cause a smear problem, the fusion weighting coefficients of the first image and the second image may be respectively adjusted according to different practical situations, or only the fusion weighting coefficient of the first image may be adjusted, or only the fusion weighting coefficient of the second image may be adjusted, so as to obtain the first fusion weighting coefficient of the first image and the second fusion weighting coefficient of the second image. In order to make the resulting fused image closer to the image with better image quality of the first image and the second image, the difference between the first fusion weighting coefficient and the second fusion weighting coefficient may be made larger than the first difference threshold, i.e., the first fusion weighting coefficient and the second fusion weighting coefficient are made to differ greatly. Then, the first image and the second image are subjected to image fusion based on the obtained first fusion weighting coefficient and the second fusion weighting coefficient, so that the obtained fusion image is more inclined to the image with better quality in the first image and the second image, and the image quality of the fusion image is improved.

Fig. 4 is a schematic structural diagram illustrating an image fusion apparatus according to an exemplary embodiment, which may be implemented by software, hardware, or a combination of the two as part or all of an image capturing device. Referring to fig. 4, the apparatus includes: an acquisition module 401, an adjustment module 402 and an image fusion module 403.

An obtaining module 401, configured to obtain a first image and a second image, where the first image is acquired by the camera device without infrared supplementary lighting, and the second image is acquired by the camera device with infrared supplementary lighting;

an adjusting module 402, configured to adjust a fusion weighting coefficient of the first image and/or the second image if the first image is acquired by the image capturing apparatus in the long exposure mode, to obtain a first fusion weighting coefficient of the first image and a second fusion weighting coefficient of the second image, where a difference between the first fusion weighting coefficient and the second fusion weighting coefficient is greater than a first difference threshold, and an exposure duration in the long exposure mode is greater than an exposure duration threshold;

the image fusion module 403 is configured to perform image fusion on the first image and the second image based on the first fusion weighting coefficient and the second fusion weighting coefficient to obtain a fusion image.

In one possible implementation manner of the present application, the adjusting module 402 is configured to:

if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object;

in case the second image comprises a moving object, the fusion weighting coefficient of the first image is decreased and/or the fusion weighting coefficient of the second image is increased, the first fusion weighting coefficient being smaller than the second fusion weighting coefficient.

In one possible implementation manner of the present application, the adjusting module 402 is configured to:

if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object;

in case the second image does not comprise moving objects, the fusion weighting factor of the first image is increased and/or the fusion weighting factor of the second image is decreased, the first fusion weighting factor being larger than the second fusion weighting factor.

In a possible implementation manner of the present application, the obtaining module 401 is further configured to:

determining the external illumination intensity for multiple times;

and if the external illumination intensity is determined to be continuously lower than the first illumination intensity threshold value according to the recorded comparison result, entering a long exposure mode.

In one possible implementation manner of the present application, the ambient light intensity is determined as follows:

determining the determined illumination intensity as the ambient illumination intensity.

In a possible implementation manner of the present application, the obtaining module 401 is further configured to:

determining the current camera shooting parameters as reference camera shooting parameters;

acquiring an image based on the reference camera parameters;

if the difference value between the brightness value of the acquired image and the expected brightness value is larger than a second difference threshold value, adjusting the current shooting parameters of the shooting equipment;

determining the adjusted camera shooting parameters as reference camera shooting parameters, and continuously returning to the step of acquiring images based on the reference camera shooting parameters;

and determining the shooting parameters corresponding to the currently acquired image as target shooting parameters until the difference between the brightness value of the acquired image and the expected brightness value is less than or equal to a second difference threshold.

In a possible implementation manner of the present application, the long exposure mode includes at least one exposure duration, and the obtaining module 401 is further configured to:

adjusting the gain of the camera equipment to be a first gain, wherein the first gain is a gain which enables the noise of the collected image to be smaller than a noise threshold value;

and increasing the exposure time of the camera equipment to obtain one exposure time in the long exposure mode.

In a possible implementation manner of the present application, the obtaining module 401 is further configured to:

under the condition that the brightness value of the image acquired based on the increased exposure time length and the first gain is smaller than the expected brightness value and the difference value between the brightness value of the image acquired based on the increased exposure time length and the first gain and the expected brightness value is larger than a second difference threshold value, continuing to increase the exposure time length of the camera equipment to obtain another exposure time length in the long exposure mode; alternatively, the first and second electrodes may be,

and under the condition that the brightness value of the image acquired based on the increased exposure time length and the first gain is greater than the expected brightness value, and the difference between the brightness value of the image acquired based on the increased exposure time length and the first gain and the expected brightness value is greater than a second difference threshold value, reducing the exposure time length of the camera equipment to obtain another exposure time length in the long exposure mode.

In a possible implementation manner of the present application, the obtaining module 401 is further configured to:

adjusting the current exposure duration of the camera equipment to a specified exposure duration, wherein the specified exposure duration is less than or equal to an exposure duration threshold;

and adjusting the current gain of the camera device.

In the embodiment of the application, a first image and a second image acquired by a camera device are acquired, the first image is acquired without infrared supplementary lighting, and the second image is acquired with infrared supplementary lighting. If the first image is acquired by the image pickup apparatus in the long exposure mode in which the exposure duration is greater than the exposure duration threshold, since the image acquired in the long exposure mode may be relatively clear and may also cause a smear problem, according to an actual situation, the fusion weighting coefficients of the first image and the second image may be respectively adjusted, or only the fusion weighting coefficient of the first image may be adjusted, or only the fusion weighting coefficient of the second image may be adjusted, so as to obtain the first fusion weighting coefficient of the first image and the second fusion weighting coefficient of the second image. In order to make the resulting fused image closer to the image with better image quality of the first image and the second image, the difference between the first fusion weighting coefficient and the second fusion weighting coefficient may be made larger than the first difference threshold, i.e., the first fusion weighting coefficient and the second fusion weighting coefficient are made to differ greatly. Then, the first image and the second image are subjected to image fusion based on the obtained first fusion weighting coefficient and the second fusion weighting coefficient, so that the obtained fusion image is more inclined to the image with better quality in the first image and the second image, and the image quality of the fusion image is improved.

It should be noted that: in the image fusion device provided in the above embodiment, only the division of the above functional modules is taken as an example for performing image fusion, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions. In addition, the image fusion device and the image fusion method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments in detail and are not described herein again.

Fig. 5 is a schematic structural diagram illustrating an image fusion apparatus that may be implemented by software, hardware, or a combination of both as part or all of an image capturing apparatus according to another exemplary embodiment. Referring to fig. 5, the apparatus includes: a first image sensor 501, a second image sensor 502 and a processor 503.

The first image sensor 501 is configured to acquire a first image, where the first image is acquired without infrared supplementary lighting;

the first image sensor 501 may be a visible light image sensor, and the first image may be a visible light image.

The second image sensor 502 is configured to acquire a second image, where the second image is acquired through infrared supplementary lighting;

the second image sensor 502 may be an infrared image sensor, and the second image may be an infrared image.

The processor 503 is configured to adjust the fusion weighting coefficient of the first image and/or the second image if the first image is acquired by the image capturing apparatus in the long exposure mode, to obtain a first fusion weighting coefficient of the first image and a second fusion weighting coefficient of the second image, where a difference between the first fusion weighting coefficient and the second fusion weighting coefficient is greater than a first difference threshold, and an exposure duration in the long exposure mode is greater than an exposure duration threshold. And carrying out image fusion on the first image and the second image based on the first fusion weighting coefficient and the second fusion weighting coefficient to obtain a fusion image.

In one possible implementation manner of the present application, the processor 503 is configured to:

and if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object. In case the second image comprises a moving object, the fusion weighting coefficient of the first image is decreased and/or the fusion weighting coefficient of the second image is increased, the first fusion weighting coefficient being smaller than the second fusion weighting coefficient.

That is, if the first image is captured by the image capturing apparatus in the long exposure mode, the processor may determine whether the second image includes a moving object, and if the second image includes the moving object, it is indicated that the first image also includes the moving object, and in the long exposure mode, the first image including the moving object may have a serious smear problem, so that the fusion weighting coefficient of the first image may be reduced, or the fusion weighting coefficient of the second image may be increased, or the fusion weighting coefficient of the first image may be reduced and the fusion weighting coefficient of the second image may be increased, so that the first fusion weighting coefficient is smaller than the second fusion weighting coefficient, which may make the fused image more inclined to the second image, and improve the image quality of the fused image.

In one possible implementation manner of the present application, the processor 503 is configured to:

and if the first image is acquired by the camera equipment in the long exposure mode, determining whether the second image comprises a moving object. In case the second image does not comprise moving objects, the fusion weighting factor of the first image is increased and/or the fusion weighting factor of the second image is decreased, the first fusion weighting factor being larger than the second fusion weighting factor.

That is, if the first image is captured by the image capturing apparatus in the long exposure mode, the processor may determine whether the second image includes a moving object, and if the second image does not include the moving object, it is determined that the first image does not include the moving object, and in the long exposure mode, the first image that does not include the moving object is clearer, so the fusion weighting coefficient of the first image may be increased, or the fusion weighting coefficient of the second image may be decreased, or the fusion weighting coefficient of the first image may be increased and the fusion weighting coefficient of the second image may be decreased, so that the first fusion weighting coefficient is greater than the second fusion weighting coefficient, which may make the fused image more inclined to the first image, and improve the image quality of the fused image.

In one possible implementation manner of the present application, the processor 503 is further configured to:

and determining the external illumination intensity for multiple times, comparing the currently determined external illumination intensity with an illumination intensity threshold value every time the external illumination intensity is determined, and recording a comparison result, wherein the illumination intensity threshold value comprises a first illumination intensity threshold value and/or a second intensity threshold value. And if the external illumination intensity is determined to be continuously lower than the first illumination intensity threshold value according to the recorded comparison result, entering a long exposure mode.

In one possible implementation manner of the present application, the processor 503 is configured to determine the ambient light intensity by:

and determining target shooting parameters, wherein the difference value between the brightness value of the image acquired by the shooting equipment under the target shooting parameters and the expected brightness value is smaller than or equal to a second difference threshold value. And determining corresponding illumination intensity from the specified mapping relation based on the target shooting parameters, determining the determined illumination intensity as the external illumination intensity, and using the specified mapping relation to indicate the corresponding relation between the shooting parameters and the illumination intensity.

In one possible implementation manner of the present application, the processor 503 is configured to:

determining the current camera shooting parameters as reference camera shooting parameters, and acquiring images based on the reference camera shooting parameters;

In one possible implementation manner of the present application, the processor 503 is configured to:

the method comprises the steps that at least one exposure duration is included in a long exposure mode, the gain of the camera shooting equipment is adjusted to be a first gain, and the first gain is a gain enabling the noise of a collected image to be smaller than a noise threshold value. And increasing the exposure time of the camera equipment to obtain one exposure time in the long exposure mode.

In one possible implementation manner of the present application, the processor 503 is further configured to:

and under the condition that the brightness value of the image acquired based on the increased exposure time length and the first gain is greater than the expected brightness value, and the difference between the brightness value of the image acquired based on the increased exposure time length and the first gain and the expected brightness value is greater than a second difference threshold value, reducing the exposure time length of the camera equipment to obtain another exposure time length in the long exposure mode.

In one possible implementation manner of the present application, the processor 503 is further configured to:

In one possible implementation manner of the present application, the processor 503 is configured to:

and adjusting the current exposure time of the camera equipment to a specified exposure time, wherein the specified exposure time is less than or equal to an exposure time threshold, and adjusting the current gain of the camera equipment.

In the embodiment of the application, a first image and a second image acquired by a camera device are acquired, the first image is acquired without infrared supplementary lighting, and the second image is acquired with infrared supplementary lighting. If the first image is acquired by the image pickup apparatus in the long exposure mode in which the exposure duration is greater than the exposure duration threshold, since the image acquired in the long exposure mode may be relatively clear and may also cause a smear problem, according to an actual situation, the fusion weighting coefficients of the first image and the second image may be respectively adjusted, or only the fusion weighting coefficient of the first image may be adjusted, or only the fusion weighting coefficient of the second image may be adjusted, so as to obtain the first fusion weighting coefficient of the first image and the second fusion weighting coefficient of the second image. In order to make the resulting fused image closer to the image with better image quality of the first image and the second image, the difference between the first fusion weighting coefficient and the second fusion weighting coefficient may be made larger than the first difference threshold, i.e., the first fusion weighting coefficient and the second fusion weighting coefficient are made to differ greatly. Then, the first image and the second image are subjected to image fusion based on the obtained first fusion weighting coefficient and the second fusion weighting coefficient, so that the obtained fusion image is more inclined to the image with better quality in the first image and the second image, and the image quality of the fusion image is improved.

Fig. 6 is a schematic configuration diagram of an image pickup apparatus according to an exemplary embodiment. The image pickup apparatus includes a Central Processing Unit (CPU)601, a system memory 604 including a Random Access Memory (RAM)602 and a Read Only Memory (ROM)603, and a system bus 605 connecting the system memory 604 and the central processing unit 601. The camera device also includes a basic input/output system (I/O system) 606 to facilitate information transfer between various devices within the computer, and a mass storage device 607 for storing an operating system 613, application programs 614, and other program modules 615.

The basic input/output system 606 includes a display 608 for displaying information and an input device 609 such as a mouse, keyboard, etc. for user input of information. Wherein a display 608 and an input device 609 are connected to the central processing unit 601 through an input output controller 610 connected to the system bus 605. The basic input/output system 606 may also include an input/output controller 610 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input/output controller 610 may also provide output to a display screen, a printer, or other type of output device.

The mass storage device 607 is connected to the central processing unit 601 through a mass storage controller (not shown) connected to the system bus 605. The mass storage device 607 and its associated computer-readable media provide non-volatile storage for the imaging device. That is, mass storage device 607 may include a computer-readable medium (not shown), such as a hard disk or CD-ROM drive.

Without loss of generality, computer readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media is not limited to the foregoing. The system memory 604 and mass storage device 607 described above may be collectively referred to as memory.

According to various embodiments of the present application, the image pickup apparatus may also operate by a remote computer connected to a network through a network such as the internet. That is, the image pickup apparatus may be connected to the network 612 through the network interface unit 611 connected to the system bus 605, or may be connected to another type of network or a remote computer system (not shown) using the network interface unit 611.

The memory further includes one or more programs, and the one or more programs are stored in the memory and configured to be executed by the CPU.

In some embodiments, a computer-readable storage medium is also provided, in which a computer program is stored, which, when being executed by a processor, implements the steps of the image fusion method in the above embodiments. For example, the computer readable storage medium may be a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

It is noted that the computer-readable storage medium referred to herein may be a non-volatile storage medium, in other words, a non-transitory storage medium.

It should be understood that all or part of the steps for implementing the above embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The computer instructions may be stored in the computer-readable storage medium described above.

That is, in some embodiments, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the steps of the image fusion method described above.

The above-mentioned embodiments are provided not to limit the present application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

28页详细技术资料下载

Image fusion method and device, camera equipment and storage medium

相关技术

网友询问留言