阅读说明：本技术 一种视频优化处理系统、处理方法、终端设备及存储介质 (video optimization processing system, processing method, terminal device and storage medium ) 是由 李程启 季坤 甄超 李坚林 操松元 赵常威 张骥 于 2019-07-23 设计创作，主要内容包括：本发明公开了一种视频优化处理系统,包括：初始图像库,用于存储原始图像；视频抖动检测模块,用于对原始图像进行检测,判断原始图像是否为抖动图像；视频抖动修正模块,对抖动图像进行修正得到修正图像；图像播放库,用于存储无抖动图像和修正后的修正图像；所述视频抖动检测模块与初始图像库、图像播放库和视频抖动修正模块连接,所述视频抖动修正模块与初始图像库和图像播放库连接。本发明还提供一种视频优化处理系统、处理终端设备及存储介质。本发明通过子区域块的划分,针对每一帧图像,以子区域块为单位进行抖动消除和运动补偿,保证了存在抖动模糊的图像的修复效率和品质,保证视频播放速率。(The invention discloses a video optimization processing system, which comprises: the initial image library is used for storing original images; the video jitter detection module is used for detecting the original image and judging whether the original image is a jittered image; the video jitter correction module is used for correcting the jittered image to obtain a corrected image; the image playing library is used for storing the shake-free image and the corrected image; the video jitter detection module is connected with the initial image library, the image playing library and the video jitter correction module, and the video jitter correction module is connected with the initial image library and the image playing library. The invention also provides a video optimization processing system, processing terminal equipment and a storage medium. The invention carries out the jitter elimination and the motion compensation by taking the sub-area block as a unit aiming at each frame image through the division of the sub-area block, thereby ensuring the repair efficiency and quality of the image with jitter blurring and ensuring the video playing speed.)

1. A video optimization processing system, comprising:

the initial image library is used for storing original images;

the video jitter detection module is used for detecting the original image and judging whether the original image is a jittered image;

The video jitter correction module is used for correcting the jittered image to obtain a corrected image;

The image playing library is used for storing the shake-free image and the corrected image;

The video jitter detection module is connected with the initial image library, the image playing library and the video jitter correction module, and the video jitter correction module is connected with the initial image library and the image playing library.

2. the system of claim 1, wherein the video judder correction module comprises:

the buffer database is used for storing the jitter images copied to the video jitter correction module by the video jitter detection module;

The image dividing unit is used for calling the image from the buffer database and dividing the image into a plurality of sub-area blocks;

The jitter elimination unit is used for calculating the gray gradient of each sub-area block and eliminating the sub-area block with jitter blur according to the gray gradient;

And the motion compensation unit is used for performing motion compensation on the eliminated sub-area blocks through motion estimation and moving the compensated image to an image play library.

3. the system of claim 2, wherein the jitter cancellation unit comprises:

The gray gradient calculation module is used for calculating the gray gradient of each sub-area block;

the gray threshold value calculating module is used for calculating a gradient threshold value according to the gray gradient of each sub-region block; and eliminating sub-region modules with gray gradients smaller than a gradient threshold.

4. the system of claim 2, wherein the jitter cancellation unit comprises:

The gray gradient calculation module is used for calculating the gray gradient of each sub-area block;

and the difference value calculation module is used for calculating the difference value corresponding to each sub-region block according to the difference value calculation model and eliminating the sub-region block corresponding to the difference value larger than the difference value threshold value.

5. The system according to claims 1-4, wherein the video optimization processing system comprises the following steps:

Storing an original image in an initial image library;

Detecting an original image in an initial image library, and judging whether the original image is a jittering image;

correcting the jittering image to obtain a corrected image;

And storing the shake-free image and the corrected image in an image playing library.

6. A video optimization terminal device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, wherein said processor implements a video optimization system according to claim 5 when executing said computer program.

7. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, implements a video optimization processing system according to claim 5.

Technical Field

the present invention relates to the field of video processing technologies, and in particular, to a video optimization processing system, a video optimization processing method, a terminal device, and a storage medium.

background

Video jitter refers to the overall displacement between video frames, thereby affecting a series of subsequent operations such as video impression and compression coding.

there are many existing video jitter detection methods, for example, a video jitter automatic detection method of application No. 201410318324.X, a video jitter detection method and apparatus of application No. 201310747263.4 are used to determine whether to perform anti-shake processing on the video; a video shake detection method based on image gray distribution characteristics, and the like, which are filed as application No. 201610873192.6, all describe video shake detection methods.

Although the above prior art has mentioned a video jitter correction method, most of the methods directly delete the jittered images after detecting the video jitter, so that the corrected video lacks images, which affects the continuity and picture feeling of video playing.

Disclosure of Invention

In view of the above-mentioned deficiencies of the prior art, the present invention provides a video optimization processing system, a terminal device and a storage medium.

the technical scheme adopted by the invention is as follows:

In a first aspect, the present invention provides a video optimization processing system, including:

the initial image library is used for storing original images;

The video jitter detection module is used for detecting the original image and judging whether the original image is a jittered image;

The video jitter correction module is used for correcting the jittered image to obtain a corrected image;

the image playing library is used for storing the shake-free image and the corrected image;

the video jitter detection module is connected with the initial image library, the image playing library and the video jitter correction module, and the video jitter correction module is connected with the initial image library and the image playing library.

In a first possible implementation manner of the first aspect, the video shake correction module includes:

the buffer database is used for storing the jitter images copied to the video jitter correction module by the video jitter detection module;

the image dividing unit is used for calling the image from the buffer database and dividing the image into a plurality of sub-area blocks;

the jitter elimination unit is used for calculating the gray gradient of each sub-area block and eliminating the sub-area block with jitter blur according to the gray gradient;

and the motion compensation unit is used for performing motion compensation on the eliminated sub-area blocks through motion estimation and moving the compensated image to an image play library.

in a second possible implementation manner of the first aspect, the jitter elimination unit includes:

the gray gradient calculation module is used for calculating the gray gradient of each sub-area block;

The gray threshold value calculating module is used for calculating a gradient threshold value according to the gray gradient of each sub-region block; and eliminating sub-region modules with gray gradients smaller than a gradient threshold.

in a third possible implementation of the first aspect, the jitter cancellation unit comprises:

The gray gradient calculation module is used for calculating the gray gradient of each sub-area block;

and the difference value calculation module is used for calculating the difference value corresponding to each sub-region block according to the difference value calculation model and eliminating the sub-region block corresponding to the difference value larger than the difference value threshold value.

in a second aspect, the present invention provides a video optimization processing system, which is characterized by comprising the following steps:

storing an original image in an initial image library;

detecting an original image in an initial image library, and judging whether the original image is a jittering image;

Correcting the jittering image to obtain a corrected image;

and storing the shake-free image and the corrected image in an image playing library.

In a third aspect, the present invention provides a video optimization terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a video optimization processing system as described above when executing the computer program.

In a fourth aspect, the present invention provides a computer-readable storage medium, which stores a computer program, wherein the computer program, when executed by a processor, implements a video optimization processing system as described above.

the invention has the beneficial effects that:

The invention screens the images in the initial image library through the video jitter detection module, so that the video jitter correction module corrects the images with jitter blur, and the efficiency of image correction is improved. Through the division of the sub-area blocks, for each frame image, the sub-area blocks are used as units to perform jitter elimination and motion compensation, the algorithm is simple, the efficiency is high, and the repair efficiency and quality of the image with jitter blur are ensured. Meanwhile, the jitter detection and the jitter correction are separated and synchronously carried out, which is beneficial to further improving the image transfer efficiency in the image playing library, thereby ensuring the video playing speed.

Drawings

fig. 1 is a structural diagram of a video optimization processing system according to the present invention;

Fig. 2 is a structural diagram of a video optimization processing system according to the present invention;

fig. 3 is a flow chart of a video optimization processing system according to the present invention.

Detailed Description

the invention provides a video optimization processing system, which ensures the continuity of stored images in a video playing library and the quality of each frame of image by repairing the image with jitter of each frame, thereby ensuring the quality of video playing and avoiding the problems of video image jumping and blurring.

the foregoing is the core idea of the present application, and in order to make those skilled in the art better understand the scheme of the present application, the present application will be further described in detail with reference to the accompanying drawings. It should be understood that the specific features in the embodiments and examples of the present application are detailed description of the technical solutions of the present application, and are not limited to the technical solutions of the present application, and the technical features in the embodiments and examples of the present application may be combined with each other without conflict.

fig. 1 is a flow chart of a video optimization processing system according to the present invention.

Referring to fig. 1, a video optimization processing system includes:

an initial image library 101 for storing original images;

the video jitter detection module 102 is configured to detect an original image and determine whether the original image is a jittered image;

The video shake correction module 103 corrects the shake image to obtain a corrected image;

an image play library 104 for storing the shake-free image and the corrected image;

the video jitter detection module is connected with the initial image library, the image playing library and the video jitter correction module, and the video jitter correction module is connected with the initial image library and the image playing library.

in the embodiment of the invention, a video jitter detection module is respectively connected with an image play library, an initial image library and a video jitter correction module, and is used for detecting images in the initial image library one by one, copying images without jitter into the image play library and copying images with jitter into the video jitter correction module; the video jitter correction module is also connected with the image playing library and used for moving the image without jitter to the image playing library.

In the embodiment, the video shake detection module is used for screening the images in the initial image library, so that the video shake correction module corrects the images with shake blur, and the efficiency of image correction is improved. In this embodiment, the video jitter detection module detects the video image by using the existing video jitter detection method. In addition, in the embodiment, the jitter detection and the jitter correction are separated and synchronously performed, which is beneficial to further improving the image transfer efficiency in the image playing library, thereby ensuring the video playing speed.

according to the method, through the division of the sub-area blocks, the shake elimination and the motion compensation are carried out on each frame of image by taking the sub-area blocks as units, the algorithm is simple, the efficiency is high, and the repair efficiency and the quality of the image with shake blur are guaranteed.

Referring to fig. 2, a structure diagram of a video optimization processing system according to the present invention is shown;

As shown in fig. 2, the video shake correction module 103 includes:

A buffer database 131 for storing the shake image copied from the video shake detection module to the video shake correction module;

an image dividing unit 132, configured to call an image from the cache database and divide the image into a plurality of sub-region blocks;

a shake elimination unit 133, configured to calculate a gray scale gradient of each sub-region block, and eliminate the sub-region block in which shake blur exists according to the gray scale gradient;

and a motion compensation unit 134 for performing motion compensation on the removed sub-region block through motion estimation, and moving the compensated image to an image play library.

In this embodiment, the video shake correction module is provided with a cache database, and the cache database is used for storing the image copied to the video shake correction module by the video shake detection module. The setting of the cache database is beneficial to avoiding the jitter correction efficiency of the video jitter correction module from interfering with the image screening efficiency of the video jitter detection module, thereby ensuring that the image screening in the initial database and the jitter elimination aiming at a single image are carried out simultaneously and are not interfered with each other, and further improving the image storage efficiency in the image play library.

The video shake correction module is used for dividing the acquired image into a plurality of sub-area blocks and calculating the gray gradient of each sub-area block; the video shake correction module is used for screening the sub-region blocks according to the gray gradient aiming at each frame of image and performing motion compensation on the image subjected to the screening of the sub-region blocks through motion estimation by combining with the image in the initial image library.

the invention repairs the images with jitter in each frame, thereby ensuring the continuity of the stored images in the video playing library and the quality of each frame of images, ensuring the quality of video playing and avoiding the problems of video image jumping and blurring.

In another embodiment of the present invention, the jitter removing unit 403 includes:

A gray gradient calculation module 4031 for calculating the gray gradient of each sub-region block;

a gray threshold calculation module 4032 for calculating a gradient threshold according to the gray gradient of each sub-region block; and eliminating sub-region modules with gray gradients smaller than a gradient threshold.

The method specifically comprises the following steps: the gray gradient calculation module is used for calculating the gray gradient of each sub-region block and calculating a gradient threshold value according to the gray gradient of each sub-region block; the gray threshold calculation module is used for eliminating the sub-region module of which the gray gradient is smaller than the gradient threshold.

The model used by the jitter removal unit to calculate the gradient threshold is:Where a0 is the gradient threshold, n is the number of sub-region blocks, ai is the gray gradient of the ith sub-region block,。

That is, in this embodiment, the shake elimination unit determines that the sub-region module with the gray gradient smaller than the gradient threshold is the sub-region block with shake blur, and eliminates the sub-region block.

In another embodiment of the present invention, a jitter removing unit includes:

A gray gradient calculation module 4033 for calculating the gray gradient of each sub-region block;

and a difference calculation module 4034, configured to calculate a difference value corresponding to each sub-region block according to the difference calculation model, and eliminate the sub-region block corresponding to the difference value greater than the difference threshold.

The method specifically comprises the following steps: the jitter elimination unit is internally provided with a difference value calculation module:

；

wherein n is the number of sub-region blocks,for the gray scale gradient of each sub-region block, c0 is the difference threshold, and ci is the gray scale gradient ofthe difference value corresponding to the sub-region block of (1);

and the difference value calculation module is used for calculating the difference value corresponding to each sub-region block according to the difference value calculation model and eliminating the sub-region block corresponding to the difference value larger than the difference value threshold value. Assuming that c2 and c5 are both larger than c0 in the present embodiment, the shake elimination unit determines that there is shake blur in the sub-region blocks with gray gradients of e3 and e6 and eliminates the shake blur.

in this embodiment, the screening of the sub-region blocks is performed according to the gray gradient difference, so that the screening precision of the video jitter is further improved.

in this embodiment, the video shake detection module is configured to sequentially detect whether each image in the initial image library shakes, and when the image does not shake, the video shake detection module is configured to copy the image in the initial image library to the image playback library. When the image has jitter, the video jitter detection module is used for copying the image to the video jitter correction module and inserting a blank image into the image play library. The video jitter correction module is used for replacing a corresponding blank image in the image playing library with the image after jitter elimination every time one frame of image is eliminated. The blank images are inserted to occupy the jittered images in the play database, so that the images after jitter correction are moved to the storage position in the play database, the arrangement sequence of the images in the play database is consistent with the arrangement sequence of the images in the initial database, and the smoothness of video playing is ensured. Meanwhile, through blank image occupation, the simplicity and high efficiency of inserting the image after the shake correction into the image playing library are ensured, and the interference of the image insertion with other images in the image playing library is avoided.

In the embodiment, by dividing the sub-region blocks, for each frame of image, the sub-region blocks are used as a unit to perform jitter elimination and motion compensation, the algorithm is simple, the efficiency is high, and the efficiency and the quality of repairing the image with jitter blur are ensured.

based on the same inventive concept as the video optimization processing system in the foregoing embodiment, the present invention also provides a video optimization processing system. Referring to fig. 3, a flow chart of a video optimization processing system according to the present invention is shown.

as shown in fig. 3, a video optimization processing system includes the following steps:

Step 201, storing an original image in an initial image library;

Step 202, detecting an original image in an initial image library, and judging whether the original image is a jittered image;

step 203, correcting the jittered image to obtain a corrected image;

Step 204, storing the shake-free image and the corrected image in an image play library.