Image shooting method and device
阅读说明：本技术 一种图像拍摄方法和装置 (Image shooting method and device ) 是由 孙新江 仇芳 张�雄 苗森 皮志明 李宗原 那柏林 曹飞祥 于 2018-08-31 设计创作，主要内容包括：本申请实施例公开了一种图像拍摄方法和装置,涉及通信技术领域,解决了现有技术中路人或朋友的摄影技巧未达到用户期望时,无法拍出满足用户个性化需求的照片,导致终端的拍照效率较低的问题。具体方案为：基于卷积神经网络运算获取第一图像中的目标人物的第一身体特征信息；根据第一身体特征信息生成与第一图像对应的第一特征参数；若第一特征参数在预设的目标特征参数的范围之外,获取第一特征参数和目标特征参数的上限或下限的第一偏差信息；根据第一偏差信息生成第一提示信息；第一提示信息用于引导拍摄者移动电子设备以拍摄目标人物。(The embodiment of the application discloses an image shooting method and device, relates to the technical field of communication, and solves the problem that in the prior art, when the photographic skills of passers-by or friends do not meet the user expectation, a photo meeting the personalized requirements of a user cannot be shot, so that the shooting efficiency of a terminal is low. The specific scheme is as follows: acquiring first body feature information of a target person in the first image based on convolutional neural network operation; generating a first characteristic parameter corresponding to the first image according to the first body characteristic information; if the first characteristic parameter is out of the range of the preset target characteristic parameter, acquiring first deviation information of the upper limit or the lower limit of the first characteristic parameter and the target characteristic parameter; generating first prompt information according to the first deviation information; the first prompt message is used for guiding the photographer to move the electronic equipment to photograph the target person.)
An image capturing method applied to an electronic apparatus having an image capturing function, the method comprising:
acquiring first body feature information of a target person in the first image based on convolutional neural network operation;
generating a first characteristic parameter corresponding to the first image according to the first body characteristic information, wherein the first characteristic parameter is used for identifying position information of the image corresponding to the target person in the first image and pitch angle information of the electronic equipment when the electronic equipment shoots the target person;
if the first characteristic parameter is out of the range of a preset target characteristic parameter, acquiring first deviation information of the first characteristic parameter and the upper limit or the lower limit of the target characteristic parameter;
generating first prompt information according to the first deviation information; the first prompt message is used for guiding a photographer to move the electronic equipment to photograph the target person.
The image capturing method according to claim 1, before the step of acquiring the first body feature information of the target person in the first image based on a convolutional neural network operation, further comprising:
performing face recognition on the target person based on convolutional neural network operation;
if the face of the target person is identified, acquiring the first body feature information;
and if the face of the target person is not recognized, terminating.
The image capturing method according to claim 1 or 2, wherein the first body feature information is a plurality of key points of the target person; before the step of generating a first feature parameter corresponding to the first image according to the first body feature information, the method further includes:
determining the reasonability of a human body frame formed by connecting the plurality of key points based on the operation of a convolutional neural network;
if the human body frame of the target person is reasonable, generating a first characteristic parameter corresponding to the first image according to the first body characteristic information;
and if the human body frame of the target person is not reasonable, terminating.
The image capturing method according to any one of claims 1 to 3, characterized in that the first feature parameter is generated in a case where a pose of the target person in the first image satisfies a preset condition.
The image capturing method according to claim 4, wherein the preset condition includes: the target person is the whole body and is in a standing posture.
The image capturing method according to any one of claims 1 to 5, characterized in that the method further comprises:
acquiring second body feature information of the target person in a second image based on convolutional neural network operation; the second image is the image of the target person shot after the electronic equipment is adjusted according to the first prompt information;
generating a second characteristic parameter corresponding to the second image according to the second body characteristic information;
if the second characteristic parameter is out of the range of the preset target characteristic parameter, second deviation information of the second characteristic parameter and the upper limit or the lower limit of the target characteristic parameter is obtained;
generating second prompt information according to the second deviation information; the second prompt message is used for guiding a photographer to move the electronic equipment to photograph the target person.
The image capturing method according to any one of claims 4 to 6,
if the number of the target persons in the first image is multiple, generating a first characteristic parameter corresponding to the first image according to the first body characteristic information comprises:
if the proportion of the persons with the positions meeting the preset conditions in the target person is larger than or equal to the preset proportion; generating a first characteristic parameter corresponding to the first image according to the first body characteristic information.
The image capturing method according to any one of claims 1 to 7, wherein the first body feature information includes a left ankle key point and a right ankle key point of the target person in the first image, and the first feature parameter includes an ankle position y of the target person in the first image in a preset coordinate systemankleAnd a shooting pitch angle beta of the electronic device, wherein the target characteristic parameter comprises a reference ankle position y of the target person in the preset coordinate system0And a reference photographing pitch angle beta of the electronic device0The first deviation information includes: the y-axis direction deviation Δ y and the shooting pitch angle deviation Δ β, and correspondingly, the acquiring of the first deviation information of the upper limit or the lower limit of the first characteristic parameter and the target characteristic parameter includes:
according to the reference ankle position y of the target person0And the ankle position y of the target personankleCalculating a difference value to obtain the deviation delta y in the y-axis direction; according to the reference shooting pitch angle beta0And the upper limit or the lower limit of (3) and the photographingAnd solving a difference value of the pitch angle beta to obtain the shooting pitch angle deviation delta beta.
The image capturing method according to claim 8, wherein the first body feature information further includes an overhead key point of the target person in the first image, and the first feature parameter further includes a horizontal position x of the target person in the first image in a preset coordinate systemheadAnd a height h of the character imagesThe target characteristic parameter further comprises a reference horizontal position x of the target person in the preset coordinate system0And a reference character image height hs0The first deviation information further includes: the x-axis direction deviation Δ x and the distance deviation Δ z, and accordingly, the acquiring of the first deviation information of the upper limit or the lower limit of the first characteristic parameter and the target characteristic parameter includes:
according to the reference horizontal position x of the target person0And the horizontal position x of the target personheadCalculating a difference value to obtain the deviation delta x in the x-axis direction; according to the reference person image height h of the target persons0And the height h of the person image of the target personsAnd calculating a difference value to obtain the distance deviation delta z.
The image capturing method according to claim 8,
if the number of the target characters is one, yankleThe vertical coordinates of the lower points of the key points of the left ankle and the right ankle of the target person are shown; the beta is a shooting pitch angle of the first image shot by the electronic equipment;
if the number of the target characters is multiple, yankleA vertical coordinate of a lowest point of a plurality of the target person's left ankle keypoints and right ankle keypoints; the beta is a shooting pitch angle of the first image shot by the electronic equipment.
The image capturing method according to claim 9,
if the number of the target characters is one, the x isheadThe abscissa of the key point at the top of the head of the target person is taken as the abscissa; h issIs said yankleThe difference value of the head top key point vertical coordinate of the target person;
if the number of the target characters is multiple, the xheadAveraging the abscissas of the vertex keypoints of at least two of the plurality of target characters; h issIs said yankleA difference from a vertical coordinate of a highest point among the vertex keypoints of the plurality of target characters.
The image capturing method according to any one of claims 1 to 11, wherein the first prompt information includes: movement indication information and/or rotation indication information, wherein the movement indication information is used for indicating a photographer to move the electronic equipment; the rotation indication information is used for indicating a photographer to rotate the electronic equipment.
The image capturing method according to any one of claims 1 to 12, wherein if the number of the target person is one, the method further includes:
acquiring a human face yaw angle of the target person;
if the human face yaw angle is within the range of the preset angle interval, the reference horizontal position x0Is a first predetermined threshold;
if the human face yaw angle is smaller than the minimum value of the preset angle interval range, the reference horizontal position x0Is a second preset threshold value, and the second preset threshold value is greater than the first preset threshold value; if the human face yaw angle is larger than the maximum value of the range of the preset angle interval, the reference horizontal position x0Is a third preset threshold, which is smaller than the first preset threshold; alternatively, the first and second electrodes may be,
if the human face yaw angle is smaller than the minimum value of the preset angle interval range, the reference horizontal position x0Is that it isA third preset threshold; if the human face yaw angle is larger than the maximum value of the range of the preset angle interval, the reference horizontal position x0And is the second preset threshold.
The image capturing method according to claims 1 to 13, wherein generating first prompt information based on the first deviation information includes:
acquiring state information of the electronic equipment through a sensor;
and generating the first prompt message according to the state information and the first deviation information.
The image capturing method according to claim 12, wherein the sensor includes: at least one of a pressure sensor, a gyroscope sensor, an air pressure sensor, a magnetic sensor, a gravitational acceleration sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, or a bone conduction sensor.
An image photographing apparatus, comprising an arithmetic array and a central processing unit CPU,
the operation array is used for acquiring first body characteristic information of a target person in the first image based on convolutional neural network operation;
the CPU is used for generating a first characteristic parameter corresponding to the first image according to the first body characteristic information, and the first characteristic parameter is used for identifying the position information of the image corresponding to the target person in the first image and the shooting pitch angle information of the electronic equipment; if the first characteristic parameter is out of the range of a preset target characteristic parameter, acquiring first deviation information of the first characteristic parameter and the upper limit or the lower limit of the target characteristic parameter; generating first prompt information according to the first deviation information; the first prompt message is used for guiding a photographer to move the electronic equipment to photograph the target person.
The image capturing apparatus according to claim 16, wherein the operation array is further configured to perform face recognition on the target person based on a convolutional neural network operation; if the face of the target person is identified, acquiring the first body feature information; and if the face of the target person is not recognized, terminating.
The image capturing apparatus according to claim 16 or 17, wherein the first body feature information is a plurality of key points of the target person;
the operation array is also used for determining the reasonability of a human body frame formed by connecting the plurality of key points based on the operation of a convolutional neural network; if the human body frame of the target person is reasonable, generating a first characteristic parameter corresponding to the first image according to the first body characteristic information; and if the human body frame of the target person is not reasonable, terminating.
The image capturing apparatus according to any one of claims 16 to 18, wherein the first feature parameter is generated in a case where a pose of the target person in the first image satisfies a preset condition.
The image capturing apparatus according to claim 19, wherein the preset condition includes: the target person is the whole body and is in a standing posture.
The image capturing apparatus according to any one of claims 16 to 20,
the operation array is further used for acquiring second body characteristic information of the target person in a second image based on convolutional neural network operation; the second image is the image of the target person shot after the electronic equipment is adjusted according to the first prompt information;
the CPU is further used for generating a second characteristic parameter corresponding to the second image according to the second body characteristic information; if the second characteristic parameter is out of the range of the preset target characteristic parameter, second deviation information of the second characteristic parameter and the upper limit or the lower limit of the target characteristic parameter is obtained; generating second prompt information according to the second deviation information; the second prompt message is used for guiding a photographer to move the electronic equipment to photograph the target person.
The image capturing apparatus according to any one of claims 19 to 21,
the CPU is specifically configured to generate a first characteristic parameter corresponding to the first image according to the first body characteristic information if the proportion occupied by the person whose posture in the target person meets the preset condition is greater than or equal to a preset proportion.
The image capturing apparatus as claimed in any one of claims 16 to 22, wherein the first feature information includes a key point of a left ankle and a key point of a right ankle of the target person in the first image, and the first feature parameter includes an ankle position y of the target person in the first image in a predetermined coordinate systemankleAnd a shooting pitch angle beta of the electronic device, wherein the target characteristic parameter comprises a reference ankle position y of the target person in the preset coordinate system0And a reference photographing pitch angle beta of the electronic device0The first deviation information includes: the deviation delta y of the y-axis direction and the deviation delta beta of the shooting pitch angle,
the CPU is specifically used for referencing the ankle position y of the target person0And the ankle position y of the target personankleCalculating a difference value to obtain the deviation delta y in the y-axis direction; according to the reference shooting pitch angle beta0And calculating a difference value between the upper limit or the lower limit of the pitch angle and the shooting pitch angle beta to obtain the shooting pitch angle deviation delta beta.
The image capture device of claim 23, wherein the second component is a lens assemblyThe body feature information further comprises the key point of the head of the target person in the first image, and the first feature parameter further comprises the horizontal position x of the target person in the first image in a preset coordinate systemheadAnd a height h of the character imagesThe target characteristic parameter further comprises a reference horizontal position x of the target person in the preset coordinate system0And a reference character image height hs0The first deviation information further includes: the deviation Delta x in the direction of the x axis and the distance deviation Delta z,
the CPU is specifically used for determining the reference horizontal position x of the target person0And the horizontal position x of the target personheadCalculating a difference value to obtain the deviation delta x in the x-axis direction; according to the reference person image height h of the target persons0And the height h of the person image of the target personsAnd calculating a difference value to obtain the distance deviation delta z.
The image capturing apparatus according to claim 23,
if the number of the target characters is one, yankleThe vertical coordinates of the lower points of the key points of the left ankle and the right ankle of the target person are shown; the beta is a shooting pitch angle of the first image shot by the electronic equipment;
if the number of the target characters is multiple, yankleA vertical coordinate of a lowest point of the left ankle keypoints and the right ankle keypoints of the plurality of target characters; the beta is a shooting pitch angle of the first image shot by the electronic equipment.
The image capturing apparatus according to claim 24,
if the number of the target characters is one, the x isheadThe abscissa of the key point at the top of the head of the target person is taken as the abscissa; h issIs said yankleThe difference value of the head top key point vertical coordinate of the target person;
if the target person isA plurality of, xheadAveraging the abscissa of the vertex key points of at least two of the plurality of target characters; h issIs said yankleA difference from a vertical coordinate of a highest point among the vertex keypoints of the plurality of target characters.
The image capturing apparatus according to any one of claims 16 to 26, wherein the first prompt information includes: movement indication information and/or rotation indication information, wherein the movement indication information is used for indicating a photographer to move the electronic equipment; the rotation indication information is used for indicating a photographer to rotate the electronic equipment.
The image capturing apparatus as claimed in any one of claims 16 to 27, wherein the operation array is further configured to obtain a yaw angle of the target person if the number of the target persons is one;
if the human face yaw angle is within the range of the preset angle interval, the reference horizontal position x0Is a first preset threshold value;
if the human face yaw angle is smaller than the minimum value of the preset angle interval range, the reference horizontal position x0Is a second preset threshold value, and the second preset threshold value is greater than the first preset threshold value; if the human face yaw angle is larger than the maximum value of the range of the preset angle interval, the reference horizontal position x0Is a third preset threshold, which is smaller than the first preset threshold; alternatively, the first and second electrodes may be,
if the human face yaw angle is smaller than the minimum value of the preset angle interval range, the reference horizontal position x0The third preset threshold value is set; if the human face yaw angle is larger than the maximum value of the range of the preset angle interval, the reference horizontal position x0And is the second preset threshold.
The image capturing device according to any one of claims 16 to 28, wherein the CPU is configured to obtain status information of the electronic apparatus via a sensor; and generating the first prompt message according to the state information and the first deviation information.
The image capturing apparatus according to claim 29, wherein the sensor includes: at least one of a pressure sensor, a gyroscope sensor, an air pressure sensor, a magnetic sensor, a gravitational acceleration sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, or a bone conduction sensor.
An image capturing apparatus, characterized in that the apparatus comprises:
the acquiring unit is used for acquiring first body characteristic information of a target person in the first image based on convolutional neural network operation;
the processing unit is used for generating a first characteristic parameter corresponding to the first image according to the first body characteristic information, wherein the first characteristic parameter is used for identifying the position information of the image corresponding to the target person in the first image and the shooting pitch angle information of the electronic equipment; if the first characteristic parameter is out of the range of a preset target characteristic parameter, acquiring first deviation information of the first characteristic parameter and the upper limit or the lower limit of the target characteristic parameter; generating first prompt information according to the first deviation information; the first prompt message is used for guiding a photographer to move the electronic equipment to photograph the target person.
The image capturing apparatus of claim 31, wherein the processing unit is further configured to perform face recognition on the target person based on a convolutional neural network operation; if the face of the target person is identified, acquiring the first body feature information; and if the face of the target person is not recognized, terminating.
The image capturing apparatus according to claim 31 or 32, wherein the first body feature information is a plurality of key points of the target person;
the processing unit is further used for determining the reasonability of a human body frame formed by connecting the plurality of key points based on convolutional neural network operation; if the human body frame of the target person is reasonable, generating a first characteristic parameter corresponding to the first image according to the first body characteristic information; and if the human body frame of the target person is not reasonable, terminating.
The image capturing apparatus according to any one of claims 31 to 33, wherein the first feature parameter is generated in a case where a pose of the target person in the first image satisfies a preset condition.
The image capturing apparatus according to claim 34, wherein the preset condition includes: the target person is the whole body and is in a standing posture.
The image capturing apparatus according to any one of claims 31 to 35,
the acquisition unit is further used for acquiring second body characteristic information of the target person in a second image based on convolutional neural network operation; the second image is the image of the target person shot after the electronic equipment is adjusted according to the first prompt information;
the processing unit is further used for generating a second characteristic parameter corresponding to the second image according to the second body characteristic information; if the second characteristic parameter is out of the range of the preset target characteristic parameter, second deviation information of the second characteristic parameter and the upper limit or the lower limit of the target characteristic parameter is obtained; generating second prompt information according to the second deviation information; the second prompt message is used for guiding a photographer to move the electronic equipment to photograph the target person.
The image capturing apparatus according to any one of claims 34 to 36,
the processing unit is specifically configured to generate a first feature parameter corresponding to the first image according to the first body feature information if the proportion occupied by the person whose posture in the target person meets the preset condition is greater than or equal to a preset proportion.
The image capturing apparatus as claimed in any one of claims 31 to 37, wherein the first feature information includes a key point of a left ankle and a key point of a right ankle of the target person in the first image, and the first feature parameter includes an ankle position y of the target person in the first image in a predetermined coordinate systemankleAnd a shooting pitch angle beta of the electronic device, wherein the target characteristic parameter comprises a reference ankle position y of the target person in the preset coordinate system0And a reference photographing pitch angle beta of the electronic device0The first deviation information includes: the deviation delta y of the y-axis direction and the deviation delta beta of the shooting pitch angle,
the processing unit is specifically configured to determine a reference ankle position y of the target person0And the ankle position y of the target personankleCalculating a difference value to obtain the deviation delta y in the y-axis direction; according to the reference shooting pitch angle beta0And calculating a difference value between the upper limit or the lower limit of the pitch angle and the shooting pitch angle beta to obtain the shooting pitch angle deviation delta beta.
The image capturing apparatus as claimed in claim 38, wherein the first body feature information further includes an overhead key point of the target person in the first image, and the first feature parameter further includes a horizontal position x of the target person in the first image in a preset coordinate systemheadAnd a height h of the character imagesThe target characteristic parameter further comprises a reference horizontal position x of the target person in the preset coordinate system0And a reference character image height hs0The first deviation information further includes: deviation in x-axis directionThe difference Deltax and the near-far distance deviation Deltaz,
the processing unit is specifically configured to determine the reference horizontal position x of the target person0And the horizontal position x of the target personheadCalculating a difference value to obtain the deviation delta x in the x-axis direction; according to the reference person image height h of the target persons0And the height h of the person image of the target personsAnd calculating a difference value to obtain the distance deviation delta z.
The image capturing apparatus according to claim 38,
if the number of the target characters is one, yankleThe vertical coordinates of the lower points of the key points of the left ankle and the right ankle of the target person are shown; the beta is a shooting pitch angle of the first image shot by the electronic equipment;
if the number of the target characters is multiple, yankleA vertical coordinate of a lowest point of a plurality of the target person's left ankle keypoints and right ankle keypoints; the beta is a shooting pitch angle of the first image shot by the electronic equipment.
The image capturing apparatus according to claim 39,
if the number of the target characters is one, the x isheadThe abscissa of the key point at the top of the head of the target person is taken as the abscissa; h issIs said yankleThe difference value of the head top key point vertical coordinate of the target person;
if the number of the target characters is multiple, the xheadAveraging the abscissas of the vertex keypoints of at least two of the plurality of target characters; h issIs said yankleA difference from a vertical coordinate of a highest point among the vertex keypoints of the plurality of target characters.
The image capturing apparatus according to any one of claims 31 to 41, wherein the first prompt information includes: movement indication information and/or rotation indication information, wherein the movement indication information is used for indicating a photographer to move the electronic equipment; the rotation indication information is used for indicating a photographer to rotate the electronic equipment.
The image capturing apparatus as claimed in any one of claims 31 to 42, wherein the obtaining unit is further configured to obtain a yaw angle of the face of the target person if the number of the target persons is one;
if the human face yaw angle is within the range of the preset angle interval, the reference horizontal position x0Is a first preset threshold value;
if the human face yaw angle is smaller than the minimum value of the preset angle interval range, the reference horizontal position x0Is a second preset threshold value, and the second preset threshold value is greater than the first preset threshold value; if the human face yaw angle is larger than the maximum value of the range of the preset angle interval, the reference horizontal position x0Is a third preset threshold, which is smaller than the first preset threshold; alternatively, the first and second electrodes may be,
if the human face yaw angle is smaller than the minimum value of the preset angle interval range, the reference horizontal position x0The third preset threshold value is set; if the human face yaw angle is larger than the maximum value of the range of the preset angle interval, the reference horizontal position x0And is the second preset threshold.
The image capturing device of any one of claims 31 to 43, wherein the processing unit is specifically configured to obtain status information of the electronic device via a sensor; and generating the first prompt message according to the state information and the first deviation information.
The image capture device of claim 44, wherein the sensor comprises: at least one of a pressure sensor, a gyroscope sensor, an air pressure sensor, a magnetic sensor, a gravitational acceleration sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, or a bone conduction sensor.
A computer storage medium having computer program code stored therein, which when run on a processor causes the processor to perform the image capturing method according to any one of claims 1-15.
- 上一篇：一种医用注射器针头装配设备
- 下一篇：车载照相机系统、车辆用灯具