Shooting adjustment method and device of video shooting equipment and electronic equipment

Abstract

The present application discloses a shooting adjustment method, device and electronic device of a video shooting device, including: obtaining at least one video image, wherein the video image contains at least one person; obtaining image position information of multiple key points in the video image, wherein the key points correspond to designated body parts of the person; obtaining target posture information of the person and person relative position information of the person in the video image according to the image position information of the multiple key points; adjusting the shooting parameters of the video shooting device according to the target posture information and the person relative position information, wherein the shooting parameters at least include shooting direction and shooting position; and shooting the video image using the adjusted shooting parameters. The method enables the video shooting device to quickly follow the person's posture and dynamically adjust its own shooting parameters to adapt to the shooting scene and the person's posture, and avoids the problem that the shooting may need to be interrupted when the person is manually operating.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet live broadcast technology, and more specifically, to a method, device and electronic device for adjusting the shooting of a video shooting device. The present application also relates to a video shooting device. Background Art

[0002] At present, when users are broadcasting live or recording, they usually use mobile terminals or personal computers as video capture devices. In this case, when starting to shoot a video, the user is generally required to manually adjust the shooting parameters of the video capture device according to the changes in the shooting scene and their own posture; and in the process of shooting a video, when the user's own posture changes, it is also necessary to interrupt the live broadcast and manually adjust the video capture device to the corresponding posture before continuing to shoot the video. Therefore, the existing video capture device at least has the problem of not being able to dynamically adjust its own shooting parameters according to the shooting scene or the user's posture. Summary of the invention

[0003] One purpose of the embodiments of the present disclosure is to provide a new technical solution for adjusting shooting parameters of a video shooting device.

[0004] According to a first aspect of the present disclosure, a shooting adjustment method for a video shooting device is provided, the method comprising:

[0005] Acquire at least one video image, wherein the video image includes at least one person;

[0006] Acquire image position information of a plurality of key points in the video image, wherein the key points correspond to designated body parts of the person;

[0007] According to the image position information of the multiple key points, target posture information of the person and relative position information of the person in the video image are obtained;

[0008] According to the target posture information and the person's relative position information, adjusting the shooting parameters of the video shooting device, the shooting parameters at least including a shooting direction and a shooting position;

[0009] Use the adjusted shooting parameters to shoot video images.

[0010] Optionally, obtaining target posture information of the person according to the image position information of the multiple key points includes:

[0011] Obtaining the number of key points according to the image position information of the plurality of key points;

[0012] According to the number of key points, target posture information of the character is obtained.

[0013] Optionally, obtaining the target posture information of the character based on the number of key points includes: when the number of key points is less than a preset threshold number, determining that the target posture information is first posture information representing a sitting posture; and when the number of key points is not less than the preset threshold number, determining that the target posture information is second posture information representing a standing posture.

[0014] Optionally, the at least one video image satisfies at least one of the following conditions: the number of the at least one video image is not less than a preset number, and the duration corresponding to the at least one video image is not less than a preset duration.

[0015] Optionally, the body parts include head parts; and obtaining the relative position information of the person in the video image based on the image position information of the multiple key points includes: acquiring image position data of the head part of the person from the image position information of the multiple key points, wherein the image position data represents the position of the head part of the person in the video image; and obtaining the relative position information of the person based on the image position data.

[0016] Optionally, obtaining the relative position information of the person according to the image position data includes at least one of the following: when the image position data indicates that the head part of the person is in a first preset area of ​​the video image, determining the relative position information of the person as first relative position information, wherein the first relative position information indicates that the height of the image acquisition device of the video shooting equipment is higher than the head part of the person; when the position data indicates that the head part of the person is in a second preset area of ​​the video image, determining the relative position information of the person as second relative position information, wherein the second relative position information indicates that the height of the image acquisition device is lower than the head part of the person; when the position data indicates that the head part of the person is in a third preset area of ​​the video image, determining the relative position information of the person as third relative position information, wherein the third relative position information indicates that the image acquisition device is located on the right side of the person; when the position data indicates that the head part of the person is in a fourth preset area of ​​the video image, determining the relative position information of the person as fourth pair of position information, wherein the fourth relative position information indicates that the image acquisition device is located on the left side of the person.

[0017] Optionally, adjusting the shooting parameters of the video shooting device according to the target posture information and the relative position information of the person includes: adjusting the posture of the display device of the video shooting device according to the target posture information; and adjusting the shooting parameters of the image acquisition device of the video shooting device according to the relative position information of the person.

[0018] Optionally, adjusting the posture of the display device of the video capture device according to the target posture information includes: when the target posture information is first posture information representing a standing posture, adjusting the display device of the video capture device to a vertical screen display mode; and when the target posture information is second posture information representing a sitting posture, adjusting the display device to a horizontal screen display mode.

[0019] Optionally, adjusting the shooting parameters of the image acquisition device of the video shooting equipment according to the relative position information of the person includes at least one of the following: when the relative position information of the person is the first relative position information of the person, controlling the image acquisition device to move vertically downward; when the relative position information of the person is the second relative position information of the person, controlling the image acquisition device to move vertically upward; when the relative position information of the person is the third relative position information of the person, controlling the image acquisition device to move horizontally to the left; and when the relative position information of the person is the fourth relative position information of the person, controlling the image acquisition device to move horizontally to the right.

[0020] Optionally, adjusting the shooting parameters of the image acquisition device of the video shooting equipment according to the relative position information of the person includes: obtaining a displacement value, where the displacement value is used to indicate the moving distance of the image acquisition device; and adjusting the shooting parameters of the image acquisition device according to the relative position information of the person and the displacement value.

[0021] Optionally, during the process of adjusting the shooting parameters of the video shooting device, the method further includes: receiving a first input for confirming current shooting parameters; in response to the first input, stopping adjusting the shooting parameters, and using the shooting parameters at the current moment as the shooting parameters of the video shooting device.

[0022] Optionally, there is at least one of the target posture information and the person's relative position information, and the at least one target posture information and the at least one person's relative position information correspond to the at least one person respectively; adjusting the shooting parameters of the video shooting device according to the target posture information and the person's relative position information includes: adjusting the shooting parameters of the video shooting device according to the at least one target posture information and the at least one person's relative position information.

[0023] Optionally, after adjusting the shooting parameters, the method further includes: obtaining a character identification of the person in the video image; obtaining mapping data according to a correspondence between the character identification and the adjusted shooting parameters; and storing the mapping data.

[0024] Optionally, after acquiring the at least one video image, the method further includes: acquiring a character identification of the character in the video image; obtaining preset shooting parameters corresponding to the character based on the character identification; and adjusting shooting parameters of the video shooting device based on the preset shooting parameters.

[0025] Optionally, before adjusting the shooting parameters, the method further includes: obtaining object relative position information of the target object in the video image, wherein the target object is an object other than the person contained in the video image, and the ratio of image pixels corresponding to the target object to foreground pixels of the video image is not less than a preset pixel ratio; adjusting the shooting parameters of the video shooting device according to the target posture information and the person relative position information includes: adjusting the shooting parameters of the video shooting device according to the target posture information, the person relative position information and the object relative position information.

[0026] Optionally, during the process of shooting video images using the adjusted shooting parameters, the method further includes: receiving a second input for adjusting the current shooting parameters; and adjusting the shooting parameters of the video shooting device in response to the second input.

[0027] According to a second aspect of the present disclosure, there is also provided a video shooting device, including:

[0028] An image acquisition device, used for acquiring video images;

[0029] An image transmission device, used for transmitting the video image to a server in real time;

[0030] A control module is used to adjust the shooting parameters of the image acquisition device according to the method described in the first aspect of the present disclosure.

[0031] Optionally, the video shooting equipment further includes: a display device, which is connected to the image acquisition device and is used to receive and display the video image.

[0032] According to a third aspect of the present disclosure, there is also provided a shooting adjustment device for a video shooting device, comprising:

[0033] An image acquisition module, used to acquire at least one video image, wherein the video image contains at least one person;

[0034] An image position information acquisition module, used to acquire image position information of a plurality of key points in the video image, wherein the key points correspond to designated body parts of the person;

[0035] An information processing module, used for obtaining target posture information of the person and relative position information of the person in the video image according to the image position information of the multiple key points;

[0036] A parameter adjustment module, used to adjust the shooting parameters of the video shooting device according to the target posture information and the person's relative position information, wherein the shooting parameters at least include a shooting direction and a shooting position;

[0037] The image shooting module is used to shoot video images using the adjusted shooting parameters.

[0038] According to a fourth aspect of the present disclosure, an electronic device is further provided, comprising the apparatus according to the third aspect of the present disclosure; or comprising:

[0039] A memory for storing executable instructions;

[0040] The processor is used to operate the electronic device to execute the method according to the first aspect of the present disclosure under the control of the executable instructions.

[0041] According to a fifth aspect of the present disclosure, a computer-readable storage medium is further provided, wherein the computer-readable storage medium stores a computer program that can be read and executed by a computer, and the computer program is used to execute the method according to the first aspect of the present disclosure when read and executed by the computer.

[0042] According to an embodiment of the present disclosure, when a user starts shooting a video or in the process of shooting a video, by obtaining at least one video image containing at least one person, and by obtaining the image position information of multiple key points corresponding to the specified body parts of the person contained in the video image, the target posture information of the person and the person's relative position information in the video image can be obtained according to the image position information, and then according to the target posture information and the person's relative position information, the video shooting device can automatically adjust its own shooting parameters, and shoot the video image using the adjusted shooting parameters. This method can enable the video shooting device to quickly follow the person's posture and dynamically adjust its own shooting parameters to adapt to the recording scene and the person's posture, avoiding the problem that the live broadcast may need to be interrupted when the person manually operates.

[0043] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0045] Figure 1 It is a schematic diagram of the structure of a video shooting device provided in an embodiment of the present disclosure.

[0046] Figure 2 It is a scene schematic diagram of the shooting adjustment method of the video shooting device provided in an embodiment of the present disclosure.

[0047] Figure 3 It is a flowchart of a shooting adjustment method of a video shooting device provided in an embodiment of the present disclosure.

[0048] Figure 4 It is a schematic diagram of multiple key points of designated body parts of a corresponding character provided by an embodiment of the present disclosure.

[0049] Figure 5 It is a flowchart of the shooting adjustment method provided by an embodiment of the present disclosure.

[0050] Figure 6 It is a schematic principle block diagram of a shooting adjustment device of a video shooting device provided in an embodiment of the present disclosure.

[0051] Figure 7a is a schematic principle block diagram of an electronic device according to an embodiment of the present disclosure.

[0052] Figure 7b is a schematic principle block diagram of an electronic device according to another embodiment of the present disclosure. DETAILED DESCRIPTION

[0053] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0054] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0055] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0056] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0057] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0058] In view of the problem in the prior art that when a mobile terminal or a personal computer is directly used as a video shooting device, the video shooting device cannot dynamically adjust its own shooting parameters according to the recording scene or the posture of the person, the embodiment of the present disclosure provides a video shooting device for solving the above problem. Figure 1 , which is a structural diagram of a video shooting device provided in an embodiment of the present disclosure.

[0059] like Figure 1 As shown, the video shooting device 10 provided in the embodiment of the present disclosure may include an image acquisition device 12 and an image transmission device (not shown in the figure) and a control module (not shown in the figure), wherein the image acquisition device 12 is used to acquire video images; the image transmission device is used to transmit the video images to a server in real time; the control module is used to adjust the shooting parameters of the image acquisition device according to the shooting adjustment method of the video shooting device provided in the embodiment of the present disclosure.

[0060] In one embodiment, the video shooting device may further include a supporting component 11 , and the supporting component 11 is movably connected to the image acquisition device 12 .

[0061] In a specific implementation, the supporting component 11 may be a component for supporting the image acquisition device 12 and the display device 13 , for example, may be a pan / tilt platform.

[0062] In one embodiment, the image acquisition device 12 can be a camera, and the image acquisition device 12 is movably connected to the support component 11. For example, it can be movably connected to the support component 11 through a first connecting component 14. The movable connection allows the image acquisition device 12 to move vertically up and down or horizontally left and right relative to the support component 11 to adjust its vertical height or adjust its horizontal position. No special limitation is made here.

[0063] In one embodiment, the video shooting device 10 may further include a display device 13 , which is connected to the image acquisition device 12 and is used to receive and display the video image acquired by the image acquisition device 12 .

[0064] The display device 13 is connected to the image acquisition device 12, and can receive and display the video images acquired by the image acquisition device to form a live broadcast picture.

[0065] In a specific implementation, the display device 13 can be movably connected to the support assembly 11. For example, it can be movably connected to the support assembly 11 through a second connecting assembly (not shown in the figure). This movable connection allows the display device 13 to rotate and move vertically relative to the support assembly 11 to adjust its height and adjust its vertical screen display mode or horizontal screen display mode.

[0066] In this embodiment, the control module can adjust the posture of the display device 13 and the image acquisition device 12 in the video capture device 10 according to the shooting adjustment method of the video capture device provided in the embodiment of the present disclosure. In specific implementation, the control module can control the movement of the first connecting component 14 or the second connecting component through a motor to adjust the posture of the image acquisition device 12 or the display device 13.

[0067] Figure 2 FIG. 1 is a schematic diagram of a scene of a method for adjusting the shooting of a video shooting device provided by an embodiment of the present disclosure. Figure 2 As shown, at the first moment, the image acquisition device 12 of the video shooting device 10 acquires at least one video image containing at least one person. At this moment, the display device 13 can display the video image to form a live screen or can also transmit the video image to the server in real time through the image transmission device. Figure 2 As shown, at the first moment, the head of the person is in the lower area of ​​the video image, and because the person is standing, when the display device 13 is in the horizontal screen display mode, it cannot present more image content in the vertical direction, which is not conducive to user viewing; therefore, the control module of the video shooting device 10 can obtain the image position information of multiple key points corresponding to the specified body parts of the person, and obtain the target posture information of the person and the person's relative position information in the video image based on the image position information of the multiple key points, and then adjust the shooting parameters of the video shooting device based on the target posture information and the relative position relationship of the person, for example, the image acquisition device 12 is moved vertically downward to reduce its height; and the display device 13 can also be flipped and adjusted to the vertical screen display mode, so that at the second moment, the video image captured by the video shooting device 10 can present more image content in the vertical direction, and the person is placed in the central area of ​​the video image, which is convenient for user viewing.

[0068] It should be noted that, in a specific implementation, the video shooting device 10 may further include an audio input device, which may be a microphone, for example.

[0069] According to the above description, the video shooting device provided by the embodiment of the present disclosure can dynamically and adaptively adjust its shooting parameters according to the target posture information of the character when the character starts to shoot a video or is in the process of shooting a video, so as to adapt to the shooting scene and the character's posture, thereby avoiding the problem that the shooting may need to be interrupted when the character operates manually.

[0070] Figure 3 FIG. 1 is a flow chart of a method for adjusting the shooting of a video shooting device provided by an embodiment of the present disclosure. The method provided by this embodiment can be applied to a video shooting device, for example, Figure 1 In the video capture device 10 shown.

[0071] It should be noted that, in the present embodiment, the method is directly applied to a video capture device as an example for explanation. In the specific implementation, since the computing power of the video capture device may be slow, in order to improve the computing speed, the method can also be applied to an electronic device that is communicatively connected to the video capture device. For example, in a server, the electronic device obtains the image position information of multiple key points of the specified body parts of the corresponding person, obtains the target posture information of the person and the relative position information of the person in the video image, and generates an instruction to adjust the shooting parameters of the video capture device based on the target posture information and the relative position information of the person, and sends the instruction to the control module of the video capture device, so that the control module adjusts its shooting parameters according to the instruction. The detailed processing process will not be repeated here.

[0072] according to Figure 3 As shown, the method of this embodiment may include the following steps S3100 to S3500, which are described in detail below.

[0073] Step S3100, obtaining at least one video image, wherein the video image includes at least one person.

[0074] In this embodiment, the video image may be an image containing a person captured by an image capture device of a video shooting device, for example, it may be a video image in a video stream in nv21 format captured by a camera.

[0075] When adjusting the shooting parameters of a video shooting device using the method provided in the embodiment of the present application, in order to avoid the problem of frequent image jitter caused by the frequent adjustment of shooting parameters due to the instantaneous dynamics of the characters, in specific implementation, the at least one video image can meet at least one of the following conditions: the number of the at least one video image is not less than the preset number, and the duration corresponding to the at least one video image is not less than the preset duration. That is, based on the preset number of video images or the preset duration of video images, it is determined whether the shooting parameters of the video shooting device need to be adjusted, wherein the preset number and the preset duration can be set as needed, and are not specifically limited here.

[0076] Step S3200, obtaining image position information of a plurality of key points in the video image, wherein the key points correspond to designated body parts of the person.

[0077] The key point may be a point corresponding to a designated body part of the character. In this embodiment, the posture information of the character may be determined by obtaining points corresponding to different body parts of the character, for example, whether the character is currently standing or sitting.

[0078] Please see Figure 4, which is a schematic diagram of multiple key points of a designated body part of a corresponding character provided by an embodiment of the present disclosure. Figure 4 As shown, the key points can be the key points of the joints, head and other parts of the character's body, for example, key point 1 corresponding to the character's head, key point 2 and key point 6 corresponding to the left and right shoulders of the character, key point 3 and key point 7 corresponding to the left and right elbows of the character, key point 5 corresponding to the middle part of the chest cavity of the character, key point 4 and key point 8 corresponding to the left and right wrists of the character, key point 9 and key point 10 corresponding to the left and right hips of the character, key point 11 and key point 13 corresponding to the left and right knees of the character, and key point 12 and key point 14 corresponding to the left and right ankles of the character.

[0079] It should be noted that in this embodiment, the number of key points corresponding to the specified body parts of the character is 14 for example. In specific implementation, the positions of the key points and the number of the key points can also be set as needed, and no special limitation is made here.

[0080] In addition, in this embodiment, the image position information corresponding to each key point can be the position data of the key point in the corresponding video image, that is, coordinate data, wherein the video image can be an image containing the person captured by the image capture device of the video shooting equipment.

[0081] Specifically, in this embodiment, the obtaining of image position information of a plurality of key points of the video image includes: inputting the video image into a human key point recognition model to obtain image position information of the plurality of key points.

[0082] That is, in this embodiment, in order to obtain the posture information of the person, the posture information of the person can be obtained by a human key point detection (HumanKeypointsDetection) algorithm, that is, a human posture estimation algorithm, for example, whether the person is standing or sitting.

[0083] In this embodiment, when starting to shoot a video or in the process of shooting a video, a video image containing at least one person captured by an image capture device of a video shooting device can be input into a human key point recognition model to obtain image position information of the multiple key points in the video image.

[0084] The human body key point recognition model can be a convolutional neural network model obtained through pre-training and used to recognize the position information of human body key points. The model can be a 2D key point detection model or a 3D key point detection model, which is not specifically limited here.

[0085] Of course, with the continuous advancement of technology, image position information of multiple key points of designated body parts corresponding to a person may also be obtained through other algorithms, which will not be elaborated here.

[0086] Step S3300, obtaining target posture information of the person and relative position information of the person in the video image according to the image position information of the multiple key points.

[0087] After obtaining the position information of multiple key points of the specified body parts of the corresponding person in the video image through step S3200, the target posture information of the person and the relative position information of the person in the video image can be obtained based on the image position information of the multiple key points, which is described in detail below.

[0088] Specifically, obtaining the target posture information of the character based on the image position information of the multiple key points includes: obtaining the number of key points based on the image position information of the multiple key points; and obtaining the target posture information of the character based on the number of key points.

[0089] In this embodiment, the number of key points is the number of valid key points, wherein a valid key point means that the position information corresponding to the key point is valid, for example, the position data of the key point in the coordinate space of the corresponding video frame is not zero.

[0090] Specifically, in the field of computer vision, when using a human key point recognition algorithm to identify human key points, when the position information of a point can be identified, the coordinate data representing the position information of the point is output; when the position information of a point cannot be identified, the coordinate data of the point is generally represented by zero. Therefore, whether the key point is valid can be determined by judging whether the position data corresponding to the key point is zero.

[0091] For example, when the position information is two-dimensional coordinate data, when both the horizontal coordinate and the vertical coordinate of a key point are not zero, the key point can be determined to be a valid key point.

[0092] Of course, in practice, when the human key point detection algorithm cannot identify a key point, its coordinate data may also be set to negative values. At this time, the validity of the key point can be judged based on whether the value in the coordinate data of the key point is greater than zero. I will not go into details here.

[0093] It should be noted that in this embodiment, the number of key points is obtained based on the image position information of multiple key points. In specific implementation, when the position information of multiple key points is obtained using the human body key point recognition model, the model can also output the number of key points at the same time. No special limitation is made here.

[0094] After the number of key points corresponding to the current posture of the character is obtained through the above processing, the target posture information of the character can be obtained according to the number of key points. In this embodiment, the target posture information of the character is obtained according to the number of key points, including: when the number of key points is less than a preset number threshold, determining that the target posture information is the first posture information representing the sitting posture; and when the number of key points is not less than the preset number threshold, determining that the target posture information is the second posture information representing the standing posture.

[0095] In this embodiment, the preset number threshold is 14 for example, that is, the data of multiple key points corresponding to the body parts of the character is 14. When the number of key points is less than 14, it can be determined that the current posture of the character is sitting, and the posture information is set to the first posture information representing the sitting posture, for example, set to "0"; on the contrary, when the number of key points is not less than 14, it can be determined that the current posture of the character is standing, and the posture information is set to the second posture information representing the standing posture, for example, set to "1". It should be noted that in the specific implementation, the preset number threshold can be set according to the situation, and no special limitation is made here.

[0096] It should also be noted that, in a specific implementation, when there are multiple video images, a to-be-determined posture information corresponding to a person can be determined based on each video image respectively. Then, from the multiple to-be-determined posture information corresponding to the multiple video images, the to-be-determined posture information with the largest number of corresponding posture categories and not less than a preset posture number threshold is selected as the target posture information of the person.

[0097] For example, when the number of video images is 10 and the preset threshold value of the number of postures is 5, when, among the 10 posture information to be determined corresponding to the 10 video images, the posture category is the second posture information, that is, the number of posture information to be determined of standing posture is 6, which is greater than the preset threshold value of the number of postures, it can be determined that the target posture information of the character is the second posture information, that is, standing posture, based on the 10 video images.

[0098] In the above, how to obtain the target posture information of a person is described. In the following, how to obtain the relative position information of a person in a video image is described in detail.

[0099] In this embodiment, the body parts of the character include the head part; obtaining the relative position information of the character in the video image based on the image position information of the multiple key points includes: acquiring the image position data of the head part of the character from the image position information of the multiple key points, wherein the image position data represents the position of the head part of the character in the video image; and obtaining the relative position information of the character based on the image position data.

[0100] Specifically, obtaining the relative position information of the person according to the image position data includes at least one of the following: when the image position data indicates that the head part of the person is in a first preset area of ​​the video image, determining the relative position information of the person as first relative position information, wherein the first relative position information indicates that the height of the image acquisition device of the video shooting equipment is higher than the head part of the person; when the position data indicates that the head part of the person is in a second preset area of ​​the video image, determining the relative position information of the person as second relative position information, wherein the second relative position information indicates that the height of the image acquisition device is lower than the head part of the person; when the position data indicates that the head part of the person is in a third preset area of ​​the video image, determining the relative position information of the person as third relative position information, wherein the third relative position information indicates that the image acquisition device is located on the right side of the person; when the position data indicates that the head part of the person is in a fourth preset area of ​​the video image, determining the relative position information of the person as fourth pair of position information, wherein the fourth relative position information indicates that the image acquisition device is located on the left side of the person.

[0101] In this embodiment, the first preset area can be the area below the center of the video image, for example, the area below 1 / 3 of the height of the video image; the second preset area can be the area above the center of the video image, for example, the area above 2 / 3 of the height of the video image; the third preset area can be the area to the left of the center of the video image, for example, the area of ​​the leftmost 1 / 3; the fourth preset area can be the area to the right of the center of the video image, for example, the area of ​​the rightmost 1 / 3.

[0102] That is, in the process of shooting a video, when the posture of a person changes or the distance between the person and the video shooting device changes, in order to ensure that the person can be in the center area of ​​the video image to enhance the user's viewing experience, in this embodiment, the image position data of the key points of the user's head in the video image, that is, the coordinate data, can be used to obtain the relative position information of the user in the video image.

[0103] For example, the position data is two-dimensional coordinate data (x1, y1). In specific implementation, the vertical coordinate y of the center point of the video image can be obtained. Then, when y1 > y, it can be determined that the head part of the person is in the area above the center of the video image; when y1 < y, it can be determined that the head part of the person is in the area below the center of the video image. Additionally, the horizontal coordinate x of the center point of the video image can be obtained. Then, when x1 < x, it can be determined that the head part of the person is in the area to the left of the center of the video image, and when x1 > x, it can be determined that the head part of the person is in the area to the right of the center of the video image.

[0104] It should be noted that in specific implementation, the relative position information of the person in the video image can also be obtained by other methods, and no special limitation is made here.

[0105] After step S3300, step S3400 is executed to adjust the shooting parameters of the video shooting device according to the target pose information and the relative position information of the person, and the shooting parameters at least include the shooting direction and the shooting position.

[0106] After obtaining the target pose information representing the current pose of the person and the relative position information of the person in the video image through step S3300, the shooting parameters of the video shooting device can be adjusted according to the above information.

[0107] Specifically, the adjustment of the shooting parameters of the video shooting device can specifically be to adjust the horizontal and vertical screen display modes of the display device of the video shooting device, and to adjust the height position and / or the horizontal position of the image acquisition device.

[0108] That is, the adjustment of the shooting parameters of the video shooting device according to the target pose information and the relative position information of the person includes: adjusting the pose of the display device of the video shooting device according to the target pose information; and adjusting the shooting parameters of the image acquisition device of the video shooting device according to the relative position information of the person.

[0109] In specific implementation, the adjustment of the pose of the display device of the video shooting device according to the target pose information includes: when the target pose information is the first pose information representing a standing pose, adjusting the display device of the video shooting device to the vertical screen display mode; and when the target pose information is the second pose information representing a sitting pose, adjusting the display device to the horizontal screen display mode.

[0110] For example, when the user's current posture is standing, the display device of the video capture device can be rotated to put it into a portrait display mode, so that the video image can display more content in the vertical direction; and when the user's current posture is sitting, the display device of the video capture device can be rotated to put it into a landscape display mode, so that the video image can display more content in the horizontal direction.

[0111] In addition, adjusting the shooting parameters of the image acquisition device of the video shooting equipment according to the relative position information of the person includes at least one of the following: when the relative position relationship is a first relative position relationship, controlling the image acquisition device to move vertically downward; when the relative position relationship is a second relative position relationship, controlling the image acquisition device to move vertically upward; when the relative position information of the person is third relative position information of the person, controlling the image acquisition device to move horizontally to the left; and when the relative position information of the person is fourth relative position information of the person, controlling the image acquisition device to move horizontally to the right.

[0112] In a specific implementation, the control module of the video shooting device, for example, the video shooting device 10, can control the first connecting component 14 to move vertically up and down and / or horizontally left and right through a first motor to control the image acquisition device to move up, down, left and right; and can control the second connecting component to rotate through a second motor to adjust the posture of the display device so that the character is in the center of the video image.

[0113] In one embodiment, adjusting the shooting parameters of the image acquisition device of the video shooting equipment according to the relative position information of the person includes: obtaining a displacement value, wherein the displacement value is used to indicate the moving distance of the image acquisition device; and adjusting the shooting parameters of the image acquisition device according to the relative position information of the person and the displacement value.

[0114] That is, in order to accurately adjust the shooting parameters of the video shooting equipment, after obtaining the relative position information of the person in the video image, a displacement value can be calculated according to the parameters of the image acquisition device. The displacement value can represent the movement distance of the image acquisition device in the vertical direction and / or horizontal direction. Thereafter, the shooting parameters of the image acquisition device can be accurately adjusted according to the relative posture information of the person and the displacement value.

[0115] In one embodiment, during the process of adjusting the shooting parameters of the video shooting device, the method further includes: receiving a first input for confirming the current shooting parameters; in response to the first input, stopping adjusting the shooting parameters, and using the shooting parameters at the current moment as the shooting parameters of the video shooting device.

[0116] That is, in the process of the video capture device adjusting its shooting parameters according to information such as the target posture information and the relative position information of the person, during the adjustment process, when the user believes that the parameters at the current moment have met the video capture requirements, in order to avoid excessive or improper adjustment of the shooting parameters, the user can input a first input to the video capture device to confirm the current shooting parameters through a remote control, voice, gesture, or key input; in response to the first input, the video capture device stops adjusting the shooting parameters and uses the shooting parameters at the current moment as the shooting parameters of the video capture device. Of course, in specific implementation, confirmation information can also be input to the video capture device through other methods, which are not specifically limited here.

[0117] In one embodiment, when the video image includes at least one person, the target posture information and the person position information may each be at least one, and the at least one target posture information and the at least one person relative position information respectively correspond to the at least one person; in this embodiment, adjusting the shooting parameters of the video shooting device according to the target posture information and the person relative position information includes: adjusting the shooting parameters of the video shooting device according to the at least one target posture information and the at least one person relative position information.

[0118] That is, when a video image contains multiple persons, the shooting parameters can be adjusted according to the comprehensive distribution of the multiple persons in the video image, and the specific implementation method will not be repeated here.

[0119] After step S3400, step S3500 is executed to shoot a video image using the adjusted shooting parameters.

[0120] In one embodiment, after adjusting the shooting parameters of the video shooting device through the above-mentioned processing, in order to enable the device to automatically adjust its shooting parameters to parameters suitable for the person when the person uses the video shooting device in the future to enhance the user experience, the method provided in this embodiment also includes: obtaining a character identification of the person in the video image; obtaining mapping data based on the correspondence between the character identification and the adjusted shooting parameters; and storing the mapping data.

[0121] In this embodiment, after obtaining at least one video image containing at least one person through the above step S3100, in order to further reduce user operations so that the video capture device can quickly adjust the shooting parameters to suit the person's preferences, the method provided in this embodiment also includes: obtaining the person identification of the person in the video image; obtaining the preset shooting parameters corresponding to the person according to the person identification; adjusting the shooting parameters of the video capture device according to the preset shooting parameters. Among them, how to identify the person identification of the person in the video image can be to identify the person identification of the person by using a face recognition method after obtaining user authorization, and the detailed implementation method is not repeated here.

[0122] In one embodiment, when a person is shooting a video, the shot video image may also include items. For example, in a live shopping scenario, when a person is broadcasting live, the video image often also includes items while including the person. In order to more accurately and intelligently adjust the shooting parameters of the device, in this embodiment, before adjusting the shooting parameters, the method also includes: obtaining object relative position information of the target object in the video image, wherein the target object is an object other than the person contained in the video image, and the ratio of the image pixels corresponding to the target object to the foreground pixels of the video image is not less than a preset pixel ratio. Adjusting the shooting parameters of the video shooting device according to the target posture information and the person relative position information includes: adjusting the shooting parameters of the video shooting device according to the target posture information, the person relative position information and the object relative position information.

[0123] In specific implementation, the foreground and background of the video image can be segmented, and the foreground image obtained by the segmentation process can be processed for object recognition to identify objects other than people contained therein. For example, in the foreground image, the ratio of the pixels of a certain object to all pixels is 20%. When the preset pixel ratio is 15%, the object can be identified as the target object; and when adjusting the shooting parameters, the shooting parameters of the video shooting device can also be adjusted according to the relative position information of the target object in the video image. Of course, in specific implementation, the target object in the video image can also be identified by other methods, which will not be repeated here.

[0124] In addition, in the process of shooting video images using the adjusted shooting parameters, in order to facilitate the user to adjust or fine-tune the shooting parameters of the video shooting device at any time as needed, the method also includes: receiving a second input for adjusting the current shooting parameters; and adjusting the shooting parameters of the video shooting device in response to the second input.

[0125] For example, in a live shopping scenario, when a close-up of the current product is required, the user can input a second input to the video capture device to adjust the current shooting parameters, thereby accurately adjusting the shooting parameters of the device. The second input can be information for instructing the video capture device to move horizontally or vertically or to rotate the capture angle of the image capture device. The input method can be a remote control, gesture, voice, button, etc., and there is no special limitation here.

[0126] In summary, the video capture device and the shooting adjustment method of the video capture device provided in the present embodiment, when the user starts shooting a video or in the process of shooting a video, by obtaining at least one video image, and by obtaining the image position information of multiple key points corresponding to the specified body parts of the person contained in the video image, the target posture information of the person and the person's relative position information in the video image can be obtained according to the image position information, and then according to the target posture information and the person's relative position information, the video capture device can automatically adjust its own shooting parameters, and use the adjusted shooting parameters to shoot the video image. This method can enable the video capture device to quickly follow the person's posture and dynamically adjust its own shooting parameters to adapt to the recording scene and the person's posture, avoiding the problem that the live broadcast may need to be interrupted when the person manually operates.

[0127] Figure 5 A flow chart of an embodiment of the video shooting device 10 applying the above shooting adjustment method is provided. In this example, the video shooting device 10 is used to shoot a live video.

[0128] Step S5100, start live broadcast.

[0129] Step S5200: collect at least one video image, wherein the video image includes the anchor.

[0130] That is, after the video capture device receives the broadcast start instruction from the anchor, in response to the instruction, the video capture device controls the image acquisition device facing the anchor, for example, the camera acquires at least one video image containing the anchor. In a specific implementation, the format of the video image can be nv21 format.

[0131] Step S5300, obtaining image position information of multiple key points corresponding to designated body parts of the host in the video image.

[0132] After acquiring the above-mentioned video image, a human posture recognition algorithm, such as a pixelAI algorithm, is called frame by frame on the video image to obtain multiple key points of human posture recognition, such as image position information of 14 key points. The image position information can be directly the coordinates of the 14 key points.

[0133] After step 5300, step S5400 is executed to obtain the coordinates of the key points of the head according to the image position information; and step S5700 is executed to obtain the number of key points according to the image position information.

[0134] Specifically, after obtaining the image position information, that is, the coordinates, of the multiple key points, the coordinates of the head key points can be used to determine the area where the coordinates of the head key points are located on the screen, that is, in the video image. When the coordinates of the head key points are located above the screen, step S5500 is executed to adjust the camera height upward; and, when the coordinates of the head key points are located below the screen, step S5600 is executed to adjust the camera height downward; that is, through steps S5500 and S5600, the anchor position is ensured to be in the center of the video image.

[0135] In addition, it is also possible to determine whether the host is standing or sitting at the current moment through the valid key points among the multiple key points, that is, the number of key points whose corresponding coordinates have non-zero values, wherein the preset number threshold for executing the judgment can be 14; and when the number of key points is less than 14, execute step S5800 to determine that the host's posture is sitting, and adjust the display device to landscape display to display more image content in the horizontal direction; and, when the number of key points is not less than 14, execute step S5900 to determine that the host's posture is standing, and adjust the display device to portrait display to display more image content in the vertical direction.

[0136] In this embodiment, the acquisition parameters of the image acquisition device and the display mode of the display device can be adjusted by adjusting the motor; of course, during the adjustment process, the remote control can also be used to fine-tune the shooting parameters to more accurately adjust the shooting parameters of the device.

[0137] According to the above embodiments, during video shooting, such as live broadcast, the video shooting device obtains the coordinates of the head key points and the number of key points by identifying the image position information of multiple key points corresponding to the character; thereafter, the video shooting device may not require the user to manually adjust its shooting parameters, but instead adaptively adjusts the shooting parameters of its image acquisition device according to the coordinates of the head key points, such as the shooting direction and shooting angle, etc.; and, it may also determine whether the anchor is standing or sitting according to the number of key points, thereby adaptively adjusting the display mode of its display device to provide users with a better viewing experience.

[0138] Corresponding to the above embodiment, this embodiment also provides a shooting adjustment device for a video shooting device, such as Figure 6 As shown, it is a schematic principle block diagram of the shooting adjustment device of the video shooting equipment provided by an embodiment of the present disclosure.

[0139] according to Figure 6 As shown, the shooting adjustment device 6000 of the video shooting equipment of this embodiment includes an image acquisition module 6100 , an image position information acquisition module 6200 , an information processing module 6300 , a parameter adjustment module 6400 and an image shooting module 6500 .

[0140] The image acquisition module 6100 is used to acquire at least one video image, wherein the video image includes at least one person.

[0141] The image position information acquisition module 6200 is used to acquire image position information of a plurality of key points in the video image, wherein the key points correspond to designated body parts of the person.

[0142] In one embodiment, when acquiring the image position information of multiple key points of the video image, the image position information acquisition module 6200 can be used to: input the video image into a human key point recognition model to obtain the image position information of the multiple key points.

[0143] The information processing module 6300 is used to obtain the target posture information of the character and the relative position information of the character in the video image according to the image position information of the multiple key points.

[0144] In one embodiment, when the information processing module 6300 obtains the target posture information of the character based on the image position information of the multiple key points, it can be used to: obtain the number of key points based on the image position information of the multiple key points; and obtain the target posture information of the character based on the number of key points.

[0145] In this embodiment, when the information processing module 6300 obtains the target posture information of the character based on the number of key points, it can be used to: when the number of key points is less than a preset threshold number, determine that the target posture information is the first posture information representing a sitting posture; and when the number of key points is not less than the preset threshold number, determine that the target posture information is the second posture information representing a standing posture.

[0146] In one embodiment, the body parts include head parts; when the information processing module 6300 obtains the relative position information of the person in the video image based on the image position information of the multiple key points, it can be used to: obtain the image position data of the head part of the person from the image position information of the multiple key points, wherein the image position data represents the position of the head part of the person in the video image; and obtain the relative position information of the person based on the image position data.

[0147] In this embodiment, the information processing module 6300 is used to obtain the relative position information of the person through at least one of the following: when the image position data indicates that the head part of the person is in the first preset area of ​​the video image, determining the relative position information of the person as the first relative position information, wherein the first relative position information indicates that the height of the image acquisition device of the video shooting device is higher than the head part of the person; when the position data indicates that the head part of the person is in the second preset area of ​​the video image, determining the relative position information of the person as the second relative position information, wherein the second relative position information indicates that the height of the image acquisition device is lower than the head part of the person; when the position data indicates that the head part of the person is in the third preset area of ​​the video image, determining the relative position information of the person as the third relative position information, wherein the third relative position information indicates that the image acquisition device is located on the right side of the person; when the position data indicates that the head part of the person is in the fourth preset area of ​​the video image, determining the relative position information of the person as the fourth pair of position information, wherein the fourth relative position information indicates that the image acquisition device is located on the left side of the person.

[0148] The parameter adjustment module 6400 is used to adjust the shooting parameters of the video shooting device according to the target posture information and the person's relative position information, and the shooting parameters at least include a shooting direction and a shooting position.

[0149] In one embodiment, when the parameter adjustment module 6400 adjusts the shooting parameters of the video shooting device according to the target posture information and the relative position information of the person, it can be used to: adjust the posture of the display device of the video shooting device according to the target posture information; and adjust the shooting parameters of the image acquisition device of the video shooting device according to the relative position information of the person.

[0150] In this embodiment, when the parameter adjustment module 6400 adjusts the posture of the display device of the video capture device according to the target posture information, it can be used to: when the target posture information is the first posture information representing a standing posture, adjust the display device of the video capture device to a vertical screen display mode; and when the target posture information is the second posture information representing a sitting posture, adjust the display device to a horizontal screen display mode.

[0151] In this embodiment, the parameter adjustment module 6400 is used to adjust the shooting parameters of the image acquisition device of the video shooting equipment through at least one of the following: when the relative position information of the person is the first relative position information of the person, controlling the image acquisition device to move vertically downward; when the relative position information of the person is the second relative position information of the person, controlling the image acquisition device to move vertically upward; when the relative position information of the person is the third relative position information of the person, controlling the image acquisition device to move horizontally to the left; and when the relative position information of the person is the fourth relative position information of the person, controlling the image acquisition device to move horizontally to the right.

[0152] In one embodiment, when the parameter adjustment module 6400 adjusts the shooting parameters of the image acquisition device of the video capture equipment according to the relative position information of the person, it can be used to: obtain a displacement value, wherein the displacement value is used to indicate the moving distance of the image acquisition device; and adjust the shooting parameters of the image acquisition device according to the relative position information of the person and the displacement value.

[0153] In one embodiment, the device also includes a shooting parameter confirmation module, which is used to: receive a first input for confirming the current shooting parameters during the process of adjusting the shooting parameters of the video shooting device; in response to the first input, stop adjusting the shooting parameters, and use the shooting parameters at the current moment as the shooting parameters of the video shooting device.

[0154] In one embodiment, each of the target posture information and the character relative position information is at least one, and the at least one target posture information and the at least one character relative position information correspond to the at least one character respectively; when the parameter adjustment module 6400 adjusts the shooting parameters of the video shooting device according to the target posture information and the character relative position information, it can be used to: adjust the shooting parameters of the video shooting device according to the at least one target posture information and the at least one character relative position information.

[0155] In one embodiment, the device also includes a mapping data storage module, which is used to: obtain a character identification of the character in the video image after adjusting the shooting parameters; obtain mapping data based on the correspondence between the character identification and the adjusted shooting parameters; and store the mapping data.

[0156] In one embodiment, the device also includes an object relative position information acquisition module, which is used to: before adjusting the shooting parameters, obtain the object relative position information of the target object in the video image, wherein the target object is an object other than the person contained in the video image, and the ratio of the image pixels corresponding to the target object to the foreground pixels of the video image is not less than a preset pixel ratio.

[0157] In this embodiment, when the parameter adjustment module 6400 adjusts the shooting parameters of the video shooting device according to the target posture information and the relative position information of the character, it can be used to: adjust the shooting parameters of the video shooting device according to the target posture information, the relative position information of the character and the relative position information of the object.

[0158] The image shooting module 6500 is used to shoot video images using the adjusted shooting parameters.

[0159] In one embodiment, the device also includes an identification corresponding module, which is used to: after acquiring the at least one video image, obtain the character identification of the person in the video image; obtain preset shooting parameters corresponding to the person based on the character identification; and adjust the shooting parameters of the video shooting device based on the preset shooting parameters.

[0160] In one embodiment, the apparatus further includes a parameter fine-tuning module for: receiving a second input for adjusting the current shooting parameters during the process of shooting video images using the adjusted shooting parameters; and adjusting the shooting parameters of the video shooting device in response to the second input.

[0161] Corresponding to the above embodiment, this embodiment provides an electronic device, such as Figure 7a As shown, the electronic device 100 includes a shooting adjustment device 6000 of a video shooting device according to any embodiment of the present disclosure.

[0162] In another embodiment, Figure 7b As shown, the electronic device 100 may include a memory 110 and a processor 120, wherein the memory 110 is used to store executable instructions; and the processor 120 is used to execute a method as in any method embodiment of the present disclosure under the control of the executable instructions.

[0163] Corresponding to the above method embodiments, in this embodiment, a computer-readable storage medium is also provided, which stores a computer program that can be read and executed by a computer, and the computer program is used to execute the method described in any of the above embodiments of the present disclosure when read and executed by the computer.

[0164] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0165] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0166] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0167] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0168] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0169] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so as to produce a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device for implementing the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions make the computer, programmable data processing device, and / or other equipment work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0170] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0171] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of an instruction, and the module, a program segment or a part of an instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0172] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present disclosure is defined by the appended claims.

Claims

1. A shooting adjustment method for a video shooting device, comprising: Acquire at least one video image, wherein the video image includes at least one person; Obtaining image position information of a plurality of key points in the video image, wherein the plurality of key points correspond to different body parts of the person; According to the image position information of the multiple key points, target posture information of the person and relative position information of the person in the video image are obtained; According to the target posture information and the person's relative position information, adjusting the shooting parameters of the video shooting device, the shooting parameters at least including a shooting direction and a shooting position, wherein the video shooting device includes a display device, the display device is connected to the image acquisition device, and is used to receive and display video images; Using the adjusted shooting parameters, shooting video images; Wherein, obtaining the target posture information of the person according to the image position information of the multiple key points includes: obtaining the number of key points according to the image position information of the multiple key points; obtaining the target posture information of the person according to the number of key points, wherein the number of key points includes the number of valid key points whose position information corresponding to the key points is valid; Wherein, adjusting the shooting parameters of the video capture device according to the target posture information and the relative position information of the person includes: adjusting the posture of the display device of the video capture device according to the target posture information, wherein, adjusting the posture of the display device of the video capture device according to the target posture information includes: when the target posture information is first posture information representing a standing posture, adjusting the display device of the video capture device to a vertical screen display mode; and, when the target posture information is second posture information representing a sitting posture, adjusting the display device to a horizontal screen display mode.

2. The method according to claim 1, wherein obtaining target posture information of the character according to the number of key points comprises: When the number of key points is less than a preset number threshold, determining that the target posture information is first posture information representing a sitting posture; as well as, When the number of key points is not less than the preset number threshold, the target posture information is determined to be second posture information representing a standing posture.

3. According to the method of claim 1, the at least one video image satisfies at least one of the following conditions: the number of the at least one video image is not less than a preset number, and the duration corresponding to the at least one video image is not less than a preset duration.

4. The method of claim 1, wherein the body part comprises a head part; The step of obtaining the relative position information of the person in the video image according to the image position information of the multiple key points includes: Acquire image position data of the head of the person from the image position information of the multiple key points, wherein the image position data represents the position of the head of the person in the video image; The relative position information of the person is obtained according to the image position data.

5. The method according to claim 4, wherein obtaining the relative position information of the person according to the image position data comprises at least one of the following: In the case where the image position data indicates that the head of the person is located in the first preset area of ​​the video image, the person relative position information is determined to be the first relative position information, wherein: The first relative position information indicates that the height of the image acquisition device of the video shooting device is higher than the head of the person; In the case where the position data indicates that the head of the person is in a second preset area of ​​the video image, determining the person's relative position information as second relative position information, wherein the second relative position information indicates that the height of the image acquisition device is lower than the head of the person; In the case where the position data indicates that the head of the person is located in a third preset area of ​​the video image, determining the person's relative position information as third relative position information, wherein the third relative position information indicates that the image acquisition device is located on the right side of the person; When the position data indicates that the head of the person is in a fourth preset area of ​​the video image, the relative position information of the person is determined to be a fourth pair of position information, wherein the fourth relative position information indicates that the image acquisition device is located on the left side of the person.

6. The method according to claim 1, wherein adjusting the shooting parameters of the video shooting device according to the target posture information and the person's relative position information further comprises: According to the relative position information of the person, the shooting parameters of the image acquisition device of the video shooting equipment are adjusted.

7. The method according to claim 6, wherein adjusting the shooting parameters of the image acquisition device of the video shooting device according to the relative position information of the person comprises at least one of the following: When the person relative position information is the first person relative position information, controlling the image acquisition device to move vertically downward; When the person relative position information is the second person relative position information, controlling the image acquisition device to move vertically upward; When the person relative position information is the third person relative position information, controlling the image acquisition device to move horizontally to the left; and When the person relative position information is the fourth person relative position information, the image acquisition device is controlled to move horizontally to the right.

8. The method according to claim 6, wherein adjusting the shooting parameters of the image acquisition device of the video shooting device according to the relative position information of the person comprises: Acquiring a displacement value, wherein the displacement value is used to indicate a moving distance of the image acquisition device; The shooting parameters of the image acquisition device are adjusted according to the relative position information of the person and the displacement value.

9. The method according to claim 1, in the process of adjusting the shooting parameters of the video shooting device, the method further comprises: Receiving a first input for confirming current shooting parameters; In response to the first input, the adjustment of the shooting parameters is stopped, and the shooting parameters at the current moment are used as the shooting parameters of the video shooting device.

10. The method according to claim 1, wherein each of the target posture information and the character relative position information is at least one, and the at least one target posture information and the at least one character relative position information correspond to the at least one character respectively; The step of adjusting the shooting parameters of the video shooting device according to the target posture information and the person's relative position information includes: Adjust the shooting parameters of the video shooting device according to the at least one target posture information and the at least one person relative position information.

11. The method according to claim 1, after adjusting the shooting parameters, the method further comprises: Obtaining a person identification of the person in the video image; Obtaining mapping data according to the correspondence between the character identification and the adjusted shooting parameters; The mapping data is stored.

12. The method according to claim 1, after acquiring the at least one video image, the method further comprises: Obtaining a person identification of the person in the video image; According to the character identification, obtaining preset shooting parameters corresponding to the character; According to the preset shooting parameters, the shooting parameters of the video shooting device are adjusted.

13. The method according to claim 1, before adjusting the shooting parameters, the method further comprises: Obtaining object relative position information of a target object in the video image, wherein the target object is an object other than the person contained in the video image, and a ratio of image pixels corresponding to the target object to foreground pixels of the video image is not less than a preset pixel ratio; The step of adjusting the shooting parameters of the video shooting device according to the target posture information and the person's relative position information includes: The shooting parameters of the video shooting device are adjusted according to the target posture information, the person relative position information and the object relative position information.

14. The method according to claim 1, in the process of shooting video images using the adjusted shooting parameters, the method further comprises: receiving a second input for adjusting a current shooting parameter; In response to the second input, a capture parameter of the video capture device is adjusted.

15. The method according to claim 1, wherein obtaining the image position information of a plurality of key points of the video image comprises: The video image is input into a human key point recognition model to obtain image position information of the multiple key points.

16. A video shooting device, comprising: An image acquisition device, used for acquiring video images; An image transmission device, used for transmitting the video image to a server in real time; A control module, used to adjust the shooting parameters of the image acquisition device according to the method described in any one of claims 1-15.

17. A shooting adjustment device for a video shooting device, comprising: An image acquisition module, used to acquire at least one video image, wherein the video image contains at least one person; An image position information acquisition module, used to acquire image position information of a plurality of key points in the video image, wherein the plurality of key points correspond to different body parts of the person; An information processing module is used to obtain the target posture information of the person and the person's relative position information in the video image according to the image position information of the multiple key points, wherein the obtaining the target posture information of the person according to the image position information of the multiple key points includes: obtaining the number of key points according to the image position information of the multiple key points; obtaining the target posture information of the person according to the number of key points, wherein the number of key points includes the number of valid key points whose position information corresponding to the key points is valid; A parameter adjustment module, for adjusting the shooting parameters of the video shooting device according to the target posture information and the person's relative position information, the shooting parameters at least including a shooting direction and a shooting position, wherein the video shooting device includes a display device, the display device is connected to an image acquisition device, and is used to receive and display video images, wherein the adjusting the shooting parameters of the video shooting device according to the target posture information and the person's relative position information includes: adjusting the posture of the display device of the video shooting device according to the target posture information, wherein the adjusting the posture of the display device of the video shooting device according to the target posture information includes: when the target posture information is first posture information representing a standing posture, adjusting the display device of the video shooting device to a vertical screen display mode; and when the target posture information is second posture information representing a sitting posture, adjusting the display device to a horizontal screen display mode; The image shooting module is used to shoot video images using the adjusted shooting parameters.

18. An electronic device, comprising the apparatus according to claim 17; or comprising: A memory for storing executable instructions; A processor is used to operate the electronic device to execute the method according to any one of claims 1-15 under the control of the executable instructions.

19. A computer-readable storage medium, wherein: The computer-readable storage medium stores a computer program that can be read and executed by a computer, and the computer program is used to execute the method according to any one of claims 1 to 15 when being read and executed by the computer.

Images