Viewing angle switching control method, device, medium and electronic device for display panel

Video data is collected through multiple image acquisition devices, facial recognition and expression feature analysis are performed, and the viewing angle of the display panel is automatically switched, which solves the problem of low efficiency of manual switching perspectives in the prior art and improves the viewing experience of live events.

CN118608742BActive Publication Date: 2024-11-26SHENZHEN OUGUAN MICROELECTRONICS TECH CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411080924.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-26
Estimated Expiration
2044-08-08

AI Technical Summary

Technical Problem

In the prior art, the subjectivity and efficiency of manually switching perspectives of staff during the live broadcast of the event are subjective and inefficient, resulting in the loss of the contestants' classic perspective images and affecting the audience's viewing experience.

Method used

Video data is collected through multiple image acquisition devices, face recognition and expression feature analysis are performed, and the viewing angle of the display panel is automatically switched. When the degree of change in the target expression is greater than the set threshold, switch to the target acquisition viewing angle to capture key images.

Benefits of technology

It improves the intelligence and user experience of viewing angle switching on the display panel, ensuring that the viewing angle is automatically switched when face expressions change, reducing the loss of player's viewing image.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118608742B_ABST
    Figure CN118608742B_ABST
Patent Text Reader

Abstract

The present disclosure relates to a method, device, medium and electronic device for controlling the viewing angle switching of a display panel. The method comprises: extracting a target frame containing a face image from a plurality of video data, generating face video data corresponding to each video data based on the time domain sequence of the target frame, determining facial expression features of faces in a plurality of face images in a first face video data, identifying the change relationship between facial expression feature points in face images in adjacent frames based on the facial expression features, determining the degree of change of a first expression of the face in the first face video data based on the change relationship, acquiring target video data corresponding to the target expression change degree, and switching the current display viewing angle of the display panel to the target acquisition viewing angle based on the target video data. Thus, the intelligence of the viewing angle switching of the display panel is improved, and the user experience is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, medium and electronic device for controlling viewing angle switching of a display panel. Background Art

[0002] With the continuous advancement of LCD display technology, people's entertainment life has been enriched with a richer visual experience. For example, the continuous development of the gaming industry has led to the emergence of live broadcasts and rebroadcasts of gaming-related events. During the live broadcast of events, the relevant staff manually switches the perspective to capture the changes in the expressions of the e-sports players during the game events and present them to the audience to adapt to the complex and ever-changing broadcasting of events and bring a better live viewing experience to the audience. In the related technologies, the manual switching of the staff is subjective and autonomous, and the switching efficiency is low. If the switching is not done in time, the classic perspective images of the players will be lost, which will affect the audience's viewing experience. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a viewing angle switching control method of a display panel.

[0004] According to a first aspect of an embodiment of the present disclosure, a viewing angle switching control method of a display panel is provided, the method comprising:

[0005] In response to a plurality of video data collected by a plurality of image acquisition devices, face recognition is performed on each frame of image data in the plurality of video data, and a target frame having a face image in the plurality of video data is extracted, and face video data corresponding to each video data is generated based on the time domain sequence of the target frame, wherein each image acquisition device corresponds to a different acquisition angle of view, and each video data is associated with the acquisition angle of view of the corresponding image acquisition device;

[0006] Performing expression feature recognition on the face image in the target frame corresponding to the first face video data to determine the facial expression features of the faces in the multiple frames of face images in the first face video data;

[0007] According to the facial expression features, identifying the change relationship between facial expression feature points in adjacent frames of face images, and determining the degree of change of the first facial expression of the face in the first face video data based on the change relationship, wherein the first face video data is any one of the multiple video data;

[0008] If the degree of change of the target expression is greater than a set degree threshold, the target video data corresponding to the degree of change of the target expression is obtained, and according to the target acquisition angle corresponding to the target video data, the current display angle of the display panel is switched to the target acquisition angle, so that the currently displayed video of the display panel is the video image captured by the target image acquisition device corresponding to the target acquisition angle.

[0009] Optionally, the performing expression feature recognition on the face image in the target frame corresponding to the first face video data to determine the facial expression features of the faces in the multiple frames of face images in the first face video data includes:

[0010] Determine the position information of the face key points of the face image in each target frame in the first face video data, wherein the face key points include: eye key points, eyebrow key points, nose key points and mouth key points;

[0011] Determining, based on the position information, a position change trend of the same facial key point in each target frame in consecutive target frames;

[0012] Obtaining the mapping relationship between the facial expression features and position change trends of the facial key points corresponding to the facial organ types of the human face;

[0013] generating a plurality of key point expression features of each facial key point in the first facial video data according to the mapping relationship and the position change trend;

[0014] According to a preset weight relationship, the multiple key point expression features are fitted to generate the facial expression features.

[0015] Optionally, the determining the position information of the facial key points of the facial images in each target frame in the first facial video data in the target frame includes:

[0016] Performing a multi-scale transformation on an image in a first target frame to generate a first image pyramid set of different sizes corresponding to the first target frame, where the first target frame is any target frame in the first face video data;

[0017] Performing frame selection evaluation on facial organ features in the first image pyramid set by using sliding frames corresponding to different types of facial key points, and determining a plurality of frame selection image sets whose evaluation scores are greater than a set threshold;

[0018] The multiple framed image sets are merged to determine the image area of ​​the facial organ features in the first target frame, and the target position information corresponding to the center of the image area is used as the position information of the facial key points in the first target frame.

[0019] Optionally, the performing frame selection evaluation on the facial organ features in the first image pyramid set by using sliding frames corresponding to different types of facial key points to determine a plurality of frame selection image sets having evaluation scores greater than a set threshold includes:

[0020] Performing contour recognition on the facial organs in the first target frame to identify multiple regional positions of each facial organ in the first target frame;

[0021] Divide the first target frame into images according to the multiple region positions to generate multiple second target frames corresponding to different facial organs;

[0022] The facial organ feature selection evaluation is performed on the third target frame according to the target sliding frame to generate a selected image with an evaluation score greater than the set threshold, the third target frame is any target frame among the multiple second target frames, and the target sliding frame is a sliding frame that matches the facial organ type corresponding to the third target frame.

[0023] Optionally, identifying the change relationship between facial expression feature points in adjacent frames of facial images according to the facial expression features includes:

[0024] According to the facial expression features, dividing the image frames of the first face video data corresponding to the areas where the facial key points in the adjacent target frames are located into regions;

[0025] Determine adjacent change information according to the position change relationship of facial key points in the same area of ​​the same face in two adjacent target frames;

[0026] Tracking the position transformation relationship of the same facial key point in different image frames in the target frame corresponding to the first facial video image to determine continuous change information;

[0027] The change relationship is determined according to the adjacent change information and the continuous change information.

[0028] Optionally, the determining the change relationship according to the adjacent change information and the continuous change information includes:

[0029] Determining a change trend of the facial key points according to the adjacent change information;

[0030] Correcting the contact change information according to the change trend to generate target change information;

[0031] Determining a change characteristic vector of the facial key points according to the target change information;

[0032] The change relationship is generated according to the change feature vector.

[0033] According to a second aspect of an embodiment of the present disclosure, there is provided a viewing angle switching control device for a display panel, comprising:

[0034] A generating module, configured to perform face recognition on each frame of image data in the multiple video data in response to the multiple video data collected by the multiple image acquisition devices, extract the target frame containing the face image in the multiple video data, and generate face video data corresponding to each video data based on the time domain sequence of the target frame, wherein each image acquisition device has a different acquisition angle of view, and each video data is associated with the acquisition angle of view of the corresponding image acquisition device;

[0035] A determination module, configured to perform expression feature recognition on a face image in a target frame corresponding to the first face video data, and determine facial expression features of faces in multiple frames of face images in the first face video data;

[0036] A recognition module, configured to recognize a change relationship between facial expression feature points in adjacent frames of face images according to the facial expression features, and determine a change degree of a first facial expression of the face in the first face video data based on the change relationship, wherein the first face video data is any one of the multiple video data;

[0037] The execution module is used to obtain the target video data corresponding to the target expression change degree if the target expression change degree is greater than a set degree threshold, and switch the current display viewing angle of the display panel to the target acquisition viewing angle according to the target acquisition viewing angle corresponding to the target video data, so that the current display video of the display panel is the video image captured by the target image acquisition device corresponding to the target acquisition viewing angle.

[0038] Optionally, the determining module includes:

[0039] A first determination submodule is used to determine the position information of the face key points of the face image in each target frame in the first face video data in the target frame, wherein the face key points include: eye key points, eyebrow key points, nose key points and mouth key points;

[0040] A second determination submodule is used to determine the position change trend of the same facial key point in each target frame in consecutive target frames according to the position information;

[0041] An acquisition submodule is used to acquire a mapping relationship between a set facial expression feature and a position change trend corresponding to a facial organ type of a facial key point;

[0042] A first generating submodule, used for generating a plurality of key point expression features of each facial key point in the first facial video data according to the mapping relationship and the position change trend;

[0043] The second generating submodule is used to fit the multiple key point expression features according to a preset weight relationship to generate the facial expression features.

[0044] According to a third aspect of an embodiment of the present disclosure, there is provided a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods described in the first aspect are implemented.

[0045] According to a fourth aspect of an embodiment of the present disclosure, there is provided an electronic device, including:

[0046] processor;

[0047] a memory for storing processor-executable instructions;

[0048] The processor is configured to execute executable instructions in the memory to implement the method described in any one of the first aspects.

[0049] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0050] Through the above-mentioned method, in response to multiple video data collected by multiple image acquisition devices, face recognition is performed on each frame of image data in the multiple video data, and target frames with face images in the multiple video data are extracted, and face video data corresponding to each video data is generated based on the time domain sequence of the target frames, wherein the image acquisition devices correspond to different acquisition angles, and each video data is associated with the acquisition angle of the corresponding image acquisition device, and expression feature recognition is performed on the face image in the target frame corresponding to the first face video data, and the facial expression features of the faces in multiple frames of face images in the first face video data are determined, and according to the facial expression Features, identifying the change relationship between facial expression feature points in adjacent frames of facial images, determining the degree of change of the first facial expression of the face in the first facial video data based on the change relationship, wherein the first facial video data is any video data among the multiple video data, and if the target expression change degree is greater than the set degree threshold, then obtaining the target video data corresponding to the target expression change degree, and switching the current display angle of the display panel to the target acquisition angle according to the target acquisition angle corresponding to the target video data, so that the current display video of the display panel is the video image collected by the target image acquisition device corresponding to the target acquisition angle. Thus, the facial expression changes of the face are captured through face recognition, and when there is a large expression change on the face, the display angle is automatically switched, which improves the intelligence of the display panel angle switching and improves the user experience.

[0051] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0053] Figure 1 The figure is a flow chart showing a method for controlling viewing angle switching of a display panel according to an exemplary embodiment.

[0054] Figure 2 The invention is a block diagram showing a viewing angle switching control device of a display panel according to an exemplary embodiment. DETAILED DESCRIPTION

[0055] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0056] It should be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located, and with the authorization given by the owner of the corresponding device.

[0057] Figure 1 FIG. 1 is a flow chart showing a method for controlling a viewing angle switching of a display panel according to an exemplary embodiment. Figure 1 As shown, the method includes:

[0058] In step S11, in response to multiple video data acquired by multiple image acquisition devices, face recognition is performed on each frame of image data in the multiple video data, and target frames containing face images in the multiple video data are extracted, and face video data corresponding to each video data is generated based on the time domain sequence of the target frames, wherein each image acquisition device has a different acquisition viewing angle, and each video data is associated with the acquisition viewing angle of the corresponding image acquisition device.

[0059] By way of example, this embodiment is applied to a terminal, which displays images through a display panel, and the display panel is connected to multiple image acquisition devices for acquiring video data from different viewing angles. The image acquisition device acquires multiple video data and sends them to the display panel, performs facial feature recognition on each frame of image data in the multiple video data, and extracts target frames containing facial images from the multiple video data. By way of example, faces in each frame of image data in the video data can be recognized by a related facial feature recognition algorithm, and features of target frames containing facial images from the multiple video data can be extracted, and facial video data corresponding to each video data can be generated according to the time domain sequence of the target frames.

[0060] In step S12, expression feature recognition is performed on the face image in the target frame corresponding to the first face video data to determine the facial expression features of the faces in the multiple frames of face images in the first face video data.

[0061] Optionally, in some embodiments, position information of facial key points of the facial image in each target frame in the first facial video data is determined in the target frame, the facial key points including: eye key points, eyebrow key points, nose key points and mouth key points;

[0062] Determining, based on the position information, a position change trend of the same facial key point in each target frame in consecutive target frames;

[0063] Obtaining the mapping relationship between the facial expression features and position change trends of the facial key points corresponding to the facial organ types of the human face;

[0064] generating a plurality of key point expression features of each facial key point in the first facial video data according to the mapping relationship and the position change trend;

[0065] According to a preset weight relationship, the multiple key point expression features are fitted to generate the facial expression features.

[0066] Optionally, in some embodiments, determining the position information of the facial key points of the facial images in each target frame in the first facial video data in the target frame includes:

[0067] Performing a multi-scale transformation on an image in a first target frame to generate a first image pyramid set of different sizes corresponding to the first target frame, where the first target frame is any target frame in the first face video data;

[0068] Performing frame selection evaluation on facial organ features in the first image pyramid set by using sliding frames corresponding to different types of facial key points, and determining a plurality of frame selection image sets whose evaluation scores are greater than a set threshold;

[0069] The multiple framed image sets are merged to determine the image area of ​​the facial organ features in the first target frame, and the target position information corresponding to the center of the image area is used as the position information of the facial key points in the first target frame.

[0070] Optionally, in some embodiments, the step of performing frame selection evaluation on facial organ features in the first image pyramid set by using sliding frames corresponding to different types of facial key points to determine a plurality of frame selection image sets having evaluation scores greater than a set threshold comprises:

[0071] Performing contour recognition on the facial organs in the first target frame to identify multiple regional positions of each facial organ in the first target frame;

[0072] Divide the first target frame into images according to the multiple region positions to generate multiple second target frames corresponding to different facial organs;

[0073] The facial organ feature selection evaluation is performed on the third target frame according to the target sliding frame to generate a selected image with an evaluation score greater than the set threshold, the third target frame is any target frame among the multiple second target frames, and the target sliding frame is a sliding frame that matches the facial organ type corresponding to the third target frame.

[0074] In step S13, according to the facial expression features, the change relationship between the facial expression feature points in adjacent frame face images is identified, and the degree of change of the first expression of the face in the first face video data is determined based on the change relationship, wherein the first face video data is any one of the multiple video data.

[0075] Optionally, in some embodiments, the above step of identifying the change relationship between facial expression feature points in adjacent frames of facial images according to the facial expression features includes:

[0076] According to the facial expression features, dividing the image frames of the first face video data corresponding to the areas where the facial key points in the adjacent target frames are located into regions;

[0077] Determine adjacent change information according to the position change relationship of facial key points in the same area of ​​the same face in two adjacent target frames;

[0078] Tracking the position transformation relationship of the same facial key point in different image frames in the target frame corresponding to the first facial video image to determine continuous change information;

[0079] The change relationship is determined according to the adjacent change information and the continuous change information.

[0080] Optionally, in some embodiments, determining the change relationship according to the adjacent change information and the continuous change information includes:

[0081] Determining a change trend of the facial key points according to the adjacent change information;

[0082] Correcting the contact change information according to the change trend to generate target change information;

[0083] Determining a change characteristic vector of the facial key points according to the target change information;

[0084] The change relationship is generated according to the change feature vector.

[0085] In step S14, if the degree of change of the target expression is greater than a set degree threshold, the target video data corresponding to the degree of change of the target expression is obtained, and according to the target acquisition angle corresponding to the target video data, the current display angle of the display panel is switched to the target acquisition angle, so that the currently displayed video of the display panel is the video image captured by the target image acquisition device corresponding to the target acquisition angle.

[0086] Through the above-mentioned method, in response to multiple video data collected by multiple image acquisition devices, face recognition is performed on each frame of image data in the multiple video data, and target frames with face images in the multiple video data are extracted, and face video data corresponding to each video data is generated based on the time domain sequence of the target frames, wherein the image acquisition devices correspond to different acquisition angles, and each video data is associated with the acquisition angle of the corresponding image acquisition device, and expression feature recognition is performed on the face image in the target frame corresponding to the first face video data, and the facial expression features of the faces in multiple frames of face images in the first face video data are determined, and according to the facial expression Features, identifying the change relationship between facial expression feature points in adjacent frames of facial images, determining the degree of change of the first facial expression of the face in the first facial video data based on the change relationship, wherein the first facial video data is any video data among the multiple video data, and if the target expression change degree is greater than the set degree threshold, then obtaining the target video data corresponding to the target expression change degree, and switching the current display angle of the display panel to the target acquisition angle according to the target acquisition angle corresponding to the target video data, so that the current display video of the display panel is the video image collected by the target image acquisition device corresponding to the target acquisition angle. Thus, the facial expression changes of the face are captured through face recognition, and when there is a large expression change on the face, the display angle is automatically switched, which improves the intelligence of the display panel angle switching and improves the user experience.

[0087] Figure 2FIG. 1 is a block diagram of a display panel viewing angle switching control device according to an exemplary embodiment. Figure 2 As shown, the device 100 includes:

[0088] The generating module 110 is used for performing face recognition on each frame of image data in the multiple video data in response to the multiple video data collected by the multiple image acquisition devices, extracting the target frame with the face image in the multiple video data, and generating the face video data corresponding to each video data based on the time domain sequence of the target frame, wherein the acquisition angle corresponding to each image acquisition device is different, and each video data is associated with the acquisition angle of the corresponding image acquisition device;

[0089] A determination module 120 is used to perform expression feature recognition on a face image in a target frame corresponding to the first face video data, and determine facial expression features of faces in multiple frames of face images in the first face video data;

[0090] The recognition module 130 is used to identify the change relationship between the facial expression feature points in the facial images of adjacent frames according to the facial expression features, and determine the degree of change of the first facial expression of the face in the first facial video data based on the change relationship, wherein the first facial video data is any one of the multiple video data;

[0091] The execution module 140 is used to obtain the target video data corresponding to the target expression change degree if the target expression change degree is greater than a set degree threshold, and switch the current display viewing angle of the display panel to the target acquisition viewing angle according to the target acquisition viewing angle corresponding to the target video data, so that the current display video of the display panel is the video image captured by the target image acquisition device corresponding to the target acquisition viewing angle.

[0092] Optionally, the determining module 120 includes:

[0093] A first determination submodule is used to determine the position information of the face key points of the face image in each target frame in the first face video data in the target frame, wherein the face key points include: eye key points, eyebrow key points, nose key points and mouth key points;

[0094] A second determination submodule is used to determine the position change trend of the same facial key point in each target frame in consecutive target frames according to the position information;

[0095] An acquisition submodule is used to acquire a mapping relationship between a set facial expression feature and a position change trend corresponding to a facial organ type of a facial key point;

[0096] A first generating submodule, used for generating a plurality of key point expression features of each facial key point in the first facial video data according to the mapping relationship and the position change trend;

[0097] The second generating submodule is used to fit the multiple key point expression features according to a preset weight relationship to generate the facial expression features.

[0098] Optionally, the first determining submodule includes:

[0099] a generating unit, configured to perform a multi-scale transformation on an image in a first target frame to generate a first image pyramid set of different sizes corresponding to the first target frame, wherein the first target frame is any target frame in the first face video data;

[0100] A first determining unit is used to perform frame selection evaluation on facial organ features in the first image pyramid set through sliding frames corresponding to different types of facial key points, and determine a plurality of frame selection image sets whose evaluation scores are greater than a set threshold;

[0101] The second determination unit is used to merge the multiple framed image sets, determine the image area of ​​the facial organ features in the first target frame, and use the target position information corresponding to the center of the image area as the position information of the facial key points in the first target frame.

[0102] Optionally, the first determining unit is configured to:

[0103] Performing contour recognition on the facial organs in the first target frame to identify multiple regional positions of each facial organ in the first target frame;

[0104] Divide the first target frame into images according to the multiple region positions to generate multiple second target frames corresponding to different facial organs;

[0105] The facial organ feature selection evaluation is performed on the third target frame according to the target sliding frame to generate a selected image with an evaluation score greater than the set threshold, the third target frame is any target frame among the multiple second target frames, and the target sliding frame is a sliding frame that matches the facial organ type corresponding to the third target frame.

[0106] Optionally, the identification module 130 includes:

[0107] A division submodule, for dividing the image frames of the first face video data corresponding to the areas where the face key points in the adjacent target frames are located according to the facial expression features;

[0108] The first determination submodule is used to determine adjacent change information according to the position change relationship of the facial key points in the same area of ​​the same face in two adjacent target frames;

[0109] A second determination submodule is used to track the position transformation relationship of the same facial key point in different image frames in the target frame corresponding to the first facial video image to determine continuous change information;

[0110] The third determining submodule is used to determine the change relationship according to the adjacent change information and the continuous change information.

[0111] Through the above-mentioned method, in response to multiple video data collected by multiple image acquisition devices, face recognition is performed on each frame of image data in the multiple video data, and target frames with face images in the multiple video data are extracted, and face video data corresponding to each video data is generated based on the time domain sequence of the target frames, wherein the image acquisition devices correspond to different acquisition angles, and each video data is associated with the acquisition angle of the corresponding image acquisition device, and expression feature recognition is performed on the face image in the target frame corresponding to the first face video data, and the facial expression features of the faces in multiple frames of face images in the first face video data are determined, and according to the facial expression Features, identifying the change relationship between facial expression feature points in adjacent frames of facial images, determining the degree of change of the first facial expression of the face in the first facial video data based on the change relationship, wherein the first facial video data is any video data among the multiple video data, and if the target expression change degree is greater than the set degree threshold, then obtaining the target video data corresponding to the target expression change degree, and switching the current display angle of the display panel to the target acquisition angle according to the target acquisition angle corresponding to the target video data, so that the current display video of the display panel is the video image collected by the target image acquisition device corresponding to the target acquisition angle. Thus, the facial expression changes of the face are captured through face recognition, and when there is a large expression change on the face, the display angle is automatically switched, which improves the intelligence of the display panel angle switching and improves the user experience.

[0112] The present disclosure also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in any one of the aforementioned embodiments are implemented.

[0113] The present disclosure also provides an electronic device, including:

[0114] processor;

[0115] a memory for storing processor-executable instructions;

[0116] The processor is configured to execute executable instructions in the memory to implement the method described in any one of the aforementioned embodiments.

[0117] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0118] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for controlling viewing angle switching of a display panel, characterized in that: The method comprises: In response to a plurality of video data collected by a plurality of image acquisition devices, face recognition is performed on each frame of image data in the plurality of video data, and a target frame having a face image in the plurality of video data is extracted, and face video data corresponding to each video data is generated based on the time domain sequence of the target frame, wherein each image acquisition device corresponds to a different acquisition angle of view, and each video data is associated with the acquisition angle of view of the corresponding image acquisition device; Performing expression feature recognition on the face image in the target frame corresponding to the first face video data to determine the facial expression features of the faces in the multiple frames of face images in the first face video data; According to the facial expression features, identifying the change relationship between facial expression feature points in adjacent frames of face images, and determining the degree of change of the first facial expression of the face in the first face video data based on the change relationship, wherein the first face video data is any one of the multiple video data; If the target expression change degree is greater than a set degree threshold, then the target video data corresponding to the target expression change degree is obtained, and according to the target acquisition angle corresponding to the target video data, the current display angle of the display panel is switched to the target acquisition angle, so that the current display video of the display panel is the video image acquired by the target image acquisition device corresponding to the target acquisition angle; The step of performing expression feature recognition on the face image in the target frame corresponding to the first face video data to determine the facial expression features of the faces in the multiple frames of face images in the first face video data includes: Determine the position information of the face key points of the face image in each target frame in the first face video data, wherein the face key points include: eye key points, eyebrow key points, nose key points and mouth key points; Determining, based on the position information, a position change trend of the same facial key point in each target frame in consecutive target frames; Obtaining the mapping relationship between the facial expression features and position change trends of the facial key points corresponding to the facial organ types of the human face; generating a plurality of key point expression features of each facial key point in the first facial video data according to the mapping relationship and the position change trend; Fitting the multiple key point expression features according to a preset weight relationship to generate the facial expression features; The step of identifying the change relationship between facial expression feature points in adjacent frames of facial images according to the facial expression features comprises: According to the facial expression features, dividing the image frames of the first face video data corresponding to the areas where the facial key points in the adjacent target frames are located into regions; Determine adjacent change information according to the position change relationship of facial key points in the same area of ​​the same face in two adjacent target frames; Tracking the position transformation relationship of the same facial key point in different image frames in the target frame corresponding to the first facial video data to determine continuous change information; Determining the change relationship according to the adjacent change information and the continuous change information; The determining the change relationship according to the adjacent change information and the continuous change information includes: Determining a change trend of the facial key points according to the adjacent change information; Correcting the continuous change information according to the change trend to generate target change information; Determine the change feature vector of the facial key points according to the target change information; The change relationship is generated according to the change feature vector.

2. The viewing angle switching control method of a display panel according to claim 1, characterized in that: The determining of the position information of the facial key points of the facial images in each target frame in the first facial video data in the target frame includes: Performing a multi-scale transformation on an image in a first target frame to generate a first image pyramid set of different sizes corresponding to the first target frame, where the first target frame is any target frame in the first face video data; Performing frame selection evaluation on facial organ features in the first image pyramid set by using sliding frames corresponding to different types of facial key points, and determining a plurality of frame selection image sets whose evaluation scores are greater than a set threshold; The multiple framed image sets are merged to determine the image area of ​​the facial organ features in the first target frame, and the target position information corresponding to the center of the image area is used as the position information of the facial key points in the first target frame.

3. The viewing angle switching control method of a display panel according to claim 2, characterized in that: The step of evaluating the facial organ features in the first image pyramid set by using sliding frames corresponding to different types of facial key points to determine a plurality of frame-selected image sets having evaluation scores greater than a set threshold comprises: Performing contour recognition on the facial organs in the first target frame to identify multiple regional positions of each facial organ in the first target frame; Divide the first target frame into images according to the multiple region positions to generate multiple second target frames corresponding to different facial organs; The facial organ feature selection evaluation is performed on the third target frame according to the target sliding frame to generate a selected image with an evaluation score greater than the set threshold, the third target frame is any target frame among the multiple second target frames, and the target sliding frame is a sliding frame that matches the facial organ type corresponding to the third target frame.

4. A viewing angle switching control device for a display panel, characterized in that: The device comprises: A generating module, configured to perform face recognition on each frame of image data in the multiple video data in response to the multiple video data collected by the multiple image acquisition devices, extract the target frame containing the face image in the multiple video data, and generate face video data corresponding to each video data based on the time domain sequence of the target frame, wherein each image acquisition device has a different acquisition angle of view, and each video data is associated with the acquisition angle of view of the corresponding image acquisition device; A determination module, configured to perform expression feature recognition on a face image in a target frame corresponding to the first face video data, and determine facial expression features of faces in multiple frames of face images in the first face video data; The recognition module is used to recognize the change relationship between facial expression feature points in adjacent frames of face images according to the facial expression features, and determine the degree of change of the first expression of the face in the first face video data based on the change relationship, wherein the first face video data is any video data of the multiple video data; the recognition of the change relationship between facial expression feature points in adjacent frames of face images according to the facial expression features includes: dividing the image frames of the first face video data corresponding to the areas where the facial key points in adjacent target frames are located according to the facial expression features; dividing the image frames according to the positions of the facial key points in the same area of ​​the same face in two adjacent target frames; system, determining adjacent change information; tracking the position transformation relationship of the same face key point in different image frames in the target frame corresponding to the first face video data to determine continuous change information; determining the change relationship according to the adjacent change information and the continuous change information; the determining the change relationship according to the adjacent change information and the continuous change information includes: determining the change trend of the face key point according to the adjacent change information; correcting the continuous change information according to the change trend to generate target change information; determining the change feature vector of the face key point according to the target change information; generating the change relationship according to the change feature vector; An execution module, configured to obtain target video data corresponding to the target expression change degree if the target expression change degree is greater than a set degree threshold, and switch the current display viewing angle of the display panel to the target acquisition viewing angle according to the target acquisition viewing angle corresponding to the target video data, so that the current display video of the display panel is the video image acquired by the target image acquisition device corresponding to the target acquisition viewing angle; The determining module comprises: A first determination submodule is used to determine the position information of the face key points of the face image in each target frame in the first face video data in the target frame, wherein the face key points include: eye key points, eyebrow key points, nose key points and mouth key points; A second determination submodule is used to determine the position change trend of the same facial key point in each target frame in consecutive target frames according to the position information; An acquisition submodule is used to acquire a mapping relationship between a set facial expression feature and a position change trend corresponding to a facial organ type of a facial key point; A first generating submodule, used for generating a plurality of key point expression features of each facial key point in the first facial video data according to the mapping relationship and the position change trend; The second generating submodule is used to fit the multiple key point expression features according to a preset weight relationship to generate the facial expression features.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 3 are implemented.

6. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute executable instructions in the memory to implement the method described in any one of claims 1 to 3.

Citation Information

Patent Citations

  • Human face identification based related information pushing device and method

    CN105426850A

  • Method and device for sending information on basis of facial expressions

    CN106445107A

  • Broadcast directing method and device, terminal device and storage medium

    CN110166651A

  • Emotion detection method and device based on voice recognition and image recognition

    CN112232276A

  • Image processing method and device, computer equipment and storage medium

    CN115063720A