Picture display method, system and equipment for portrait tracking and storage medium

Abstract

The invention discloses a portrait tracking picture display method, system and device and a storage medium, and the method comprises the steps: receiving and outputting a close-up picture of a first speaker on a video conference device when the first speaker is detected to speak; detecting a new speaking event in a preset time window; if at least one new speaker is detected to speak, synchronously obtaining close-up pictures of the new speakers; and according to the speaking time sequence of the new speakers, sub-display areas are divided for each new speaker in sequence, and the close-up pictures of the speakers are displayed on a display interface of the video conference equipment according to a preset layout rule. According to the invention, the picture display can be dynamically adjusted according to the speaking conditions of the participants, and the picture display effect and user experience of the video conference are improved.

Description

Technical Field

[0001] The present application relates to the field of portrait tracking and image display technology, and in particular to a method, system, device and storage medium for image display of portrait tracking. Background Art

[0002] With the widespread adoption of video conferencing technology, people are increasingly demanding higher standards for the quality and user experience of video conferencing. In scenarios such as video conferencing, accurately tracking speakers and optimizing the image display are crucial to improving the meeting experience. However, when communicating with remote devices, current video conferencing equipment statically displays part or specific areas of the conference room based on a fixed field of view or a PTZ / preset position image, and is unable to dynamically focus on the subject of communication. Although some video conferencing equipment allows for adjusting the image frame to select an area with people or voice tracking the current speaker, existing video conferencing equipment cannot solve the problem of focusing the display image on the few speakers who are interacting in scenarios where multiple people are speaking. This fails to effectively simulate the visual changes during face-to-face conversations, weakening the immersiveness and sense of presence of communication. Summary of the Invention

[0003] The main purpose of this application is to overcome the shortcomings and deficiencies of the existing technology and to provide a screen display method, system, device and storage medium for portrait tracking, which can dynamically adjust the screen display according to the speeches of the participants, thereby improving the screen display effect and user experience of video conferencing.

[0004] In order to achieve the above objectives, this application adopts the following technical solutions:

[0005] In a first aspect, the present application provides a method for displaying a portrait tracking image, comprising:

[0006] When a first speaker is detected speaking, a close-up image of the first speaker is received and outputted on the video conferencing device;

[0007] Detecting new speech events within a preset time window;

[0008] If at least one new speaker is detected, a close-up image of each new speaker is obtained simultaneously;

[0009] According to the speaking sequence of the new speaker, a sub-display area is divided for each new speaker in sequence, and a close-up image of each speaker is displayed on the display interface of the video conferencing device according to a preset layout rule.

[0010] As a preferred technical solution,

[0011] If a new speaker is detected, a close-up image of the new speaker is obtained simultaneously. Sub-display areas are divided for each new speaker in sequence according to the speaking time sequence of the new speaker, and the close-up images of each speaker are displayed on the display interface of the video conferencing device according to the preset layout rules, including:

[0012] The display interface of the video conferencing device is set to two sub-display areas, and the close-up picture of the new speaker and the close-up picture of the first speaker are controlled to be displayed in the two sub-display areas of the video conferencing device respectively.

[0013] As a preferred technical solution, if two or more new speakers are detected, sub-display areas are sequentially divided for each new speaker according to the speaking time sequence of the new speaker, and close-up images of each speaker are displayed on the display interface of the video conferencing device according to preset layout rules, including:

[0014] Every time a new speaker is detected, the sub-display area of ​​the video conference display interface is re-divided, and the close-up image already displayed on the video conferencing device is moved to the sub-display area in the preset direction, so that the close-up image of the new speaker is added to the newly added sub-display area.

[0015] As an optimal technical solution, it also includes: establishing a speaking time record table for all speakers; confirming the time difference between the last speaking time of each speaker and the current time based on the speaking time record table, and if the time difference exceeds the preset time threshold, removing the close-up image of the speaker from the display area.

[0016] As an optimal technical solution, it also includes: presetting a priority display area of ​​the current conference environment; receiving close-up images of participants in the priority display area, and fixing the close-up images of participants in the priority display area on the display interface of the conference video device for display.

[0017] As a preferred technical solution,

[0018] The receiving of the close-up image of the participant in the priority display area includes:

[0019] When multiple participants are detected in the priority display area, evaluating the contour completeness and screen ratio parameters of the portraits of the multiple participants;

[0020] Based on the descending order of the contour completeness and screen proportion parameters of the portraits of the multiple participants, it is determined that the participant ranked first is the participant in the priority display area to be displayed.

[0021] In a second aspect, the present application provides a system for displaying a portrait tracking image, which is applied to the above-mentioned method for displaying a portrait tracking image.

[0022] It includes: a processing module and a video conferencing device, wherein the processing module is connected to the video conferencing device;

[0023] Among them, the processing module is used to detect when the first speaker is speaking, receive and output the close-up image of the first speaker on the video conferencing device; detect new speaking events within a preset time window; if at least one new speaker is detected speaking, synchronously obtain close-up images of each new speaker; divide the sub-display area for each new speaker in sequence according to the speaking timing of the new speaker, and display the close-up images of all speakers on the display interface of the video conferencing device according to the preset layout rules.

[0024] As an optimal technical solution, the processing module is also used to preset the priority display area of ​​the current conference environment; receive close-up images of participants in the priority display area, and fix the close-up images of participants in the priority display area on the display interface of the conference video device for display.

[0025] Thirdly, this application is achieved through the following technical solutions:

[0026] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned methods for displaying a portrait tracking image are implemented.

[0027] In a fourth aspect, the present application provides a computer-readable storage medium.

[0028] This application is achieved through the following technical solutions:

[0029] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned methods for displaying a portrait tracking image.

[0030] In summary, compared with the prior art, the effective effects brought about by the technical solution provided by this application include at least:

[0031] When this application detects that the first speaker is speaking, it receives and outputs a close-up picture of the first speaker on the video conferencing device; detects new speaking events within a preset time window; if at least one new speaker is detected speaking, it synchronously obtains close-up pictures of each new speaker; divides sub-display areas for each new speaker in sequence according to the speaking timing of the new speaker, and displays close-up pictures of all speakers on the display interface of the video conferencing device according to preset layout rules. This application can focus on the main speaker, and based on the speaking situation of other participants, it can capture close-up pictures of new speakers in real time, and dynamically adjust the close-up pictures displayed on the display interface of the video conferencing device, which can effectively provide a more immersive video experience; at the same time, this application also pre-sets the priority display area of ​​the conference environment, detects the portraits of the priority display area, and the participants in the priority display area are independent of their speaking status, and the close-up pictures of the participants will be displayed on the video conferencing device first, which can highlight important participants. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0033] Figure 1 A flowchart of a method for displaying a portrait tracking image provided by one embodiment of the present application;

[0034] Figure 2 A schematic structural diagram of a portrait tracking image display system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0035] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0036] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0037] In addition, the term "and / or" in this application is simply a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this application, unless otherwise specified, generally indicates that the related objects are in an "or" relationship.

[0038] In this application, the terms "first", "second", etc. are used to distinguish identical or similar items with substantially the same effects and functions. It should be understood that there is no logical or temporal dependency between "first", "second", and "nth", nor is there any limitation on the quantity and execution order.

[0039] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0040] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0041] See Figure 1 As shown, in one embodiment of the present application, a method for displaying a portrait tracking image is provided, which specifically includes the following steps:

[0042] S1: When the first speaker is detected speaking, a close-up image of the first speaker is received and output on the video conferencing device.

[0043] Specifically, when the sound source of the first speaker is detected, the time difference between the sound source signal and the time difference between the sound source signal and the microphone is calculated; based on the time difference, the audio direction information of the sound source signal is determined using a sound source localization algorithm.

[0044] For example, when someone speaks in a conference environment, the sound source signal will propagate to each microphone in the array at different speeds; by calculating the time difference when the sound source signal reaches different microphones, the distance difference between the sound source and each microphone can be calculated. Based on this distance difference, the sound source localization algorithm is used to determine the position of the sound source, infer the direction and distance of the sound source, and thus accurately determine the position of the first speaker, and then accurately track the first speaker.

[0045] It should be noted that a close-up image refers to an image that focuses on the head or other details of a participant. For example, after all participants have taken their seats in the conference room or someone is detected speaking in the conference room, the participant who is speaking is determined through microphone sound source positioning, and a portrait image of the speaking participant is obtained. The processor uses portrait recognition technology to adjust the size of the participant's portrait and crop it, keeping the head of the speaker's portrait at the top 1 / 4 during cropping. This setting can provide a face-to-face meeting experience with eye level for remote participants. A certain amount of space is reserved around the portrait to show the participant's simple movements.

[0046] S2: Detect new speech events within a preset time window.

[0047] Specifically, after obtaining a close-up of the first speaker, this application uses a sound source localization algorithm and lip movement detection to determine the speaking status of other participants within a preset time window. When other participants are detected speaking within the preset time window, the position information determined by the sound source localization algorithm is used and lip movement detection is performed on the participant to determine the speaking participant.

[0048] S3: If at least one new speaker is detected, a close-up image of each new speaker is synchronously obtained.

[0049] Specifically, when a new speaker is detected, a portrait of the participant who spoke is obtained, and the portrait is processed to obtain a close-up picture of a preset size.

[0050] S4: dividing the sub-display area for each new speaker in sequence according to the speaking sequence of the new speaker, and displaying the close-up image of each speaker on the display interface of the video conferencing device according to a preset layout rule.

[0051] Specifically, according to the speaking sequence of the new speaker detected within the preset time window, the close-up images of the new speaker are dynamically added to the display interface of the video conferencing device according to the preset layout rules, and displayed together with the close-up image of the first speaker.

[0052] This application can capture and add close-up images of new speakers in real time based on the speeches of the participants, and dynamically adjust the close-up images displayed on the display interface of the video conferencing equipment, which can effectively provide a more immersive video experience.

[0053] Among them, the specific implementation process of using sound source localization algorithm and lip movement detection to determine the speaking timing of a new speaker within a preset time window is: when the camera determines that there is more than one target of the audio orientation based on the audio orientation information, by capturing continuous lip dynamic frame information and judging the dynamic changes of the lips, it can distinguish the current speaker, track and identify and focus on the speaker whose lips are moving.

[0054] Specifically, based on the participant's lip dynamic frame information, the current target tracking person is determined, including:

[0055] Perform face detection on each frame of the video sequence;

[0056] Extracting key facial feature point information based on the detected face, wherein the key facial feature point information includes lip feature point information;

[0057] For example, in the embodiments of the present application, a key point detection algorithm is used to extract key feature point information of the face.

[0058] Using a tracking algorithm, the lip feature point information of the same face in consecutive frames is correlated and matched to obtain the motion trajectory of the lip area of ​​the same face in consecutive video frames, thereby achieving continuous tracking of lip movements;

[0059] Based on the motion trajectory of the lip area of ​​the same face in consecutive frames, the SVM classifier is used to calculate the lip state of the same face in each frame. The lip state includes the degree of lip closure or opening.

[0060] The system performs a fusion analysis of the lip movements of the same face in a preset n consecutive frames to determine the current target person. When there are multiple speakers, the system combines the lip movement information of all participants to more accurately determine the current speaker and distinguish the speaking sequence of each speaker.

[0061] Furthermore, if a new speaker is detected, a close-up image of the new speaker is obtained synchronously, and sub-display areas are divided for each new speaker in sequence according to the speaking time of the new speaker, and close-up images of all participants are displayed on the display interface of the video conferencing device according to the preset layout rules, including:

[0062] The display interface of the video conferencing device is set to two sub-display areas, and the close-up image of the new speaker and the close-up image of the first speaker are controlled to be displayed in the two sub-display areas of the video conferencing device respectively.

[0063] In actual implementation, if only one new speaker is detected speaking within a preset time window, a close-up image of the new speaker is obtained; the display area of ​​the video conferencing device is divided into a first sub-display area and a second sub-display area, the first sub-display area being used to display a close-up image of the first speaker, and the second sub-display area being used to display a close-up image of the newly detected participant speaking within the preset time window, i.e., a close-up image of the new speaker. The size and position of the first sub-display area and the second sub-display area in the display area of ​​the conference video device can be set according to actual needs. For example, the first sub-display area and the second sub-display area are displayed in a 9:8 ratio, with the first sub-display area located on the left side of the display area of ​​the conference video device and the second sub-display area located on the right side of the display area of ​​the conference video device.

[0064] Furthermore, if more than two new speakers are detected, sub-display areas are sequentially divided for each new speaker according to the speaking sequence of the new speaker, and close-up images of each speaker are displayed on the display interface of the video conferencing device according to preset layout rules, including:

[0065] Every time a new speaker is detected, the sub-display area of ​​the video conference display interface is re-divided, and the close-up image already displayed on the video conferencing device is moved to the sub-display area in the preset direction, so that the close-up image of the new speaker is added to the newly added sub-display area.

[0066] For example, if two participants are detected speaking within a preset time window, they are recorded as Participant A and Participant B in the order of their speeches. When a participant is detected speaking, a close-up image of that participant is simultaneously captured. When Participant A is detected speaking, a close-up image of Participant A is captured, and the close-up image of the first speaker and Participant A are displayed in the first and second sub-display areas of the video conferencing device's display area, respectively, with the first sub-display area located on the left and the second sub-display area located on the right. When Participant B is detected speaking, a close-up image of Participant B is captured and added to the video conferencing device's display area. The video conferencing device's display area is now divided into three sub-display areas: a first sub-display area, a second sub-display area, and a third sub-display area. The first sub-display area is used to display the close-up image of the first speaker, the second sub-display area is used to display the close-up image of Participant A, and the third sub-display area is used to display the close-up image of Participant B. That is, when the close-up image of participant B is added to the display area of ​​the video conferencing device, the close-up image of the first speaker and the close-up image of participant A are moved to the left and displayed in the first sub-display area and the second sub-display area respectively, and the close-up image of participant B is displayed in the third sub-display area on the far right.

[0067] It should be noted that the display area of ​​the video conferencing device can display close-up images of up to 6 participants.

[0068] Furthermore, a record sheet of the speaker's speaking time is established;

[0069] The time difference between the last speaking time of each speaker and the current time is determined based on the speaking time record table. If the time difference exceeds a preset time threshold, the close-up image of the speaker is removed from the display area.

[0070] Specifically, the present application records each speaker's speaking time record sheet, which records the start and end time of each speaker's speech, and calculates the time difference between the end time of each participant's last speech and the current time, that is, records the time each participant has not spoken. When the non-speaking time exceeds a preset time threshold, the close-up image of the participant is removed from the display area. The preset time threshold can be modified according to actual needs. For example, within the preset time window, two different participants are detected speaking. At this time, the display area of ​​the video conferencing device displays close-ups of the first speaker i, participants A, and participants B. According to the speaking time record sheet, it is confirmed that the non-speaking time of participant A is 11 minutes, which exceeds the preset threshold of 10 minutes. Therefore, the close-up image of participant A is removed from the display area of ​​the video conferencing device; at the same time, the size of the display area of ​​the remaining close-up images of the first speaker i and participant B is adjusted.

[0071] Furthermore, the priority display area of ​​the current conference environment is preset, and when the first participant is detected to be speaking, a close-up image of the first speaker is received and output on the video conferencing device, further comprising:

[0072] Receive close-up images of participants in the priority display area, and fix the close-up images of participants in the priority display area on the display interface of the conference video device for display.

[0073] In this embodiment, users can choose to set a specific area of ​​the conference environment as a priority display area based on their needs. This priority display area is captured by a specific camera and is used to display the portraits of participants in a fixed area of ​​the conference environment. Regardless of whether the participant is speaking, the priority display area will only display a close-up of one portrait. The close-up of the priority display area is fixedly displayed on the conference interface and is specifically used to display the close-up of the priority display area. At the same time, to ensure the consistency of the interface, when other close-up images are adjusted, the close-up interface of the priority display area follows the other close-up images to maintain the coordination of the overall interface.

[0074] The close-up view of the priority display area will remain on the screen for a long time. The close-ups of other participants will change based on their speaking status, but the close-up view of the priority display area will remain unchanged. If you no longer need to highlight the close-up view of the priority display area, you can disable it in the settings. This will release the close-up view of the priority display area on the conference video device.

[0075] In an embodiment, if the function of the priority display area is in effect normally, when the first participant starts to speak, the current panoramic view screen will fade in and out to a close-up screen of the first speaker and the participant in the priority display area in 8:9 format, the portrait of the participant in the priority display area will be displayed on the right, and the panoramic view screen will be displayed according to the size set by the user. When the second participant starts to speak, the screen will be changed into three display areas, the speaker position in the priority display area will be displayed in the middle position, and the other two closest speaker portraits will be arranged according to the position of the participants in the conference room, and there will be a sliding effect when the frame position changes. When the third participant in the conference room starts to speak, the screen will be changed into four display areas, and the portrait of the person in the priority display area will be displayed on the right side of the middle area;

[0076] In addition, in an embodiment of the present application, if the participant currently displayed on the screen has not spoken for more than a preset time, the close-up image of the participant who has not spoken for more than the preset time will be removed from the video conference screen. If there are multiple participants who have not spoken and their non-speaking time is similar, they will also be removed uniformly.

[0077] If the user sets the priority display area function, and there are participants in the priority display area, the portrait of the participant in the priority display area will be the last to be removed. If the participant in the priority display area does not speak for more than the preset time (such as 10 minutes), but there are other portraits displayed, the close-up of the participant in the priority display area will not be removed, but will be removed synchronously with the removal of the close-up of the last participant. At this time, the overall picture will fade in and out to the panoramic view picture. If the participant in the priority display area speaks within 10 minutes and is the last speaker, the algorithm will remove the participant portraits and frames in order, and finally remove the portrait of the participant in the priority display area.

[0078] If a participant already displayed on the screen leaves the meeting room, the portrait of that participant will be removed instead of randomly selecting a participant to fill in and reduce the number of participants displayed.

[0079] Furthermore, close-up images of participants in the priority display area are received simultaneously, including:

[0080] When multiple participants are detected in the priority display area, the outline completeness and screen ratio parameters of the portraits of the multiple participants are evaluated;

[0081] Based on the outline completeness and screen ratio parameters of the portraits of multiple participants, the portrait of the participant ranked first is selected for tracking.

[0082] See Figure 2 As shown, in another embodiment of the present application, a system for displaying a portrait tracking image is provided.

[0083] The processing module 10 and the video conferencing device 20 are connected to the processing module;

[0084] Among them, the processing module 10 is used to detect when the first participant speaks, receive and output a close-up picture of the first speaker on the video conferencing device 20; detect new speaking events within a preset time window; if at least one new speaker is detected speaking, synchronously obtain close-up pictures of each new speaker; according to the speaking sequence of the new speaker, divide the sub-display area for each new speaker in sequence, and display the close-up picture of each speaker on the display interface of the video conferencing device 20 according to the preset layout rules.

[0085] Furthermore, the processing module is also used to preset the priority display area of ​​the current conference environment; receive close-up images of participants in the priority display area, and fix the close-up images of participants in the priority display area on the display interface of the conference video device for display.

[0086] It should be noted that the image display system for portrait tracking of the present application corresponds one-to-one to the image display method for portrait tracking of the present application. The technical features and beneficial effects described in the embodiment of the above-mentioned image display method for portrait tracking are applicable to the embodiment of the image display system for portrait tracking. For specific contents, please refer to the description in the embodiment of the method of the present application. No further details will be given here. This is hereby declared.

[0087] An embodiment of the present application provides a computer device, which may include a processor, a memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the processor executes the steps of the screen display method for portrait tracking as described in any of the above embodiments.

[0088] The working process, working details and technical effects of the computer device provided in this embodiment can be found in the embodiment of the image display method for portrait tracking above, and will not be described in detail here.

[0089] The present application provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program implements the steps of the image display method for portrait tracking described in any of the above embodiments. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick. The computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable device.

[0090] The working process, working details and technical effects of the computer-readable storage medium provided in this embodiment can be found in the embodiment of the image display method for portrait tracking above, and will not be described in detail here.

[0091] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0092] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0093] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, the division of the above-mentioned functional units and modules is only used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system described in this application is divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. A method for displaying a portrait tracking image, characterized in that: include: When a first speaker is detected speaking, a close-up image of the first speaker is received and outputted on the video conferencing device; Detecting new speech events within a preset time window; If at least one new speaker is detected, a close-up image of each new speaker is obtained simultaneously; According to the speaking sequence of the new speaker, a sub-display area is divided for each new speaker in sequence, and a close-up image of each speaker is displayed on the display interface of the video conferencing device according to a preset layout rule.

2. The image display method for portrait tracking according to claim 1, characterized in that: If a new speaker is detected, a close-up image of the new speaker is obtained simultaneously. Sub-display areas are divided for each new speaker in sequence according to the speaking time sequence of the new speaker, and the close-up images of each speaker are displayed on the display interface of the video conferencing device according to the preset layout rules, including: The display interface of the video conferencing device is set to two sub-display areas, and the close-up picture of the new speaker and the close-up picture of the first speaker are controlled to be displayed in the two sub-display areas of the video conferencing device respectively.

3. The image display method for portrait tracking according to claim 1, characterized in that: If two or more new speakers are detected, sub-display areas are divided for each new speaker in order according to the speaking sequence of the new speaker, and close-up images of each speaker are displayed on the display interface of the video conferencing device according to the preset layout rules, including: Every time a new speaker is detected, the sub-display area of ​​the video conference display interface is re-divided, and the close-up image already displayed on the video conferencing device is moved to the sub-display area in the preset direction, so that the close-up image of the new speaker is added to the newly added sub-display area.

4. The image display method for portrait tracking according to any one of claims 1 to 3, characterized in that: Also includes: Establish a record sheet of speakers’ speaking time; The time difference between the last speaking time of each speaker and the current time is determined based on the speaking time record table. If the time difference exceeds a preset time threshold, the close-up image of the speaker is removed from the display area.

5. The image display method for portrait tracking according to claim 1, characterized in that: Also includes: Preset the priority display area of ​​the current conference environment; A close-up image of the participant in the priority display area is received, and the close-up image of the participant in the priority display area is fixed on the display interface of the conference video device for display.

6. The image display method for portrait tracking according to claim 5, characterized in that: The receiving of the close-up image of the participant in the priority display area includes: When multiple participants are detected in the priority display area, evaluating the contour completeness and screen ratio parameters of the portraits of the multiple participants; Based on the descending order of the contour completeness and screen proportion parameters of the portraits of the multiple participants, it is determined that the participant ranked first is the participant in the priority display area to be displayed.

7. A portrait tracking image display system, characterized in that: The image display method for portrait tracking applied to any one of claims 1 to 6 comprises: a processing module and a video conferencing device, wherein the processing module is connected to the video conferencing device; Among them, the processing module is used to detect when the first speaker is speaking, receive and output the close-up image of the first speaker on the video conferencing device; detect new speaking events within a preset time window; if at least one new speaker is detected speaking, synchronously obtain close-up images of each new speaker; divide the sub-display area for each new speaker in sequence according to the speaking timing of the new speaker, and display the close-up image of each speaker on the display interface of the video conferencing device according to the preset layout rules.

8. The image display system for portrait tracking according to claim 7, characterized in that: The processing module is also used to preset a priority display area of ​​the current conference environment; receive close-up images of participants in the priority display area, and fix the close-up images of participants in the priority display area on the display interface of the conference video device for display.

9. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images