Method, device and computer equipment for dynamic adjustment of video conference framing

Abstract

The present disclosure provides a method and device for dynamically adjusting a video conference framing box and a computer device. The conference system monitors whether a new participant appears in the framing box of the camera in real time. If the new participant appears in the framing box, the motion trajectory of the new participant is collected, and whether the new participant is a participant is determined according to the motion trajectory. If the new participant is a participant, the framing area of the framing box is adjusted according to the motion trajectory of the new participant, so that the framing area of the adjusted framing box contains all the participants. In the present disclosure, the conference system accurately identifies the intention of the new participant through the motion trajectory of the new participant, and only adjusts the framing area of the framing box when the new participant is a participant, thereby avoiding frequent switching of panoramic pictures caused by irrelevant personnel passing through the conference room, and effectively improving the video conference experience of all participants.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, in particular to a method and device for dynamically adjusting a video conference framing box and a computer device. BACKGROUND

[0002] When a remote video conference is conducted, a camera automatically includes all the people in the current scene in a framing box to form a panoramic picture. However, since most conference rooms are now set in a relatively open scene (such as a leisure area of an office) or use glass as a partition of the conference room, when a person not participating in the conference passes through the conference room, the camera automatically adjusts the framing area of the framing box to include the person not participating in the conference in the panoramic picture, which causes the panoramic picture to be switched too frequently and seriously affects the user experience of the participants. SUMMARY

[0003] The present disclosure aims to provide a method and device for dynamically adjusting a video conference framing box, which can avoid frequent switching of a panoramic picture during a video conference and improve the user experience of the participants.

[0004] To achieve the above-mentioned purpose, the present disclosure adopts the following technical solution: a method for dynamically adjusting a video conference framing box, comprising:

[0005] monitoring whether a new participant appears in the framing box;

[0006] if the new participant appears in the framing box, collecting a motion trajectory of the new participant and determining whether the new participant is a participant according to the motion trajectory;

[0007] if the new participant is a participant, adjusting a framing area of the framing box according to the motion trajectory so that the framing area of the framing box after adjustment contains all the participants.

[0008] The present disclosure also provides a device for dynamically adjusting a video conference framing box, comprising:

[0009] a first monitoring module configured to monitor whether a new participant appears in the framing box;

[0010] a determining module configured to, if the new participant appears in the framing box, collect a motion trajectory of the new participant and determine whether the new participant is a participant according to the motion trajectory;

[0011] a first adjusting module configured to, if the new participant is a participant, adjust a framing area of the framing box according to the motion trajectory so that the framing area of the framing box after adjustment contains all the participants.

[0012] The present disclosure also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method according to any one of the preceding embodiments.

[0013] The present disclosure also provides a computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of the method according to any one of the preceding embodiments.

[0014] The present disclosure provides a method and device for dynamically adjusting a video conference framing box and a computer device. The conference system monitors whether a new participant appears in the framing box of the camera in real time. If a new participant appears in the framing box, the motion trajectory of the new participant is collected, and whether the new participant is a participant is determined according to the motion trajectory. If the new participant is a participant, the framing area of the framing box is adjusted according to the motion trajectory of the new participant, so that the framing area of the adjusted framing box contains all the participants. In the present disclosure, the conference system accurately identifies the intention of the new participant (i.e., whether the new participant is a participant in the current video conference) through the motion trajectory of the new participant, and only adjusts the framing area of the framing box when the new participant is a participant, thereby avoiding frequent switching of panoramic pictures caused by irrelevant personnel passing through the conference room (or irrelevant personnel entering the framing box), and effectively improving the video conference experience of all participants. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 is a step schematic diagram of the method for dynamically adjusting a video conference framing box in an embodiment of the present disclosure;

[0016] Figure 2 is a whole structure block diagram of the device for dynamically adjusting a video conference framing box in an embodiment of the present disclosure;

[0017] Figure 3 is a structure schematic block diagram of the computer device in an embodiment of the present disclosure.

[0018] The implementation, functional features and advantages of the present disclosure will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present disclosure and do not limit the present disclosure.

[0020] With reference to Figure 1 In an embodiment of the present disclosure, a method for dynamically adjusting a video conference framing box is provided, comprising:

[0021] S1: monitoring whether a new participant appears in the frame;

[0022] S2: if a new participant appears in the frame, collecting a motion trajectory of the new participant, and judging whether the new participant is a participant according to the motion trajectory;

[0023] S3: if the new participant is a participant, adjusting a framing area of the frame according to the motion trajectory, so that the framing area of the adjusted frame contains all the participants.

[0024] In the embodiment, when the conference system is started, the conference system collects personnel images of all personnel in the framing frame of the current camera through the portrait tracking technology, sets an initial identity number corresponding to each personnel image, and then automatically adjusts the framing area of the framing frame so that the panoramic picture contains all the current participants. During the video conference, the conference system monitors whether new participants appear in the framing frame in real time. If new participants appear, the conference system tracks the new participants through the portrait tracking technology, obtains the motion trajectory of the new participants from the position changes of the new participants in the front and back frames of images collected by the camera, and determines whether the new participants are participants in the current video conference based on the motion trajectory. Specifically, the conference system determines whether the fixed position stay duration of the new participants in the framing frame (the fixed position stay duration represents the duration that the new participants stay at a certain position in the framing area) is greater than a duration threshold according to the motion trajectory; if the fixed position stay duration of the new participants in the framing frame is greater than the duration threshold, the conference system determines that the new participants are participants in the current video conference. After determining that the new participants are participants, the conference system needs to include the new participants in the panoramic picture, and therefore needs to dynamically adjust the framing area of the current framing frame according to the motion trajectory of the new participants, so that the framing area of the adjusted framing frame contains all the participants (all the participants include the initial participants and the new participants). Specifically, the conference system tracks the motion of the new participants in real time, tracks the participant position of the new participants according to the motion trajectory of the new participants, and determines whether the new participants are about to exceed the framing area of the current framing frame. If the new participants are about to exceed the framing area of the framing frame, the conference system predicts the moving direction and moving speed of the new participants according to the motion trajectory of the new participants, sets the adjustment direction of the center of the framing area of the framing frame according to the moving direction, and sets the adjustment speed of the framing frame according to the moving speed. Finally, the conference system adjusts the framing frame according to the set adjustment direction and adjustment speed, so that the change of the panoramic picture during the adjustment of the framing frame is smooth (that is, the change of the panoramic picture during the adjustment of the framing frame is smooth), avoids affecting the video conference experience of the participants, and the framing area of the adjusted framing frame contains all the participants.

[0025] In the embodiment, the conference system accurately identifies the intention of the new participants (that is, whether the new participants are participants in the current video conference) through the motion trajectory of the new participants, and adjusts the framing area of the framing frame only when the new participants are participants, thereby avoiding frequent switching of the panoramic picture caused by irrelevant personnel passing through the conference room (or irrelevant personnel entering the framing frame), and effectively improving the video conference experience of all the participants.

[0026] Further, the step of monitoring whether a new participant appears in the frame includes:

[0027] S101: At the beginning of the video conference, using a portrait tracking technology to collect images of all participants in the frame, and setting an initial identity number for each image;

[0028] S102: Based on the initial identity number, determine whether a new identity number is added in real time;

[0029] S103: If a new identity number is added, it is determined that a new participant appears in the frame.

[0030] In this embodiment, at the beginning of the video conference, the conference system uses a portrait tracking technology to collect images of all participants in the frame, and sets an initial identity number for each image (or sets an initial identity number for all participants). All initial identity numbers are added to the participant list. The portrait tracking technology includes two parts: head detection and target tracking. The head detection uses a CNN deep learning model to detect the position of the head in the image. The target tracking uses a general tracking method (such as kcf) to determine the ID number (identity number) corresponding to each detection box by comparing the features of the previous and subsequent frames. When a new participant enters the frame, the conference system automatically sets a new identity number for the new participant. The conference system uses the initial identity number in the participant list as the basis. If a new identity number is detected in the participant list, it is determined that a new participant appears in the frame.

[0031] Further, the step of determining whether the new participant is a participant according to the motion trajectory includes:

[0032] S201: Determine whether the new participant stays in a fixed position of the frame for more than a time threshold according to the motion trajectory;

[0033] S202: If the new participant stays in a fixed position of the frame for more than a time threshold, it is determined that the new participant is a participant.

[0034] Preferably, after the step of determining whether the new participant is a participant according to the motion trajectory, the method further includes:

[0035] S6: If the new participant is not a participant, delete the new identity number.

[0036] In this embodiment, the conference system collects the motion trajectory of the new participant in real time through the portrait tracking technology, and collects the fixed stay duration of the new participant at a certain position in the framing area of the framing frame according to the motion trajectory. Specifically, the conference system obtains the fixed position stay duration corresponding to the duration of the video data collected by the camera when the new participant keeps still at a certain position, and accumulates the fixed position stay duration of the new participant when detecting that the new participant keeps still at a certain position. Then, the conference system compares the accumulated fixed position stay duration with the duration threshold to determine whether the fixed position stay duration is greater than the duration threshold. When the conference system monitors that the accumulated fixed position stay duration is greater than the duration threshold, it is determined that the new participant is a participant of the current video conference. Since personnel unrelated to the conference generally do not stay in the conference place, the conference system can avoid the interference of the personnel unrelated to the conference passing through the framing frame to the adjustment of the framing frame, avoid the frequent switching of the panoramic picture of the video conference, and effectively improve the conference experience of the participants.

[0037] Preferably, if the new participant does not stay in the framing area of the framing frame or the fixed position stay duration is less than the duration threshold, the conference system determines that the new participant is not a participant of the current video conference. In order to avoid interfering with the subsequent identification of the conference system whether a new participant appears, the conference system deletes the new identity number corresponding to the new participant.

[0038] Further, the step of adjusting the framing area of the framing frame according to the motion trajectory so that the framing area of the adjusted framing frame contains all the participants includes:

[0039] S301: tracking the participant position of the new participant according to the motion trajectory, and determining whether the new participant is about to exceed the framing area of the framing frame;

[0040] S302: if the new participant is about to exceed the framing area of the framing frame, predicting the moving direction and moving speed of the new participant according to the motion trajectory;

[0041] S303: setting the adjustment direction of the center of the framing area of the framing frame according to the moving direction, and correspondingly setting the adjustment speed of the framing frame according to the moving speed;

[0042] S304: smoothly adjusting the framing frame according to the adjustment direction and the adjustment speed, until the framing area of the adjusted framing frame contains all the participants.

[0043] In this embodiment, the conference system tracks the participation position of the newly joined person according to the motion trajectory of the newly joined person, and monitors whether the newly joined person is about to move out of the framing area of the framing box. For example, when the newly joined person moves to a preset distance (such as 0.5 m) from the boundary of the framing area of the current framing box, the conference system determines that the newly joined person is about to move out of the framing area of the framing box. When the conference system monitors that the newly joined person is about to move out of the framing area of the framing box, the moving direction of the newly joined person is obtained according to the trend between the initial position and the current position of the newly joined person in the motion trajectory, and the moving speed of the newly joined person is calculated according to the distance between the initial position and the current position of the newly joined person in the motion trajectory and the moving time corresponding to the distance. The length-width ratio of the framing box of the video conference is a fixed value (preferably 16:9), so in the process of adjusting the framing box, the position of the center of the framing area of the framing box (which can be understood as the center point of the framing box) is mainly determined to change, and the length and width of the framing box are adjusted in proportion. The conference system sets the adjustment direction of the center of the framing area of the framing box according to the moving direction of the newly joined person (it should be noted that the moving direction of the newly joined person and the adjustment direction of the center of the framing area of the framing box are not consistent, for example, the moving direction of the newly joined person is right, and the adjustment direction of the center of the framing area of the framing box is not right. Because the length-width ratio of the framing box is a fixed value, the adjustment direction of the center of the framing area of the framing box is right up or right down, and specific settings need to be made in cooperation with other participants to ensure that the existing participants will not fall out of the framing box, but the adjustment direction of the center of the framing area of the framing box still has a correlation with the moving direction of the newly joined person); and the adjustment speed of the framing box is set according to the moving speed of the newly joined person in a preset proportion. The adjustment speed represents the size of the pixel change of the length and width of the framing box, so that when the conference system adjusts the current framing box according to the adjustment direction and the adjustment speed, the overall transition of the panoramic picture reflected by the framing box is smooth, and the participants will not feel abrupt, which will affect the video conference experience of the participants; at the same time, the framing area of the adjusted framing box contains all the participants (all the participants include the initial participants and the newly joined person).

[0044] Preferably, the technical solutions described in steps S301-S304 are not only applicable to the newly joined person, but also applicable to all participants, that is, when the existing participants move in the framing box, the conference system will also adjust the framing area of the framing box according to the motion trajectory of the participants to dynamically adapt to the position change of all participants.

[0045] Further, after the step of adjusting the framing area of the framing box according to the motion trajectory to make the framing area of the adjusted framing box contain all the participants, the following steps are included:

[0046] S4: monitoring whether the first participant moves out of the maximum framing area of the framing box;

[0047] S5: if the first participant moves out of the maximum framing area of the framing box, deleting the identity number corresponding to the first participant, and performing smooth adjustment on the current framing area of the framing box at a preset adjustment speed until the framing area of the adjusted framing box contains all participants.

[0048] In this embodiment, during the video conference, if the first participant (the first participant is any one or more of all participants) starts to move, the conference system adjusts the framing area of the framing box according to the position of the first participant (for details, refer to the embodiment corresponding to steps S301-S304). However, the framing box of the camera has a maximum framing area. When the conference system monitors that the first participant continuously moves out of the maximum framing area of the framing box, the identity number corresponding to the first participant is deleted from the participant list. At the same time, since the framing area of the framing box has been adjusted according to the position of the first participant during the movement of the first participant, after the first participant leaves (i.e., moves out of the maximum framing area of the framing box), the conference system needs to adjust the framing area of the framing box according to the positions of all existing participants to avoid a large amount of blank areas in the panoramic picture and affect the conference experience of the existing participants. Specifically, the conference system determines the final framing area boundary of the framing box according to the position distribution of all existing participants, and then performs smooth adjustment on the current framing area of the framing box at a preset adjustment speed until the framing area of the adjusted framing box contains all participants (i.e., adjusted to the final framing box determined by the conference system).

[0049] Referring to Figure 2 The present disclosure provides a kind of dynamic adjustment device of video conference framing box, comprising:

[0050] The first monitoring module 1 is used to monitor whether new personnel appears in the framing box;

[0051] The judging module 2 is used to if new personnel appears in the framing box, the motion trajectory of the new personnel is collected, and whether the new personnel is a participant is judged according to the motion trajectory;

[0052] The first adjustment module 3 is used to if the new personnel is a participant, the framing area of the framing box is adjusted according to the motion trajectory, so that the framing area of the adjusted framing box contains all participants.

[0053] Further, the first monitoring module 1 comprises:

[0054] The collection unit is configured to collect personnel images of all personnel in the framing frame at the beginning of the video conference using a portrait tracking technology, and set an initial identity number for each of the personnel images;

[0055] The first judging unit is configured to judge whether to add a new identity number in real time based on the initial identity numbers;

[0056] The first determining unit is configured to determine that a new personnel appears in the framing frame if a new identity number is added.

[0057] Further, the judging module 2 comprises:

[0058] The second judging unit is configured to judge whether a duration that the new personnel stays at a fixed position of the framing frame is greater than a duration threshold according to the motion trajectory;

[0059] The second determining unit is configured to determine that the new personnel is a conference participant if the duration that the new personnel stays at the fixed position of the framing frame is greater than the duration threshold.

[0060] Further, the first adjusting module 3 comprises:

[0061] The third judging unit is configured to track a conference position of the new personnel according to the motion trajectory, and judge whether the new personnel is about to exceed a framing area of the framing frame;

[0062] The predicting unit is configured to predict a moving direction and a moving speed of the new personnel according to the motion trajectory if the new personnel is about to exceed the framing area of the framing frame;

[0063] The setting unit is configured to set an adjusting direction of a center of the framing area of the framing frame according to the moving direction, and set an adjusting speed of the framing frame according to the moving speed;

[0064] The adjusting unit is configured to perform smooth adjustment on the framing frame according to the adjusting direction and the adjusting speed, until the framing area of the adjusted framing frame contains all conference participants.

[0065] Further, the dynamic adjusting device of the video conference framing frame further comprises:

[0066] The second monitoring module 4 is configured to monitor whether a first conference participant moves out of a maximum framing area of the framing frame;

[0067] The second adjusting module 5 is configured to delete the identity number corresponding to the first participant if the first participant moves out of the maximum framing area of the framing box, and to perform smooth adjustment on the current framing area of the framing box at a preset adjustment speed until the framing area of the adjusted framing box contains all the participants.

[0068] Further, the video conference framing box dynamic adjustment apparatus further comprises:

[0069] The deleting module 6 is configured to delete the new identity number if the new participant is not a participant.

[0070] In the embodiment, each module and unit in the video conference framing box dynamic adjustment apparatus is configured to perform the steps in the video conference framing box dynamic adjustment method, and the specific implementation process is not described here.

[0071] The video conference framing box dynamic adjustment apparatus provided in the embodiment can realize real-time monitoring of whether new participants appear in the framing box of the camera by the conference system, and if new participants appear in the framing box, the motion trajectory of the new participants is collected, and whether the new participants are participants is determined according to the motion trajectory. If the new participants are participants, the framing area of the framing box is adjusted according to the motion trajectory of the new participants, so that the framing area of the adjusted framing box contains all the participants. In the disclosure, the conference system accurately identifies the intention of the new participants (i.e., whether the new participants are participants in the current video conference) through the motion trajectory of the new participants, and only adjusts the framing area of the framing box when the new participants are participants, thereby avoiding frequent switching of panoramic pictures caused by irrelevant persons passing through the conference room (or irrelevant persons entering the framing box), and effectively improving the video conference experience of all participants.

[0072] Reference Figure 3 In the embodiment of the disclosure, a computer device can be a server, and the internal structure thereof can be as shown in Figure 3 The computer device includes a processor, a memory, a network interface and a database connected through a system bus. The processor of the computer device is configured 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 operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store identity numbers and other data. The network interface of the computer device is configured to communicate with external terminals through network connection. The computer program is executed by the processor to implement a video conference framing box dynamic adjustment method.

[0073] The processor executes the steps of the dynamic adjustment method of the video conference framing box:

[0074] S1: Monitor whether a new participant appears in the framing box;

[0075] S2: If a new participant appears in the framing box, collect the motion trajectory of the new participant, and determine whether the new participant is a participant according to the motion trajectory;

[0076] S3: If the new participant is a participant, adjust the framing area of the framing box according to the motion trajectory, so that the framing area of the adjusted framing box contains all participants.

[0077] Further, the step of monitoring whether a new participant appears in the framing box comprises:

[0078] S101: At the beginning of the video conference, use portrait tracking technology to collect the personnel images of all personnel in the framing box, and set the initial identity number corresponding to each personnel image;

[0079] S102: Based on each initial identity number, determine whether a new identity number is added in real time;

[0080] S103: If a new identity number is added, it is determined that a new participant appears in the framing box.

[0081] Further, the step of determining whether the new participant is a participant according to the motion trajectory comprises:

[0082] S201: Determine whether the new participant stays in a fixed position of the framing box for a time longer than a time threshold according to the motion trajectory;

[0083] S202: If the new participant stays in a fixed position of the framing box for a time longer than a time threshold, it is determined that the new participant is a participant.

[0084] Preferably, after the step of determining whether the new participant is a participant according to the motion trajectory, the method comprises:

[0085] S6: If the new participant is not a participant, delete the new identity number.

[0086] Further, the step of adjusting the framing area of the framing box according to the motion trajectory so that the framing area of the adjusted framing box contains all participants comprises:

[0087] S301: tracking a participation position of the new participant according to the motion trajectory, and determining whether the new participant is about to exceed a framing area of the framing box;

[0088] S302: if the new participant is about to exceed the framing area of the framing box, predicting a moving direction and a moving speed of the new participant according to the motion trajectory;

[0089] S303: setting an adjustment direction of a center of the framing area of the framing box according to the moving direction, and correspondingly setting an adjustment speed of the framing box according to the moving speed;

[0090] S304: smoothly adjusting the framing box according to the adjustment direction and the adjustment speed, until the framing area of the adjusted framing box contains all the participants.

[0091] Further, the step of adjusting the framing area of the framing box according to the motion trajectory, so that the framing area of the adjusted framing box contains all the participants, comprises:

[0092] S4: monitoring whether a first participant moves out of the maximum framing area of the framing box;

[0093] S5: if the first participant moves out of the maximum framing area of the framing box, deleting an identity number corresponding to the first participant, and smoothly adjusting the current framing area of the framing box at a preset adjustment speed, until the framing area of the adjusted framing box contains all the participants.

[0094] An embodiment of the present disclosure further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement a dynamic adjustment method of a video conference framing box, and the dynamic adjustment method of the video conference framing box specifically comprises:

[0095] S1: monitoring whether a new participant appears in the framing box;

[0096] S2: if the new participant appears in the framing box, collecting a motion trajectory of the new participant, and determining whether the new participant is a participant according to the motion trajectory;

[0097] S3: if the new participant is a participant, adjusting a framing area of the framing box according to the motion trajectory, so that the framing area of the adjusted framing box contains all the participants.

[0098] Further, the step of monitoring whether a new participant appears in the framing box comprises:

[0099] S101: at the beginning of the video conference, using a portrait tracking technology to collect personnel images of all personnel in the framing frame, and setting an initial identity number corresponding to each personnel image;

[0100] S102: judging whether to add a new identity number in real time based on each initial identity number;

[0101] S103: if a new identity number is added, determining that a new added personnel appears in the framing frame.

[0102] Further, the step of judging whether the new added personnel is a participant according to the motion trajectory comprises:

[0103] S201: judging whether a staying duration of the new added personnel at a fixed position of the framing frame is greater than a duration threshold according to the motion trajectory;

[0104] S202: if the staying duration of the new added personnel at the fixed position of the framing frame is greater than the duration threshold, determining that the new added personnel is a participant.

[0105] Preferably, after the step of judging whether the new added personnel is a participant according to the motion trajectory, comprising:

[0106] S6: if the new added personnel is not a participant, deleting the new identity number.

[0107] Further, the step of adjusting a framing area of the framing frame according to the motion trajectory to make the framing area of the adjusted framing frame contain all participants comprises:

[0108] S301: tracking a participating position of the new added personnel according to the motion trajectory, and judging whether the new added personnel is about to exceed a framing area of the framing frame;

[0109] S302: if the new added personnel is about to exceed the framing area of the framing frame, predicting a moving direction and a moving speed of the new added personnel according to the motion trajectory;

[0110] S303: setting an adjustment direction of a center of the framing area of the framing frame according to the moving direction, and correspondingly setting an adjustment speed of the framing frame according to the moving speed;

[0111] S304: performing a smooth adjustment on the framing frame according to the adjustment direction and the adjustment speed, until the framing area of the adjusted framing frame contains all participants.

[0112] Further, after the step of adjusting the framing area of the framing box according to the motion trajectory so that the framing area of the adjusted framing box contains all the participants, the method further comprises:

[0113] S4: monitoring whether the first participant moves out of the maximum framing area of the framing box;

[0114] S5: if the first participant moves out of the maximum framing area of the framing box, deleting the identity number corresponding to the first participant, and performing smooth adjustment on the current framing area of the framing box according to a preset adjustment speed until the framing area of the adjusted framing box contains all the participants.

[0115] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium provided by the present disclosure and used in the embodiments 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. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), 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) and the like.

[0116] It should be noted that in this document, the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, so that a process, device, first object or method including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, device, first object or method. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of other identical elements in the process, device, first object or method including the element.

[0117] The above merely describes preferred embodiments of the present disclosure, and does not limit the patent scope of the present disclosure, and any equivalent structure or equivalent process transformation made by using the content of the present disclosure and the drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present disclosure.

Claims

1. A method for dynamic adjustment of a video conference framing, wherein, The method comprises the following steps: monitoring whether a new participant appears in the frame; if a new participant appears in the frame, collecting the motion track of the new participant, and judging whether the new participant is a conference participant according to the motion track; if the new participant is a conference participant, adjusting the framing area of the frame according to the motion track so that the framing area of the adjusted frame contains all conference participants; wherein the step of adjusting the framing area of the frame according to the motion track so that the framing area of the adjusted frame contains all conference participants comprises: tracking the conference position of the new participant according to the motion track to determine whether the new participant is about to move out of the framing area of the frame; if the new participant is about to move out of the framing area of the frame, predicting the moving direction and speed of the new participant according to the motion track; setting the adjustment direction of the center of the framing area of the frame according to the moving direction, and setting the adjustment speed of the frame according to the moving speed; smoothly adjusting the frame according to the adjustment direction and the adjustment speed until the framing area of the adjusted frame contains all conference participants; wherein the tracking of the conference position of the new participant according to the motion track, and the monitoring of whether the new participant is about to move out of the framing area of the frame, when it is monitored that the new participant is about to move out of the framing area of the frame, the moving direction of the new participant is obtained according to the trend between the initial position and the current position of the new participant in the motion track, and the moving speed of the new participant is calculated according to the distance between the initial position and the current position of the new participant in the motion track, and the moving time corresponding to the distance.

2. The method of dynamically adjusting the video conference framing according to claim 1, wherein, The step of monitoring whether a new participant appears in the frame comprises: at the beginning of the video conference, collecting the personnel images of all participants in the frame using a portrait tracking technology, and setting corresponding initial identity numbers for each personnel image; based on each initial identity number, judging in real time whether a new identity number is added; if a new identity number is added, it is determined that a new participant appears in the frame.

3. The method of dynamically adjusting the video conference viewfinder according to claim 1, wherein, The step of judging whether the new participant is a conference participant according to the motion track comprises: judging whether the length of time that the new participant stays at a fixed position in the frame is greater than a time threshold according to the motion track; if the length of time that the new participant stays at a fixed position in the frame is greater than a time threshold, it is determined that the new participant is a conference participant.

4. The method of dynamically adjusting the video conference framing according to claim 1, wherein, After the step of adjusting the framing area of the frame according to the motion track so that the framing area of the adjusted frame contains all conference participants, the method further comprises the following steps: monitoring whether a first conference participant moves out of the maximum framing area of the frame; If the first participant moves out of the maximum framing area of the framing box, the identity number corresponding to the first participant is deleted, and the current framing area of the framing box is adjusted smoothly at a preset adjustment speed until the framing area of the adjusted framing box contains all the participants.

5. The method of dynamically adjusting the video conference viewfinder according to claim 2, wherein, The step of judging whether the new participant is a participant according to the motion track comprises: If the new participant is not a participant, the new identity number is deleted.

6. An apparatus for dynamic adjustment of a video conference framing box, wherein, It comprises: A first monitoring module for monitoring whether a new participant appears in the framing box; A judging module for collecting the motion track of the new participant if a new participant appears in the framing box, and judging whether the new participant is a participant according to the motion track; A first adjustment module for adjusting the framing area of the framing box according to the motion track if the new participant is a participant, so that the framing area of the adjusted framing box contains all the participants; The step of adjusting the framing area of the framing box according to the motion track so that the framing area of the adjusted framing box contains all the participants comprises: Tracking the participant position of the new participant according to the motion track to determine whether the new participant is about to move out of the framing area of the framing box; If the new participant is about to move out of the framing area of the framing box, the moving direction and speed of the new participant are predicted according to the motion track; The adjustment direction of the center of the framing area of the framing box is set according to the moving direction, and the adjustment speed of the framing box is set correspondingly according to the moving speed; The framing box is adjusted smoothly according to the adjustment direction and the adjustment speed until the framing area of the adjusted framing box contains all the participants; Wherein, the motion track of the new participant is tracked to determine whether the new participant is about to move out of the framing area of the framing box. When it is determined that the new participant is about to move out of the framing area of the framing box, the moving direction of the new participant is obtained according to the trend between the initial position and the current position of the new participant in the motion track, and the moving speed of the new participant is calculated according to the distance between the initial position and the current position of the new participant in the motion track and the moving time corresponding to the distance.

7. The apparatus of claim 6, wherein, The monitoring module comprises: An acquisition unit for acquiring personnel images of all participants in the framing box at the beginning of the video conference using portrait tracking technology, and setting corresponding initial identity numbers for each personnel image; A first judging unit for judging in real time whether a new identity number is added based on each initial identity number; A first determining unit for determining that a new participant appears in the framing box if a new identity number is added.

8. A computer device comprising a memory and a processor, the memory having stored therein a computer program, wherein, The processor executes the computer program to realize the steps of the method of any one of claims 1 to 5.

9. A computer readable storage medium having stored thereon a computer program, wherein, The computer program is executed by the processor to realize the steps of the method of any one of claims 1 to 5.

Images