WO2022262134A1 - Procédé, appareil et dispositif d'affichage d'image et support de stockage - Google Patents

Procédé, appareil et dispositif d'affichage d'image et support de stockage Download PDF

Info

Publication number
WO2022262134A1
WO2022262134A1 PCT/CN2021/118489 CN2021118489W WO2022262134A1 WO 2022262134 A1 WO2022262134 A1 WO 2022262134A1 CN 2021118489 W CN2021118489 W CN 2021118489W WO 2022262134 A1 WO2022262134 A1 WO 2022262134A1
Authority
WO
WIPO (PCT)
Prior art keywords
image display
image
target image
target
orientation
Prior art date
Application number
PCT/CN2021/118489
Other languages
English (en)
Chinese (zh)
Inventor
陈文明
倪世坤
张世明
吕周谨
Original Assignee
深圳壹秘科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳壹秘科技有限公司 filed Critical 深圳壹秘科技有限公司
Publication of WO2022262134A1 publication Critical patent/WO2022262134A1/fr

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/14—Systems for two-way working
    • H04N7/15—Conference systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects

Definitions

  • the present application relates to the technical field of video display, and in particular to an image display method, device, equipment and storage medium.
  • the main purpose of this application is to provide an image display method, device, device, and storage medium, aiming to solve the problem that the existing technology can only be used in a single application scenario when conducting a video conversation, and cannot be used according to the number of participants and the meeting Mode selection uses different display methods, technical issues with poor user experience.
  • the application provides an image display method, the method comprising the following steps:
  • the preset private image or the current target image captured by the camera is displayed according to the target image display strategy.
  • the target image display strategy includes a target image panorama display strategy
  • the current target image acquired by the camera is displayed according to the target image panorama display strategy.
  • the target image display strategy includes a target image wide-angle display strategy
  • the current target image acquired by the camera is displayed according to the target image wide-angle display strategy.
  • the target image display policy includes a target image privacy display policy
  • the method before displaying the preset privacy image or the current target image acquired by the camera according to the target image display strategy in response to the lens orientation turning to the lens orientation, the method includes:
  • performing image segmentation on the current conference target image through a preset image segmentation model to obtain a segmented image includes:
  • Segmenting the current meeting target image by using a preset image segmentation model based on the initial segmentation point and the preset direction to obtain a segmented image.
  • the method further includes:
  • the present application also proposes an image display device, the image display device includes:
  • the instruction receiving module is configured to receive the meeting request instruction, determine the target image display mode according to the meeting request instruction, and acquire the current meeting target information;
  • the lens adjustment module is configured to determine the orientation of the lens according to the target image display mode, and adjust the orientation of the lens according to the orientation of the lens;
  • a strategy confirmation module configured to determine a target image display strategy based on the camera orientation and the current meeting target information
  • the image display module is configured to display a preset private image or a current target image captured by a camera according to the target image display policy in response to the lens turning to the lens orientation.
  • an image display device which includes: a memory, a processor, and an image display program stored in the memory and operable on the processor.
  • the above-mentioned image display program is configured to realize the steps of the above-mentioned image display method.
  • the present application also proposes a storage medium, on which an image display program is stored, and when the image display program is executed by a processor, the steps of the above-mentioned image display method are realized.
  • the present application determines the target image display mode according to the conference request command when receiving the conference request command, and obtains the current meeting target information, determines the lens orientation according to the target image display mode, and adjusts the lens according to the lens orientation Orientation: Determine the target image display strategy based on the camera orientation and the current meeting target information. When the lens orientation is rotated to the lens orientation, the preset privacy image or the current target captured by the camera will be displayed according to the target image display strategy. image for display.
  • this application determines the target image display mode through the meeting request command input by the user, and adjusts different lens orientations according to different target image display modes, and is suitable for image display in multiple scenarios.
  • the lens orientation and the current Combining the target information of the participants to select the appropriate target image display strategy, it is possible to select different image display methods according to the target information of the participants, avoiding that the video session can only be used in a single application scenario, and cannot be used according to the participants.
  • the number of people, the conference mode selection uses different display methods, and technical issues such as poor user experience.
  • FIG. 1 is a schematic structural diagram of an image display device in a hardware operating environment involved in an embodiment of the present application
  • FIG. 2 is a schematic flow chart of the first embodiment of the image display method of the present application.
  • FIG. 3 is a schematic diagram of a video conferencing device in an embodiment of an image display method of the present application
  • FIG. 4 is a schematic flow chart of the second embodiment of the image display method of the present application.
  • FIG. 5 is a schematic diagram of a VIP image display strategy of an embodiment of the image display method of the present application.
  • FIG. 6 is a schematic diagram of a moderator image display strategy in an embodiment of the image display method of the present application.
  • FIG. 7 is a schematic diagram of a multi-person conversation image display strategy in an embodiment of the image display method of the present application.
  • FIG. 8 is a schematic diagram of an alternate speech image display strategy in an embodiment of the image display method of the present application.
  • FIG. 9 is a schematic flowchart of a third embodiment of the image display method of the present application.
  • FIG. 10 is a schematic diagram of a wide-angle mode scene of an embodiment of the image display method of the present application.
  • FIG. 11 is a schematic diagram of a target image wide-angle display strategy in an embodiment of the image display method of the present application.
  • FIG. 12 is a schematic flowchart of a fourth embodiment of the image display method of the present application.
  • FIG. 13 is a structural block diagram of the first embodiment of the image display device of the present application.
  • FIG. 1 is a schematic structural diagram of an image display device in a hardware operating environment involved in the solution of the embodiment of the present application.
  • the image display device may include: a processor 1001 , such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002 , a user interface 1003 , a network interface 1004 , and a memory 1005 .
  • the communication bus 1002 is configured to realize connection and communication between these components.
  • the user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard).
  • the user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface).
  • Memory 1005 can be a high-speed random access memory (Random Access Memory, RAM), can also be a stable non-volatile memory (Non-Volatile Memory, NVM), such as disk storage.
  • RAM Random Access Memory
  • NVM Non-Volatile Memory
  • the memory 1005 may also be a storage device independent of the aforementioned processor 1001 .
  • FIG. 1 does not constitute a limitation on the image display device, and may include more or less components than those shown in the illustration, or combine some components, or arrange different components.
  • the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and an image display program.
  • the network interface 1004 is mainly configured to communicate data with the network server;
  • the user interface 1003 is mainly configured to perform data interaction with the user;
  • the processor 1001, memory 1005 may be set in the image display device, and the image display device calls the image display program stored in the memory 1005 through the processor 1001, and executes the image display method provided in the embodiment of the present application.
  • FIG. 2 is a schematic flowchart of a first embodiment of an image display method of the present application.
  • the image display method includes the following steps:
  • Step S10 receiving a meeting request instruction, determining a target image display mode according to the meeting request instruction, and acquiring current meeting target information.
  • the execution subject of this embodiment may be an image display device, wherein the image display device may be a controller of a video conferencing device, such as a personal computer, a control chip, etc., or other devices capable of video conferencing. device, which is not specifically limited in this embodiment.
  • the meeting request command may be a request command input by the user through the button of the video conference device, the remote control or the mobile APP to control the operation of the video conference device, and the meeting request command may include the start of the conference initial mode signal, in this embodiment, for the selection of the video conferencing device, refer to FIG. 3 , and describe the video conferencing device shown in FIG. 3 as an example.
  • the video conferencing device has five modules: 1. Microphone array module; 2. Motor and drive module; 3. Lens module; 4. Sensor module; 5. Controller;
  • the microphone array module is configured to collect the sound signal of the user during the video conference, and send the sound signal to the controller to detect the sound direction.
  • the microphone array can It is a multi-microphone array, for example: 4-microphone array, 6-microphone array, and 8-microphone array, etc., which is not specifically limited in this embodiment.
  • the motor and the driving module are configured to rotate according to the signal sent by the controller, so that the lens can be rotated to realize the adjustment of the lens orientation.
  • the direction of rotation is not limited, that is, in When adjusting the orientation of the lens, the motor and the driving module may rotate clockwise or counterclockwise, which is not specifically limited in this embodiment.
  • the selection of the lens in the lens module can be an image acquisition lens that can realize image acquisition at an angle of 220°, or other lenses that can achieve the same or similar functions;
  • the sensor module is configured to detect motors and drive module control The lens is rotated, and the orientation of the lens is detected to complete the rotation operation.
  • the target image display mode may be panorama mode, wide-angle mode, privacy mode, etc.
  • the video conferencing device controller may activate the corresponding target image display mode.
  • the current conference participation target information may be information such as the number of people currently participating in the conference, face information, and conference participation.
  • Step S20 Determine the orientation of the lens according to the target image display mode, and adjust the orientation of the lens according to the orientation of the lens.
  • different target image display modes correspond to different lens orientations.
  • 1 indicates a panoramic mode, and the lens orientation corresponding to the panoramic mode is upward;
  • 2 indicates a wide-angle mode , the lens orientation corresponding to the wide-angle mode is facing forward;
  • 3 indicates the privacy mode, and the lens orientation corresponding to the privacy mode is facing downward.
  • the lens is controlled to rotate according to the motor and the driving module, so that the lens orientation is rotated to the lens orientation corresponding to the target image display mode determined according to the conference request input by the user.
  • Step S30 Determine a target image display strategy based on the camera orientation and the current meeting target information.
  • the image display strategy may be the multi-person conversation image display strategy in the panorama mode, the host image display strategy, the VIP image display strategy, and the alternate speech image display strategy, etc., and may also be the wide-angle mode
  • the specific target image display strategy is determined according to the camera orientation and the current meeting target information.
  • the lens orientation is determined by the image display mode. Therefore, in this embodiment, according to three different target image display modes, the lens of the video conferencing device has three orientations, which are: lens Up, Camera Forward, and Camera Down.
  • Step S40 In response to the camera turning to the camera orientation, display the preset private image or the current target image captured by the camera according to the target image display policy.
  • the current target image may be a conference image captured by a camera when the video conference device is in a panorama mode or a wide-angle mode.
  • step S40 it also includes:
  • the preset image segmentation model can be configured to perform image segmentation on the target image captured by the camera, extract the person image in the target image, and mark it as a segmented image.
  • the current target image is an expanded view obtained after expanding the target image collected by the camera.
  • the expansion point needs to be determined first.
  • the determination of the expansion point position can be Determining the segmentation initial point of the current conference target image based on the camera orientation; segmenting the current conference target image through a preset image segmentation model based on the segmentation initial point and preset direction to obtain a segmented image.
  • the participants who speak during the video conference can also be marked, so that the user can more intuitively understand who is Speaking, can have a better experience.
  • step S40 it also includes:
  • the preset mouth shape detection model is configured to detect the mouth movement of the participant in the image of the current participant.
  • the mouth will move, thereby judging the participant who is speaking
  • the target since the target may not emit a sound signal, but detects the presence of mouth movement, the initial speaker information can be obtained through the preset mouth detection model.
  • the accurate target speaker can be determined by using the sound signal obtained by the microphone to predict the direction through the preset direction prediction model and the initial speaker information, so as to mark the image of the target speaker.
  • the marking of the target speaker can be by increasing the brightness of the image of the target speaker in the display image, marking different colors, etc., or by other marking methods with the same or similar marking functions, which are not covered in this embodiment. Specific restrictions.
  • the target image display mode is determined according to the meeting request instruction, and the current meeting target information is obtained
  • the lens orientation is determined according to the target image display mode
  • the camera orientation is adjusted according to the lens orientation.
  • Camera orientation based on the lens orientation and the current meeting target information to determine the target image display strategy, when the lens orientation is rotated to the lens orientation, according to the target image display strategy, the preset privacy image or the current image captured by the camera The target image is displayed.
  • the target image display mode is determined through the meeting request command input by the user, and different camera orientations are adjusted according to different target image display modes.
  • Select the appropriate target image display strategy and may choose different image display methods according to the different target information of the participants, avoiding that it can only be used in a single application scenario during a video session, and cannot be used according to the number of participants and the conference mode choose to use different display methods, technical issues with poor user experience.
  • FIG. 4 is a schematic flowchart of a second embodiment of an image display method of the present application.
  • the step S30 includes:
  • Step S301 Responding to the fact that the camera orientation is upward, acquire the number of conference participants and the degree of conference participation in the current conference participant information.
  • the degree of meeting participation can be calculated by judging the total number of sound signals collected by the microphone array of the video conferencing equipment, the source of the sound signals, etc., and then processing the sound signals to obtain the degree of meeting participation can be the sound signal The greater the total number of , the higher the degree of conference participation, and the greater the number of sources of sound signals, the higher the degree of conference participation.
  • Step S302 Determine a target image panorama display strategy according to the camera orientation, the number of conference participants and the conference participation degree.
  • the target image panorama display strategy includes four target image display strategies: 1. VIP image display strategy; 2. Moderator image display strategy; 3. Multi-person conversation image display strategy; 4. , Alternate speech image display strategy; it is necessary to select an appropriate target image display strategy according to the specific number of participants and the degree of participation in the meeting.
  • step S301 including:
  • the degree of meeting participation does not exceed a first preset value, and when the number of meeting participants is less than a second preset value, according to the meeting request instruction, the number of meeting participants and the meeting participation degree Determine moderator image display strategy;
  • the moderator information may be a long-term display target image, and the moderator information may be the conference moderator, the organizer, or a person who needs to be permanently displayed, or the person directly in front of the video conferencing device
  • the moderator information can be manually switched by adjusting the placement of the video conferencing equipment, or can be switched through the buttons on the video conference equipment, remote control, mobile APP, etc. This implementation Examples are not specifically limited.
  • the target image display strategy is the VIP image display strategy; when the conference participation does not exceed the first preset value, and when the number of participants is less than the second preset value, the target image
  • the display strategy is the moderator's image display strategy, and the first preset value and the second preset value may be a value preset by the user, which is not specifically limited in this embodiment.
  • a VIP position will be set.
  • the VIP position will be fixed in the upper left corner, and other numbers and positions may not be fixed.
  • the number of non-VIP positions is 5 , when it is detected that someone is speaking, the target image corresponding to the speaking participant target is extracted to several other positions through detection, and will be clockwise in the five frames of the non-VIP position starting from the VIP position.
  • the degree of participation in the meeting and the number of participants change during the video conference, it can also be detected through the preset humanoid detection model and the preset face detection model, and then re-according to different meeting participation and the number of participants Change target image display strategy.
  • the video conferencing device detects the information of the host, it confirms that A is the host.
  • the degree of participation in the meeting exceeds the first preset value, And when the number of participants is greater than the second preset value, the target image display strategy is the VIP image display strategy. Therefore, the video image display positions of six people are as shown in FIG. 5 .
  • the target image display strategy is the moderator image display strategy, so , the display positions of the video images of the six people are shown in Figure 6.
  • step S302 also includes:
  • an alternate speaking image display strategy is determined according to the conference request instruction, the number of conference participants, and the degree of conference participation.
  • the obtained target images of the participants will be integrated to obtain a panorama containing all the target images of the participants, and the panorama will be fixed on the display image.
  • the panorama will be fixed on the display image.
  • At the lower end there will be three image frames fixed on the upper end of the display image. These three image frames will be adjusted to display the target image when it is detected that there are participants speaking. If the number of participants in the panorama is not enough for three people, On the upper part of the display image, only the image frame corresponding to the number of people is displayed, and the part with insufficient number of people displays a black frame.
  • the order of these three image frames is fixed, for example: currently there are A, B, C, D, E, F six people, then display which image frame is on the top of the image in the following 10 order: ABC, ABD, ABE, ABF, ACD, ACE, ACF, ADE, ADF, AEF.
  • the screen displaying the image has only one portrait frame, showing one person;
  • the screen displaying the image is divided into left and right, and 2 people are displayed;
  • the screen displaying the image is divided into 4 equal parts according to top, bottom, left and right, and 3 people are displayed, but the screen in the lower right corner is displayed on a black screen;
  • the screen displaying the image is divided into 4 equal parts according to top, bottom, left and right, and 4 people are displayed;
  • the screen displaying the image is divided into 9 equal parts according to the top, bottom, left and right, and 7 people are displayed, but the 2 screens in the lower right corner are displayed on a black screen;
  • the screen displaying the image is divided into 9 equal parts according to the top, bottom, left and right, and 8 people are displayed, but the screen in the lower right corner is displayed on a black screen;
  • the screen displaying the image is divided into 9 equal parts according to top, bottom, left and right, and 9 people are displayed;
  • the screen shows only 9 people, and the initially displayed people are displayed clockwise according to the first person who spoke, and when the 10th person speaks, replace the last person who spoke;
  • the video conferencing device when it does not detect the moderator information, it judges the quantitative relationship between the number of conference participants and the second preset value, and when the number of conference participants does not exceed the second preset value, the target The image display strategy is a multi-person conversation image display strategy; when the number of participants in the meeting exceeds a second preset value, the target image display strategy is an alternate speaking image display strategy.
  • the target image display strategy is a multi-person conversation image display strategy, showing The image is shown in Figure 7.
  • the upper end of the previously displayed image is A, D, and F, and it is detected that C is speaking at this time, then according to the switching rule, the upper end of the displayed image will be switched to A, D, and F.
  • C, D three target images of participants.
  • the target image display strategy is an alternate speech image display strategy, and the images are displayed according to the cutting rule as shown in FIG. 8 .
  • the target image display mode is determined according to the meeting request instruction, and the current meeting target information is obtained
  • the lens orientation is determined according to the target image display mode, and the camera orientation is adjusted according to the lens orientation.
  • Camera orientation if the camera orientation is upward, then obtain the number of participants and the degree of participation in the meeting in the current meeting target information, according to the camera orientation, the number of participants and the conference participation
  • the target image panorama display strategy is determined according to the degree, and when the lens orientation is rotated to the lens orientation, the preset privacy image or the current target image captured by the camera is displayed according to the target image display strategy.
  • the target image display mode is determined through the meeting request command input by the user, and different camera orientations are adjusted according to different target image display modes, which is applicable to image display in multiple scenarios.
  • the combination of the number and the degree of meeting participation selects an appropriate target image panorama display strategy, and may select different image display methods according to the different target information of the participants, so as to avoid that it can only be used in a single application scenario when conducting a video session. It is impossible to choose different display methods according to the number of participants and the conference mode, and the technical problem is that the user experience is poor.
  • FIG. 9 is a schematic flowchart of a third embodiment of an image display method of the present application.
  • the step S30 includes:
  • Step S301A In response to the camera orientation being forward facing, determine a target image wide-angle display strategy according to the camera orientation and the current conference participant information.
  • the target display mode is the wide-angle mode, that is, when the camera orientation is forward, then the target image wide-angle display strategy is determined according to the lens orientation and the current conference participant information.
  • the lens of the video conferencing device adopts an image that can capture a wide-angle range of 220°, and the larger the angle on both sides of the lens, the greater the distortion of the image , in order to have a good image display effect, the angles on both sides of the obtained 220° image can be cut off by 20° to achieve the effect of a 180° image.
  • the existing four people A, B, C, and D are divided into four people located in front of the video conferencing equipment. D and the two people will be farther away from the lens, so the portraits of B and C displayed on the monitor are larger than those of A and D, so as to distinguish the distance relationship between the participants and the video conferencing equipment, and the final display image Refer to Figure 11.
  • the portrait of A will be enlarged accordingly and placed in the center; when the three people in ACD leave, only B is left sitting in the original position, because B itself is at the side , so when zooming in, it will give priority to keeping B in the display frame, and finally the position of B will be zoomed in to a certain extent, and will be a little to the left;
  • the image of AD is enlarged in the same proportion and placed in the center; when there are only BC on the entire conference table, the portraits of B and C are detected and enlarged in the same proportion, but because the sitting positions of BC and BC are different Move to the side, so the magnification ratio of BC is smaller than that of AD; when there are only two BDs on the entire conference table, after detecting B and D, the portrait and other scenes in the screen will be enlarged in the same ratio, because B is closer and closer to the lens Move to the side, so when zooming in on the same scale,
  • the target image display mode is determined according to the meeting request instruction, and the current meeting target information is obtained
  • the lens orientation is determined according to the target image display mode, and the camera orientation is adjusted according to the lens orientation.
  • the lens orientation if the lens orientation is the lens facing forward, then determine the wide-angle display strategy of the target image according to the lens orientation and the current participant information, and when the lens orientation rotates to the lens orientation, set the target image wide-angle display strategy according to the target image. Set a private image or the current target image acquired by the camera for display.
  • the wide-angle display mode of the target image is determined through the meeting request command input by the user, and the camera orientation is adjusted to the front of the camera according to the wide-angle display mode of the target image, which is suitable for image display in multiple scenarios. It is possible to choose a different image display method according to the different target information of the participants, so as to avoid that the video session can only be used in a single application scenario, and the conference cannot be used according to the number of participants. Mode selection uses different display methods, technical issues with poor user experience.
  • FIG. 12 is a schematic flowchart of a fourth embodiment of an image display method of the present application.
  • the step S30 includes:
  • Step S301B In response to the camera orientation being downward, determine a target image privacy display policy according to the lens orientation.
  • the target display mode is the privacy mode, that is, when the camera orientation is the lens downward, then the target image privacy display policy is determined according to the lens orientation.
  • this mode is mainly to protect the privacy of the conference. When there is something to discuss in the local area and you don’t want the other party to see the local screen and hear the local discussion sound, without closing the ongoing video call conference, It can be implemented in this manner.
  • the privacy mode can also be entered into the privacy mode from the panoramic mode or the wide-angle mode.
  • the device controller when the current target image display mode is panoramic mode, one party may need to conduct internal discussions and temporarily turn off the camera.
  • the device controller receives the display prohibition instruction, it controls the camera to rotate according to the display prohibition instruction, and controls the sensor to detect the current lens orientation; microphone.
  • the user when the current target image display mode is the wide-angle mode, the user sends an instruction by pressing a button of the video conferencing device or a remote control, etc., and when the video conferencing device controller receives the display prohibition instruction, it controls the display according to the display prohibition instruction.
  • the camera is rotated and the sensor is controlled to detect the current lens orientation. If the current lens orientation is downward, a preset privacy image is displayed and the microphone is turned off.
  • the video conference needs to be continued.
  • the user sends an instruction by pressing a button of the video conference device or a remote control, and the controller of the video conference device receives the display start instruction.
  • the display opening command controls the rotation of the camera, and when the lens restoration position is rotated to the lens position corresponding to the target image display strategy, the microphone is turned on, and the target image of the current participant is obtained back, and the target image of the current participant is passed through the preset image
  • the segmentation model performs image segmentation to obtain multiple segmented images.
  • the preset privacy image may be one or more images preset by the user, and the preset privacy image is configured to block the current video image and remind other video users that the video is not interrupted.
  • the target image display mode is determined according to the meeting request instruction, and the current meeting target information is obtained
  • the lens orientation is determined according to the target image display mode, and the camera orientation is adjusted according to the lens orientation.
  • Camera orientation if the lens orientation is facing downward, then determine the target image privacy display policy according to the lens orientation, and when the lens orientation rotates to the lens orientation, set the preset privacy image according to the target image privacy display policy to show.
  • the target image privacy display mode is determined through the meeting request command input by the user, and the camera orientation is adjusted to the lens downward according to the target image privacy display mode, which is suitable for image display in multiple scenarios, according to the camera orientation and current meeting target information It is possible to choose a different image display method according to the different target information of the participants, so as to avoid that the video session can only be used in a single application scenario, and the conference cannot be used according to the number of participants. Mode selection uses different display methods, technical issues with poor user experience.
  • the embodiment of the present application also proposes a storage medium, on which an image display program is stored, and when the image display program is executed by a processor, the steps of the above-mentioned image display method are realized.
  • the storage medium adopts all the technical solutions of all the above-mentioned embodiments, it at least has all the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be repeated here.
  • FIG. 13 is a structural block diagram of the first embodiment of the image display device of the present application.
  • the image display device proposed in the embodiment of the present application includes:
  • the instruction receiving module 10 is configured to receive a meeting request instruction, determine a target image display mode according to the meeting request instruction, and acquire current meeting target information.
  • the lens adjustment module 20 is configured to determine the orientation of the lens according to the target image display mode, and adjust the orientation of the lens according to the orientation of the lens.
  • the policy confirmation module 30 is configured to determine a target image display policy based on the camera orientation and the current meeting target information.
  • the image display module 40 is configured to display a preset private image or a current target image captured by a camera according to the target image display policy in response to the camera turning to the lens orientation.
  • the policy confirmation module 30 is further configured to obtain the number of conference participants and the degree of conference participation in the current conference participant information in response to the camera orientation being upward; according to the The target image panorama display strategy is determined by the lens orientation, the number of participants in the meeting and the degree of participation in the meeting; when the lens orientation is rotated to the lens orientation, the preset privacy image or the current image acquired by the camera is determined according to the target image display strategy.
  • the displaying of the target image further includes: displaying the current target image acquired by the camera according to the target image panorama display strategy when the lens orientation is rotated to the lens orientation.
  • the policy confirmation module 30 is further configured to determine the wide-angle display strategy of the target image according to the lens orientation and the current participant information in response to the lens orientation being the lens facing forward;
  • displaying the preset privacy image or the current target image acquired by the camera according to the target image display strategy also includes: when the lens orientation is rotated to the lens orientation, displaying the camera according to the target image wide-angle display strategy The obtained current target image is displayed.
  • the image display module 30 is further configured to determine a target image privacy display strategy according to the lens orientation in response to the lens orientation being downward; when the lens orientation is rotated to the lens orientation , displaying a preset privacy image or a current target image acquired by a camera according to the target image display strategy, and further comprising: displaying a preset privacy image according to the target image privacy display strategy when the lens orientation is rotated to the lens orientation , and turn off the microphone.
  • the image display module 40 is further configured to obtain the image of the current conference target through the camera, and turn on the microphone; perform image segmentation on the current conference target image through a preset image segmentation model to obtain the Segmenting the image; performing image processing on the segmented image to obtain the current target image.
  • the policy confirmation module 40 is further configured to determine the initial segmentation point of the current conference target image based on the camera orientation; The image is segmented through a preset image segmentation model to obtain a segmented image.
  • the image display module 40 is further configured to perform mouth shape detection on the current target image through a preset mouth shape detection model to obtain an initial speaker image; obtain the current sound signal through a microphone, and Determine speaker information based on the current sound signal; determine a target speaker image according to the speaker information and the initial speaker image, and mark the target speaker image.
  • the target image display mode is determined according to the meeting request instruction, and the current meeting target information is obtained
  • the lens orientation is determined according to the target image display mode
  • the camera orientation is adjusted according to the lens orientation.
  • Camera orientation based on the lens orientation and the current meeting target information to determine the target image display strategy, when the lens orientation is rotated to the lens orientation, according to the target image display strategy, the preset privacy image or the current image captured by the camera The target image is displayed.
  • the target image display mode is determined through the meeting request command input by the user, and different camera orientations are adjusted according to different target image display modes.
  • Select the appropriate target image display strategy and may choose different image display methods according to the different target information of the participants, avoiding that it can only be used in a single application scenario during a video session, and cannot be used according to the number of participants and the conference mode choose to use different display methods, technical issues with poor user experience.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

La présente demande divulgue un procédé, un appareil et un dispositif d'affichage d'image et un support de stockage. Dans la présente demande, un mode d'affichage d'image cible est déterminé au moyen d'une instruction de demande de conférence qui est entrée par un utilisateur, et différentes directions d'objectif sont ajustées selon différents modes d'affichage d'image cible, de façon à convenir à une présentation d'image dans une pluralité de scénarios. Une stratégie d'affichage d'image cible appropriée est sélectionnée selon une combinaison des directions d'objectif et des informations de cible de participation à une conférence actuelle ; et différents modes d'affichage d'image peuvent être sélectionnés selon différents éléments d'informations de cible de participation à une conférence, ce qui permet d'éviter le problème selon lequel un produit ne peut être utilisé que dans un seul scénario d'application pendant une vidéoconférence, et selon lequel différents modes d'affichage ne peuvent pas être sélectionnés et utilisés en fonction du nombre de participants à la conférence et de modes de conférence.
PCT/CN2021/118489 2021-09-07 2021-09-15 Procédé, appareil et dispositif d'affichage d'image et support de stockage WO2022262134A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111047995.3A CN113905204B (zh) 2021-09-07 2021-09-07 图像显示方法、装置、设备及存储介质
CN202111047995.3 2021-09-07

Publications (1)

Publication Number Publication Date
WO2022262134A1 true WO2022262134A1 (fr) 2022-12-22

Family

ID=79188827

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/118489 WO2022262134A1 (fr) 2021-09-07 2021-09-15 Procédé, appareil et dispositif d'affichage d'image et support de stockage

Country Status (2)

Country Link
CN (1) CN113905204B (fr)
WO (1) WO2022262134A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116489502A (zh) * 2023-05-12 2023-07-25 深圳星河创意科技开发有限公司 基于ai摄像头拓展坞的远程会议方法与ai摄像头拓展坞
CN117640877A (zh) * 2024-01-24 2024-03-01 浙江华创视讯科技有限公司 线上会议的画面重构方法及电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102833518A (zh) * 2011-06-13 2012-12-19 华为终端有限公司 一种mcu多画面优化配置的方法及装置
US9237140B1 (en) * 2013-03-07 2016-01-12 Cisco Technologies, Inc. Acceptance of policies for cross-company online sessions
CN112351237A (zh) * 2020-11-05 2021-02-09 安徽马钢和菱实业有限公司 一种视频会议主视频自动切换决策算法
CN112601044A (zh) * 2020-12-08 2021-04-02 深圳市焦点数字科技有限公司 一种会议场景画面自适应方法
CN113139491A (zh) * 2021-04-30 2021-07-20 厦门盈趣科技股份有限公司 视频会议控制方法、系统、移动终端及存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
NO332170B1 (no) * 2009-10-14 2012-07-16 Cisco Systems Int Sarl Anordning og fremgangsmate for kamerakontroll
US9113032B1 (en) * 2011-05-31 2015-08-18 Google Inc. Selecting participants in a video conference
US9124762B2 (en) * 2012-12-20 2015-09-01 Microsoft Technology Licensing, Llc Privacy camera
CN105306868B (zh) * 2014-06-17 2019-07-26 三亚中兴软件有限责任公司 视频会议系统及方法
CN109257559A (zh) * 2018-09-28 2019-01-22 苏州科达科技股份有限公司 一种全景视频会议的图像显示方法、装置及视频会议系统
JP7225735B2 (ja) * 2018-11-27 2023-02-21 株式会社リコー ビデオ会議システム、通信端末、及び通信端末のマイクロホンの制御方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102833518A (zh) * 2011-06-13 2012-12-19 华为终端有限公司 一种mcu多画面优化配置的方法及装置
US9237140B1 (en) * 2013-03-07 2016-01-12 Cisco Technologies, Inc. Acceptance of policies for cross-company online sessions
CN112351237A (zh) * 2020-11-05 2021-02-09 安徽马钢和菱实业有限公司 一种视频会议主视频自动切换决策算法
CN112601044A (zh) * 2020-12-08 2021-04-02 深圳市焦点数字科技有限公司 一种会议场景画面自适应方法
CN113139491A (zh) * 2021-04-30 2021-07-20 厦门盈趣科技股份有限公司 视频会议控制方法、系统、移动终端及存储介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116489502A (zh) * 2023-05-12 2023-07-25 深圳星河创意科技开发有限公司 基于ai摄像头拓展坞的远程会议方法与ai摄像头拓展坞
CN116489502B (zh) * 2023-05-12 2023-10-31 深圳星河创意科技开发有限公司 基于ai摄像头拓展坞的远程会议方法与ai摄像头拓展坞
CN117640877A (zh) * 2024-01-24 2024-03-01 浙江华创视讯科技有限公司 线上会议的画面重构方法及电子设备

Also Published As

Publication number Publication date
CN113905204B (zh) 2023-02-14
CN113905204A (zh) 2022-01-07

Similar Documents

Publication Publication Date Title
US9860486B2 (en) Communication apparatus, communication method, and communication system
CA2874715C (fr) Reglage dynamique de la video et du son dans une videoconference
US8289363B2 (en) Video conferencing
US20100118112A1 (en) Group table top videoconferencing device
RU2549169C2 (ru) Устройство обработки изображений, способ обработки изоьражений и машиночитаемый носитель информации
WO2022262134A1 (fr) Procédé, appareil et dispositif d'affichage d'image et support de stockage
US11477393B2 (en) Detecting and tracking a subject of interest in a teleconference
JP2002112215A (ja) テレビ会議システム
US10979666B2 (en) Asymmetric video conferencing system and method
JPH1042264A (ja) テレビ会議システム
EP4075794A1 (fr) Ajustement des paramètres d'une caméra basé sur une région d'intérêt dans un environnement de téléconférence
EP4106326A1 (fr) Cadrage automatique à caméras multiples
WO2022007681A1 (fr) Procédé de commande de prise de photographie, terminal mobile et support de stockage lisible par ordinateur
TWI248021B (en) Method and system for correcting out-of-focus eyesight of attendant images in video conferencing
JP6565777B2 (ja) 通信装置、会議システム、プログラムおよび表示制御方法
TWI840300B (zh) 視訊會議系統及方法
TWI785511B (zh) 應用於視訊傳輸的目標追蹤方法
JP2005110160A (ja) 撮像装置
JP2000244885A (ja) 画像撮影装置、画像撮影方法、記憶媒体、テレビ会議システム
WO2023235329A1 (fr) Cadre pour capture simultanée de sujet et bureau pendant une vidéoconférence
JP2002262138A (ja) 撮像システム、テレビ会議システム、監視システムおよび撮像機能を有した情報端末機器
CN117319594A (zh) 会议人员追踪显示方法、装置、设备及可读存储介质
TW202345589A (zh) 影音系統及其控制方法
TW202423109A (zh) 主持端視訊裝置、與會端視訊裝置及視訊會議系統

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21945714

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE