WO2021081756A1 - 视频图像显示方法和装置 - Google Patents

视频图像显示方法和装置 Download PDF

Info

Publication number
WO2021081756A1
WO2021081756A1 PCT/CN2019/114027 CN2019114027W WO2021081756A1 WO 2021081756 A1 WO2021081756 A1 WO 2021081756A1 CN 2019114027 W CN2019114027 W CN 2019114027W WO 2021081756 A1 WO2021081756 A1 WO 2021081756A1
Authority
WO
WIPO (PCT)
Prior art keywords
camera
angle
view
coordinates
horizontal
Prior art date
Application number
PCT/CN2019/114027
Other languages
English (en)
French (fr)
Inventor
房增华
Original Assignee
苏州随闻智能科技有限公司
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 苏州随闻智能科技有限公司 filed Critical 苏州随闻智能科技有限公司
Priority to US17/732,481 priority Critical patent/US20230146794A1/en
Priority to PCT/CN2019/114027 priority patent/WO2021081756A1/zh
Priority to CN201980101819.8A priority patent/CN114641984A/zh
Publication of WO2021081756A1 publication Critical patent/WO2021081756A1/zh

Links

Images

Classifications

    • 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
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • 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
    • H04N23/69—Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming

Definitions

  • This application relates to the technical field of video image processing, in particular to a video image display method and device.
  • video conferencing systems have been increasingly widely used.
  • the video conference system uses communication networks and multimedia terminal equipment to realize face-to-face remote instant meetings between participants in different places.
  • Existing video conferencing systems usually use video conferencing cameras to capture video images of participants and present them to the video conferencing display terminal through network transmission.
  • the embodiments of the present application provide a video image display method and device, which are used to solve the problem of poor display of a person's video image in a video conference system in the prior art.
  • an embodiment of the present application proposes a video image display method, which includes the following steps:
  • the angle of view of the camera is adjusted so that all persons photographed by the camera can maximize Displayed in the video image output by the camera.
  • the camera includes a wide-angle camera; wherein, the obtaining the maximum field of view image captured by the camera includes obtaining a full field of view image captured by the wide-angle camera.
  • the method further includes setting the horizontal field of view and the vertical field of view of the wide-angle camera into a plurality of gears at predetermined intervals, respectively.
  • the adjusting the angle of view of the camera based on the minimum and maximum values of the coordinates in the horizontal direction and the minimum and maximum values of the coordinates in the vertical direction of all the faces of the human face includes:
  • the method further includes: tracking the position change of the human face in the video image output by the camera in real time, and dynamically adjusting the horizontal field of view angle gear and the vertical field of view angle gear.
  • the camera includes a rotatable camera; wherein the obtaining the maximum field of view image captured by the camera includes obtaining the maximum field of view image that the rotatable camera can reach by rotating the lens in the horizontal and vertical directions.
  • the adjusting the angle of view of the camera based on the minimum and maximum values of the coordinates in the horizontal direction and the minimum and maximum values of the coordinates in the vertical direction of all the faces of the human face includes:
  • the method further includes: tracking the position change of the human face in the video image output by the camera in real time, and dynamically rotating the horizontal angle and the vertical angle of the rotatable camera.
  • the horizontal and vertical coordinates of all human faces include the coordinates of at least two corner points of the detected rectangular frame of the human face.
  • an embodiment of the present application proposes a video image display device, including:
  • the acquisition module is configured to acquire the maximum angle of view image taken by the camera
  • a detection module configured to detect the horizontal and vertical coordinates of all faces in the maximum field of view image
  • a calculation module configured to calculate the minimum and maximum values of the coordinates in the horizontal direction and the minimum and maximum values of the coordinates in the vertical direction of all the faces;
  • the adjustment module is configured to adjust the angle of view of the camera based on the minimum and maximum values of the coordinates in the horizontal direction and the minimum and maximum values of the coordinates in the vertical direction of all the faces, so that the camera can shoot All personnel of are displayed in the video image output by the camera to the maximum extent.
  • the camera includes a wide-angle camera; wherein the acquisition module is configured to acquire a full-frame angle of view image captured by the wide-angle camera.
  • the horizontal field of view and the vertical field of view of the wide-angle camera are respectively set into multiple gears at predetermined intervals.
  • the adjustment module is further configured to:
  • the device further includes: a tracking module configured to track changes in the position of the human face in the video image output by the camera in real time, and dynamically adjust the horizontal field of view angle gear and the vertical field of view angle gear Bit.
  • a tracking module configured to track changes in the position of the human face in the video image output by the camera in real time, and dynamically adjust the horizontal field of view angle gear and the vertical field of view angle gear Bit.
  • the camera includes a rotatable camera; wherein, the acquisition module is configured to obtain an image of the maximum field of view that the rotatable camera can reach by rotating the lens in the horizontal and vertical directions.
  • the adjustment module is further configured to:
  • the device further includes a tracking module configured to track changes in the position of the human face in the video image output by the camera in real time, and dynamically rotate the horizontal and vertical angles of the rotatable camera.
  • the horizontal and vertical coordinates of all human faces include the coordinates of at least two corner points of the detected rectangular frame of the human face.
  • the embodiments of the present application also provide a computer-readable storage medium on which one or more computer programs are stored, and the one or more computer programs are executed by the processor to implement the steps of the method described in the foregoing embodiments .
  • the embodiment of the present application adjusts the angle of view of the camera based on face position detection, adaptively presents the face display screen, realizes the maximized face framing, and improves the display effect of the person's video image in the video conference system.
  • Fig. 1 is a schematic flowchart of a video image display method according to an embodiment of the present application
  • Figure 2 is a schematic diagram of the horizontal field of view gear setting of the wide-angle camera
  • Figure 3 is a schematic diagram of the vertical field of view gear setting of the wide-angle camera
  • Figure 4 is a schematic diagram of face position detection based on a wide-angle camera
  • Figure 5 is a schematic diagram of face position detection based on a rotatable camera
  • Fig. 6 is a structural example diagram of a video image display device according to an embodiment of the present application.
  • Fig. 7 is a structural example diagram of a video image display device according to another embodiment of the present application.
  • the embodiments of the present application propose a video image display method and device, which adaptively adjusts the field of view (FOV) of the camera based on face position detection, so as to achieve the best picture framing of personnel, thereby It can improve the display effect of people's video images in the video conference system.
  • FOV field of view
  • the field of view is the range of angles taken by the camera lens.
  • the lens is the apex, and the angle formed by the two edges of the maximum range of the lens that the object image can pass through can be It is called the angle of view.
  • the maximum angle range of the lens shot in the horizontal direction can be called the horizontal field of view; the maximum angle range of the lens shot in the vertical direction can be called the vertical field of view.
  • Fig. 1 is a schematic flowchart of a video image display method according to an embodiment of the present application. As shown in FIG. 1, the video image display method of the embodiment of the present application includes the following steps:
  • Step S110 acquiring a maximum angle of view image taken by the camera
  • Step S120 detecting the horizontal and vertical coordinates of all faces in the image with the maximum angle of view
  • Step S130 Calculate the minimum and maximum values of the coordinates of all faces in the horizontal direction and the minimum and maximum values of the coordinates in the vertical direction;
  • Step S140 Adjust the field of view of the camera based on the minimum and maximum values of the coordinates in the horizontal direction and the minimum and maximum values of the coordinates in the vertical direction of all faces, so that all persons photographed by the camera are maximized
  • the ground is displayed in the video image output by the camera.
  • the embodiment of the application obtains the maximum field of view image taken by the camera, dynamically adjusts the field of view of the camera based on the coordinate detection of the face in the maximum field of view image, adaptively presents the face display screen, and realizes the person in the video image The best display effect.
  • the image with the maximum angle of view captured by the camera in step S110 may be understood as a video image captured by the camera with the visual range of the maximum angle of view.
  • the camera used in step S110 may include a wide-angle camera or a rotatable camera.
  • the wide-angle camera is a camera lens with a focal length shorter than a standard lens and a field angle larger than that of a standard lens.
  • a rotatable camera is a camera lens in which the lens can rotate a certain angle in different directions such as up and down, left and right, to achieve target shooting in different angle ranges.
  • the maximum field of view image taken by the wide-angle camera includes the full field of view image taken by the physical lens of the wide-angle camera.
  • Full Frame means that the area of the photosensitive element of the camera reaches a full frame size of 36mm*24mm.
  • the full-frame angle of view image taken by the wide-angle camera is the full-frame image taken within the range of the maximum horizontal and vertical angle of view.
  • the maximum field of view image captured by the rotatable camera includes the maximum field of view image that the rotatable camera can rotate the lens in the horizontal and vertical directions, that is, the lens is rotated to the maximum in the horizontal and vertical directions.
  • the angle of the image taken within the maximum viewable range.
  • Figures 2-4 exemplarily present an implementation of dynamically adjusting the angle of view based on a wide-angle camera.
  • the horizontal field of view and the vertical field of view of the wide-angle camera may be respectively set to multiple gears at predetermined intervals.
  • this embodiment sets the horizontal field of view of the wide-angle camera into multiple gears at 10° intervals, such as 120°, 110°, 100°, 90°, 80°, 70°. °.
  • the horizontal angle of view of the wide-angle camera is not less than 100°.
  • the vertical field of view of the wide-angle camera is also set to multiple gears at 10° intervals, such as 50°, 60°, 70°, and 80°.
  • the gear interval between the horizontal field of view and the vertical field of view of the wide-angle camera can be set to an appropriate angle according to the application scenario and the adjustment granularity, and is not limited to the 10° listed in the above example, and can also be other angles, such as 5°, 15°, 20°, etc.
  • this embodiment can collect the full field of view image (that is, the maximum field of view image) of the wide-angle camera at a rate of 1 frame/sec.
  • the position of the face is detected, and the (X, Y) and (X', Y') coordinates of the upper left and lower right corners of the rectangular frame of the face are recorded.
  • the coordinates of the lower left and upper right corners of the rectangular frame of the face may also be recorded.
  • the factors that affect the number of detectable faces include light, face angle, occlusion, sharpness, and so on.
  • the horizontal angle position corresponding to the minimum and maximum values of the coordinates of the face in the horizontal direction in the full field of view image of the wide-angle camera can be determined. , Calculate the minimum horizontal field of view gear that can view the face in the screen, and then adjust the horizontal field of view of the wide-angle camera to the minimum horizontal field of view gear.
  • the framing of the face image in the minimum horizontal field of view, can be symmetrical or asymmetrical, so that all faces are within the field of view of the camera and the shots are taken.
  • the margins of the video image are minimal.
  • the vertical angle positions of the minimum and maximum values of the coordinates of the face in the vertical direction can be determined in the full field of view image of the wide-angle camera. , So as to determine the best vertical field of view gear for framing the human face, and then adjust the vertical field of view of the wide-angle camera to the best vertical field of view gear.
  • the vertical viewing angle of the viewfinder includes all human faces, and a margin of 1/2 the height of the human face is left up and down.
  • Fig. 5 presents an exemplary embodiment of dynamically adjusting the angle of view based on a rotatable camera.
  • the lens of the rotatable camera is rotated to the maximum left-to-right and up-and-down rotation angles, and the reachable field of view image (that is, the maximum field of view image) is collected; all faces in the reachable field of view image are detected Horizontal and vertical coordinates; calculate the minimum and maximum values of the coordinates of all faces in the horizontal direction and the minimum and maximum values of the coordinates in the vertical direction; based on the minimum values of the coordinates of all faces in the horizontal direction And the maximum value and the minimum and maximum values of the coordinates in the vertical direction, respectively, adjust the horizontal and vertical angles of the rotatable camera to the appropriate angles to maximize the display area of people.
  • the horizontal field of view A of the rotatable camera can be rotated 30° to the left and 30° to the right, and the vertical field of view B can be rotated 15° upwards and 15° downwards.
  • the horizontal and vertical field of view A and B of the rotatable camera can be rotated from left to right, up and down, and the angle range can be set to a suitable angle according to the application scene and shooting range, and is not limited to the above examples.
  • the specific angles listed, and the angle ranges that the horizontal field angle A and the vertical field angle B of the rotatable camera can be rotated in the left and right, up and down directions may be the same or different.
  • this embodiment detects the positions of all faces in the reachable field of view image, and records the (X, Y) and (X', Y') of the upper left and lower right corners of the rectangular frame of the face. ) Coordinates, and map the face coordinates to the virtual space that can reach the field of view image. It should be understood that in some alternative implementations, the coordinates of the lower left and upper right corners of the rectangular frame of the face may also be recorded.
  • the horizontal field of view of the rotatable camera corresponding to the minimum and maximum values of the coordinates of the face in the horizontal direction can be determined, and the calculation can be used to calculate the horizontal field of view of the rotatable camera. All the framing is in the horizontal angle of view in the screen, and then the horizontal angle of the rotatable camera is rotated to realize the framing of all faces.
  • the side with less face can be discarded according to a preset rule, or the center position can be selected so that people on both sides There are just as few faces, so as to ensure that there are most faces in the field of view.
  • the vertical field of view of the rotatable camera corresponding to the minimum and maximum values of the coordinates of the face in the vertical direction can be determined. All the framing is in the vertical angle of view in the screen, and then the vertical angle of the rotatable camera is rotated to realize the framing of all faces.
  • a multi-frame tracking technology can be used to predict the direction of the face moving out of the screen, and the camera can be rotated to track people moving in the meeting.
  • Fig. 6 is a schematic structural diagram of a video image display device according to an embodiment of the present application. As shown in FIG. 6, the video image display device of the embodiment of the present application includes the following modules:
  • the acquisition module 210 is configured to acquire a maximum field of view image taken by the camera
  • the detection module 220 is configured to detect the horizontal and vertical coordinates of all faces in the maximum field of view image
  • the calculation module 230 is configured to calculate the minimum and maximum values of the coordinates in the horizontal direction and the minimum and maximum values of the coordinates in the vertical direction of all the faces;
  • the adjustment module 240 is configured to adjust the angle of view of the camera based on the minimum and maximum values of the coordinates in the horizontal direction and the minimum and maximum values of the coordinates in the vertical direction of all the faces, so that the camera All the people photographed are displayed in the video image output by the camera to the maximum extent.
  • the camera may include a wide-angle camera
  • the acquisition module 210 is further configured to obtain a maximum angle of view image captured by the wide-angle camera.
  • the maximum field of view image taken by the wide-angle camera includes the full field of view image taken by the physical lens of the wide-angle camera.
  • the horizontal field of view and the vertical field of view of the wide-angle camera are respectively set to multiple gears at predetermined intervals. Examples of the gear setting of the horizontal field of view and the vertical field of view of the wide-angle camera are shown in Figs. 2 and 3, which will not be repeated here.
  • the adjustment module 240 is further configured to:
  • the device may further include a tracking module 250 configured to track changes in the position of the face in the current video image captured by the camera in real time, and dynamically adjust the horizontal field of view gear And the vertical field of view gear.
  • the tracking module 250 can track the position change of the face in real time at a rate of 1 frame/sec. If the face moves outside the current display screen and continuously detects that all 3 frames are outside the screen, the horizontal or vertical expansion is performed.
  • the angle of view to a wider gear so as to ensure that the face is displayed within the video screen; if the face is gathered to the center of the picture, and 3 consecutive frames are detected to enter the gear with a narrower horizontal or vertical field of view, adjust the horizontal or Vertical field of view to a narrower gear.
  • the camera may include a rotatable camera.
  • the acquisition module 210 is also configured to acquire images with a maximum angle of view captured by the rotatable camera.
  • the maximum field of view image taken by the rotatable camera includes the maximum field of view image that the rotatable camera can reach by rotating the lens in the horizontal and vertical directions.
  • the adjustment module 240 is further configured to:
  • the tracking module 250 may also be configured to track changes in the position of the human face in the video image output by the camera in real time, and dynamically rotate the horizontal and vertical angles of the rotatable camera.
  • the tracking module 250 can predict the direction of the face moving out of the screen through a multi-frame tracking technology, and rotate the lens to track the moving people in the meeting.
  • the tracking module 250 can track the position change of the human face in real time at a rate of 1 frame/sec. If the human face moves outside the currently displayed image, it continuously detects the edges of the image that are all outside the image and in the opposite direction for 3 frames. If there is no face, rotate the lens to the direction that the face moves out of the screen, so that the face is displayed in the viewfinder again.
  • the horizontal and vertical coordinates of all human faces include the coordinates of at least two corner points of the detected rectangular frame of the human face.
  • detecting the coordinates of the face in the horizontal direction and the vertical direction refer to FIGS. 4 and 5, which will not be repeated here.
  • the steps, units, or modules involved in the embodiments of the present application can be implemented by software, hardware, or a combination thereof.
  • the described steps, units, or modules can also be implemented in a camera device or computing device, where the name of the unit or module does not constitute a limitation on the unit or module itself.
  • the camera device or computing device usually includes a processor that executes a program, and a memory for storing the program, where the program can implement the method steps described in this application when the program is loaded into the processor and run.
  • an embodiment of the present application may include a computer program product, which includes a readable storage medium storing one or more computer programs, and the computer program includes program code for executing the method described in the present application.
  • the embodiments of the present application may also include a computer-readable storage medium that stores one or more programs, and the one or more programs are executed by one or more processors. When executed, the method steps described in this application can be realized.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Studio Devices (AREA)

Abstract

一种视频图像显示方法和装置，该视频图像显示方法和装置获取摄像头拍摄的最大视场角图像；检测所述最大视场角图像中全部人脸在水平方向和垂直方向的坐标；计算所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值；基于所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，调整所述摄像头的视场角，使得所述摄像头拍摄的全部人员最大化地显示在所述摄像头输出的视频图像中。本申请基于人脸位置检测动态调整摄像头的视场角，自适应呈现人脸显示画面，提高了视频会议系统中人员视频图像的显示效果。

Description

视频图像显示方法和装置 技术领域
本申请涉及视频图像处理技术领域，具体涉及一种视频图像显示方法和装置。
背景技术
随着网络技术和多媒体技术的发展，视频会议系统得到了日益广泛的应用。视频会议系统利用通信网络和多媒体终端设备实现了异地参会人员之间的面对面的远程即时会议。现有的视频会议系统通常采用视频会议摄像头拍摄参会人员的视频图像，通过网络传输呈现给视频会议显示终端。
然而，现有的视频会议系统中，当采用广角摄像头时，摄像头的视场角固定，参会人员较少时，在显示画面中呈现的人像较小，参会人员较多时，则可能无法将全部人员取景在显示画面；而采用可旋转摄像头时，需要手动遥控器调整视场角，无法动态跟踪人脸调整角度。这些问题影响了视频会议系统中人员视频图像显示的效果。
发明内容
本申请实施例提供一种视频图像显示方法和装置，用于解决现有技术中视频会议系统中人员视频图像显示不佳的问题。
第一方面，本申请实施例提出一种视频图像显示方法，包括以下步骤：
获取摄像头拍摄的最大视场角图像；
检测所述最大视场角图像中全部人脸在水平方向和垂直方向的坐标；
计算所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值；
基于所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，调整所述摄像头的视场角，使得所述摄像头拍摄的全部人员最大化地显示在所述摄像头输出的视频图像中。
在一些实施方式中，所述摄像头包括广角摄像头；其中，所述获取摄像头拍摄的最大视场角图像包括获取所述广角摄像头拍摄的全幅视场角图像。
在一些实施方式中，所述方法还包括将所述广角摄像头的水平视场角和垂直视场角按照预定间隔分别设置为多个档位。
在一些实施方式中，所述基于所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，调整所述摄像头的视场角包括：
根据所述全部人脸在水平方向的坐标的最小值和最大值所对应的所述全幅视场角图像中的水平角度位置，调整所述广角摄像头的水平视场角档位；
根据所述全部人脸在垂直方向的坐标的最小值和最大值所对应的所述全幅视场角图像中的垂直角度位置，调整所述广角摄像头的垂直视场角档位。
在一些实施方式中，所述方法还包括：实时跟踪所述摄像头输出的视频图像中人脸的位置变化，动态调整所述水平视场角档位和垂直视场角档位。
在一些实施方式中，所述摄像头包括可旋转摄像头；其中，所述获取摄像头拍摄的最大视场角图像包括获取所述可旋转摄像头在水平和垂直方向旋转镜头可达的最大视场角图像。
在一些实施方式中，所述基于所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，调整所述摄像头的视场角包括：
根据所述全部人脸在水平方向的坐标的最小值和最大值所对应的所述可旋转摄像头的水平视场角，旋转所述可旋转摄像头的水平角度；
根据所述全部人脸在垂直方向的坐标的最小值和最大值所对应的所述可旋转摄像头的垂直视场角，旋转所述可旋转摄像头的垂直角度。
在一些实施方式中，所述方法还包括：实时跟踪所述摄像头输出的视频图像中人脸的位置变化，动态旋转所述可旋转摄像头的水平角度和垂直角度。
在一些实施方式中，所述全部人脸在水平方向和垂直方向的坐标包括检测出的人脸矩形框的至少两个角点的坐标。
第二方面，本申请实施例提出一种视频图像显示装置，包括：
采集模块，被配置为获取摄像头拍摄的最大视场角图像；
检测模块，被配置为检测所述最大视场角图像中全部人脸在水平方向和垂直方向的坐标；
计算模块，被配置为计算所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值；
调整模块，被配置为基于所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，调整所述摄像头的视场角，使得所述摄像头拍摄的全部人员最大化地显示在所述摄像头输出的视频图像中。
在一些实施方式中，所述摄像头包括广角摄像头；其中，所述采集模块被配置为获取所述广角摄像头拍摄的全幅视场角图像。
在一些实施方式中，所述广角摄像头的水平视场角和垂直视场角按照预定间隔分别被设置为多个档位。
在一些实施方式中，所述调整模块还被配置为：
根据所述全部人脸在水平方向的坐标的最小值和最大值所对应的所述全幅视场角图像中的水平角度位置，调整所述广角摄像头的水平视场角档位；
根据所述全部人脸在垂直方向的坐标的最小值和最大值所对应的所述全幅视场角图像中的垂直角度位置，调整所述广角摄像头的垂直视场角档位。
在一些实施方式中，所述装置还包括：跟踪模块，被配置为实时跟踪所述摄像头输出的视频图像中人脸的位置变化，动态调整所述水平视场角档位和垂直视场角档位。
在一些实施方式中，所述摄像头包括可旋转摄像头；其中，所述采集模块被配置为获取所述可旋转摄像头在水平和垂直方向旋转镜头可达的最大视场角图像。
在一些实施方式中，所述调整模块还被配置为：
根据所述全部人脸在水平方向的坐标的最小值和最大值对应的所述可旋转摄像头的水平视场角，旋转所述可旋转摄像头的水平角度；
根据所述全部人脸在垂直方向的坐标的最小值和最大值对应的所述可旋转摄像头的垂直视场角，旋转所述可旋转摄像头的垂直角度。
在一些实施方式中，所述装置还包括：跟踪模块，被配置为实时跟踪所述摄像头输出的视频图像中人脸的位置变化，动态旋转所述可旋转摄像头的水平角度和垂直角度。
在一些实施方式中，所述全部人脸在水平方向和垂直方向的坐标包括检测出的人脸矩形框的至少两个角点的坐标。
第三方面，本申请实施例还提供一种计算机可读存储介质，其上存储有一个或多个计算机程序，该一个或多个计算机程序被处理器执行以实现前述实施方式所述方法的步骤。
相对于现有技术，本申请实施例基于人脸位置检测调整摄像头的视场角，自适应呈现人脸显示画面，实现最大化人脸取景，提高了视频会议系统中人员视频图像的显示效 果。
附图说明
通过以下详细的描述并结合附图将更充分地理解本申请，其中相似的元件以相似的方式编号，其中：
图1是根据本申请实施例的视频图像显示方法的流程示意图；
图2是广角摄像头的水平视场角档位设置的示意图；
图3是广角摄像头的垂直视场角档位设置的示意图；
图4是基于广角摄像头的人脸位置检测的示意图；
图5是基于可旋转摄像头的人脸位置检测的示意图；
图6是根据本申请一实施例的视频图像显示装置的结构示例图；
图7是根据本申请又一实施例的视频图像显示装置的结构示例图。
具体实施方式
下面通过实施例，并结合附图，对本申请的技术方案进行清楚、完整地说明，但是本申请不限于以下所描述的实施例。基于以下实施例，本领域普通技术人员在没有创造性劳动的前提下所获得的所有其它实施例，都属于本申请保护的范围。为了清楚起见，在附图中省略了与描述示例性实施方式无关的部分。
应理解，本申请中诸如“包括”或“具有”等的术语旨在指示本说明书中所公开的特征、数字、步骤、行为、部件或其组合的存在，并不排除一个或多个其它特征、数字、步骤、行为、部件或其组合存在或被添加的可能性。
如前所述，现有的视频会议系统中摄像头的视场角固定或者需要手动调整，影响了视频会议系统中人员视频图像显示的效果。为了解决这些问题，本申请实施例提出一种视频图像显示方法和装置，基于人脸位置检测自适应调整摄像头的视场角(field of view，简称FOV)，实现人员的最佳画面取景，从而可以提高视频会议系统中人员视频图像显示的效果。
本申请实施例中，视场角就是摄像头镜头拍摄的角度范围，对于摄像头镜头来说，以镜头为顶点，以被拍摄目标的物像可通过镜头的最大范围的两条边缘构成的夹角可称为视场角。其中，镜头在水平方向拍摄的最大角度范围可称为水平视场角；镜头在垂直方向拍摄的最大角度范围可称为垂直视场角。
应理解，本申请实施例并不仅限于视频会议系统的应用场景，任何需要对人员进行实时视频图像显示的应用场景，均可以适用本申请实施例所描述的技术方案。
图1是根据本申请实施例的视频图像显示方法的流程示意图。如图1所示，本申请实施例的视频图像显示方法，包括以下步骤：
步骤S110，获取摄像头拍摄的最大视场角图像；
步骤S120，检测该最大视场角图像中全部人脸在水平方向和垂直方向的坐标；
步骤S130，计算该全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值；
步骤S140，基于该全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，调整该摄像头的视场角，使得所述摄像头拍摄的全部人员最大化地显示在所述摄像头输出的视频图像中。
本申请实施例通过获取摄像头拍摄的最大视场角图像，基于该最大视场角图像中人脸的坐标检测来动态调整摄像头的视场角，自适应呈现人脸显示画面，实现视频图像中人员的最佳显示效果。
本申请实施例中，步骤S110中摄像头拍摄的最大视场角图像可以理解为摄像头以最大视场角的可视范围所拍摄的视频图像。
在一些实施方式中，步骤S110中采用的摄像头可以包括广角摄像头或可旋转摄像头。其中，广角摄像头是一种焦距短于标准镜头、视场角大于标准镜头的摄像镜头。一般而言，广角摄像头的视场角越大，可视的范围就越大。可旋转摄像头是一种镜头可在上下、左右等不同方向旋转一定角度，实现不同角度范围的目标拍摄的摄像镜头。
当采用广角摄像头时，广角摄像头拍摄的最大视场角图像包括该广角摄像头的物理镜头所拍摄的全幅视场角图像。全幅(Full Frame)表示摄像头的感光元件面积达到36mm*24mm的全画幅尺寸。广角摄像头所拍摄的全幅视场角图像就是在最大水平和垂直视场角的范围内拍摄的全幅画面。
当采用可旋转摄像头时，可旋转摄像头拍摄的最大视场角图像包括该可旋转摄像头在水平和垂直方向旋转镜头可达的最大视场角图像，也就是镜头在水平和垂直方向分别旋转到最大角度所拍摄的最大可视范围内的图像。
图2-4示例性呈现了基于广角摄像头动态调整视场角的实施方式。本实施方式中，可以将广角摄像头的水平视场角和垂直视场角按照预定间隔分别设置为多个档位。随后，采集该广角摄像头的最大视场角图像；检测该最大视场角图像中全部人脸在水平方 向和垂直方向的坐标；计算该全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值；基于该全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，分别调整该广角摄像头的水平视场角和垂直视场角到合适的档位，以最大化显示有人的区域。
如图2所示，作为一种示例，本实施方式将广角摄像头的水平视场角按照10°间隔设置成多个档位，比如120°，110°，100°，90°，80°，70°。优选地，广角摄像头的水平视场角不小于100°。
如图3所示，作为一种示例，本实施方式将广角摄像头的垂直视场角按照10°间隔同样设置成多个档位，比如50°，60°，70°，80°。应理解，广角摄像头的水平视场角和垂直视场角的档位间隔可以根据应用场景和调节粒度设置合适的角度，并不限于上述示例所列举的10°，还可以是其他的角度，如5°，15°，20°等。
如图4所示，作为一种示例，本实施方式可采取1帧/秒的速度采集广角摄像头的全幅视场角图像(即最大视场角图像)，对该全幅视场角图像中的全部人脸进行位置检测，记录人脸矩形框的左上、右下两个角点的(X,Y)、(X’,Y’)坐标。应理解，在一些替代的实施方式中，还可以记录人脸矩形框的左下、右上两个角点的坐标。本实施方式中，影响可检测出人脸数的因素有光线，人脸角度，遮挡，清晰度等。
随后，计算人脸在水平方向的坐标的最小值Min(X1,X1’,…,Xn,Xn’)和最大值Max(X1,X1’,…,Xn,Xn’)，以及人脸在垂直方向的坐标的最小值Min(Y1,Y1’,…,Yn,Yn’)和最大值Max(Y1,Y1’,…,Yn,Yn’)。
在计算得到人脸在水平方向的坐标的最小值和最大值之后，可以确定人脸在水平方向的坐标的最小值和最大值所对应的在广角摄像头的全幅视场角图像中的水平角度位置，计算能把人脸取景在画面内的最小水平视场角档位，进而将广角摄像头的水平视场角调整至该最小水平视场角档位。
在一些实施方式中，最小水平视场角档位下，对人脸图像的取景可以是对称取景，也可以是非对称取景，以达到全部人脸都在摄像头的视场角范围内，且拍摄的视频图像的边缘空白最少。
在计算得到人脸在垂直方向的坐标的最小值和最大值之后，可以确定人脸在垂直方向的坐标的最小值和最大值所对应的在广角摄像头的全幅视场角图像中的垂直角度位置，从而可以确定对人脸取景的最佳垂直视场角档位，进而将广角摄像头的垂直视场角调整至该最佳垂直视场角档位。
在一些实施方式中，最佳垂直视场角档位下，可以确保取景的垂直视场角包含全部人脸，且上下保留1/2人脸高度的边缘空白。
通过上述的视场角调整方式，可以实现广角摄像头拍摄的全部人员最大化地显示在摄像头输出的视频图像中，实现人员画面的最佳取景效果。
在一些实施方式中，还可以实时跟踪摄像头拍摄的当前视频图像中人脸的位置变化，动态调整广角摄像头的水平视场角档位和垂直视场角档位。作为一种示例，可以采取1帧/秒的速度实时跟踪人脸的位置变化，如果人脸移动到当前显示画面之外，连续检测到3帧都在画面外，则扩大水平或垂直视场角到更宽的档位，从而确保人脸显示在视频画面以内；如果人脸向画面中心聚集，连续检测3帧都进入水平或垂直视场角更窄的档位，则调整水平或垂直视场角到更窄的档位。
图5呈现了基于可旋转摄像头动态调整视场角的示例性的实施方式。本实施方式中，旋转可旋转摄像头的镜头到最大左右旋转、上下旋转的角度，采集可达视场角图像(即最大视场角图像)；检测该可达视场角图像中全部人脸在水平方向和垂直方向的坐标；计算该全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值；基于该全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，分别调整可旋转摄像头的水平角度和垂直角度到合适的角度，以最大化显示有人的区域。
如图5所示，作为一种示例，可旋转摄像头的水平视场角A可向左旋转30°和向右旋转30°，垂直视场角B可向上旋转15°和向下旋转15°。应理解，本实施方式中，可旋转摄像头的水平视场角A和垂直视场角B的左右、上下可旋转的角度范围可以根据应用场景和拍摄范围设置合适的角度，并不限于上述示例所列举的具体角度，并且可旋转摄像头的水平视场角A和垂直视场角B在左右、上下方向可旋转的角度范围可以相同，也可以不同。
作为一种示例，本实施方式检测该可达视场角图像中全部人脸的位置，记录人脸矩形框的左上、右下两个角点的(X,Y)、(X’,Y’)坐标，并将人脸坐标映射到可达视场角图像的虚拟空间中。应理解，在一些替代的实施方式中，还可以记录人脸矩形框的左下、右上两个角点的坐标。
随后，计算人脸在水平方向的坐标的最小值Min(X1,X1’,…,Xn,Xn’)和最大值Max(X1,X1’,…,Xn,Xn’)，以及人脸在垂直方向的坐标的最小值Min(Y1,Y1’,…,Yn,Yn’)和最大值Max(Y1,Y1’,…,Yn,Yn’)。
在计算得到人脸在水平方向的坐标的最小值和最大值之后，可以确定人脸在水平方向的坐标的最小值和最大值所对应的可旋转摄像头的水平视场角，计算能把人脸全部取景在画面内的水平视场角，进而旋转可旋转摄像头的水平角度，实现全部人脸取景。
在一些实施方式中，如果人脸在水平方向的坐标的最小值和最大值，超出可旋转镜头的水平视场角，可以根据预设规则舍弃人脸少的一边，或者选择居中位置使得两边人脸一样少，从而确保视场角内人脸最多。
在计算得到人脸在垂直方向的坐标的最小值和最大值之后，可以确定人脸在垂直方向的坐标的最小值和最大值所对应的可旋转摄像头的垂直视场角，计算能把人脸全部取景在画面内的垂直视场角，进而旋转可旋转摄像头的垂直角度，实现全部人脸取景。
通过上述的视场角调整方式，可以实现可旋转摄像头拍摄的全部人员最大化地显示在摄像头输出的视频图像中，实现人员画面的最佳取景效果。
在一些实施方式中，还可以实时跟踪摄像头拍摄的当前视频图像中人脸的位置变化，动态调整可旋转摄像头的水平角度和垂直角度。在可选的实施方式中，可以通过多帧跟踪技术预测人脸移出画面方向，并旋转镜头以跟踪会议中移动的人员。作为一种示例，可以采取1帧/秒的速度实时跟踪人脸的位置变化，如果人脸移动到当前显示画面之外，连续检测3帧都在画面外，且相反方向的画面边缘没有人脸，则旋转镜头到人脸移动出画面的方向，以使得人脸再次被取景显示。
图6是根据本申请实施例的视频图像显示装置的结构示意图。如图6所示，本申请实施例的视频图像显示装置，包括以下模块：
采集模块210，被配置为获取摄像头拍摄的最大视场角图像；
检测模块220，被配置为检测所述最大视场角图像中全部人脸在水平方向和垂直方向的坐标；
计算模块230，被配置为计算所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值；
调整模块240，被配置为基于所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，调整所述摄像头的视场角，使得所述摄像头拍摄的全部人员最大化地显示在所述摄像头输出的视频图像中。
在一些实施方式中，所述摄像头可以包括广角摄像头，采集模块210还被配置为获取广角摄像头拍摄的最大视场角图像。广角摄像头拍摄的最大视场角图像包括该广角摄像头的物理镜头所拍摄的全幅视场角图像。
在一些实施方式中，当采用广角摄像头时，广角摄像头的水平视场角和垂直视场角按照预定间隔分别被设置为多个档位。广角摄像头的水平视场角和垂直视场角的档位设置的示例参见图2和3所示，在此不再赘述。
在一些实施方式中，调整模块240还被配置为：
根据所述全部人脸在水平方向的坐标的最小值和最大值在所述全幅视场角图像中的水平角度位置，调整所述广角摄像头的水平视场角档位；
根据所述全部人脸在垂直方向的坐标的最小值和最大值在所述全幅视场角图像中的垂直角度位置，调整所述广角摄像头的垂直视场角档位。
在一些实施方式中，如图7所示，所述装置还可以包括跟踪模块250，被配置为实时跟踪摄像头拍摄的当前视频图像中人脸的位置变化，动态调整所述水平视场角档位和垂直视场角档位。作为一种示例，跟踪模块250可以采取1帧/秒的速度实时跟踪人脸的位置变化，如果人脸移动到当前显示画面之外，连续检测到3帧都在画面外，则扩大水平或垂直视场角到更宽的档位，从而确保人脸显示在视频画面以内；如果人脸向画面中心聚集，连续检测3帧都进入水平或垂直视场角更窄的档位，则调整水平或垂直视场角到更窄的档位。
在一些实施方式中，所述摄像头可以包括可旋转摄像头。采集模块210还被配置为获取可旋转摄像头拍摄的最大视场角图像。可旋转摄像头拍摄的最大视场角图像包括该可旋转摄像头在水平和垂直方向旋转镜头可达的最大视场角图像。
在一些实施方式中，调整模块240还被配置为：
根据所述全部人脸在水平方向的坐标的最小值和最大值对应的所述可旋转摄像头的水平视场角，旋转所述可旋转摄像头的水平角度；
根据所述全部人脸在垂直方向的坐标的最小值和最大值对应的所述可旋转摄像头的垂直视场角，旋转所述可旋转摄像头的垂直角度。
在一些实施方式中，跟踪模块250还可以被配置为实时跟踪摄像头输出的视频图像中人脸的位置变化，动态旋转所述可旋转摄像头的水平角度和垂直角度。在可选的实施方式中，跟踪模块250可以通过多帧跟踪技术预测人脸移出画面方向，并旋转镜头以跟踪会议中移动的人员。作为一种示例，跟踪模块250可以采取1帧/秒的速度实时跟踪人脸的位置变化，如果人脸移动到当前显示画面之外，连续检测3帧都在画面外，且相反方向的画面边缘没有人脸，则旋转镜头到人脸移动出画面的方向，以使得人脸再次被取景显示。
在一些实施方式中，所述全部人脸在水平方向和垂直方向的坐标包括检测出的人脸矩形框的至少两个角点的坐标。人脸在水平方向和垂直方向的坐标检测的示例参见图4和5，在此不再赘述。
本申请实施例中所涉及到的步骤、单元或模块可以通过软件、硬件或其结合的方式实现。所描述的步骤、单元或模块也可以实施在摄像头器件或计算设备中，其中单元或模块的名称并不构成对该单元或模块本身的限定。该摄像头器件或计算设备通常包括执行程序的处理器，以及用于存储程序的存储器，其中所述程序加载到处理器中运行时可以实现本申请所描述的方法步骤。
本申请实施例描述的方法可以被实现为计算机软件程序。例如，本申请实施例可以包括一种计算机程序产品，其包括存储有一个或一个以上计算机程序的可读存储介质，所述计算机程序包含用于执行本申请所述描述的方法的程序代码。另一方面，本申请实施例也可以包括一种计算机可读存储介质，该计算机可读存储介质存储有一个或一个以上的程序，所述一个或一个以上的程序被一个或一个以上的处理器执行时，可以实现本申请所描述的方法步骤。
本申请的实施方式并不限于上述实施例所述，在不偏离本申请的精神和范围的情况下，本领域普通技术人员可以在形式和细节上对本申请做出各种改变和改进，这些均被认为落入了本申请的保护范围。

Claims (18)

  1. 一种视频图像显示方法，其特征在于，包括以下步骤：
    获取摄像头拍摄的最大视场角图像；
    检测所述最大视场角图像中全部人脸在水平方向和垂直方向的坐标；
    计算所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值；
    基于所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，调整所述摄像头的视场角，使得所述摄像头拍摄的全部人员最大化地显示在所述摄像头输出的视频图像中。
  2. 根据权利要求1所述的视频图像显示方法，其特征在于，所述摄像头包括广角摄像头；其中，所述获取摄像头拍摄的最大视场角图像包括获取所述广角摄像头拍摄的全幅视场角图像。
  3. 根据权利要求2所述的视频图像显示方法，其特征在于，所述方法还包括将所述广角摄像头的水平视场角和垂直视场角按照预定间隔分别设置为多个档位。
  4. 根据权利要求3所述的视频图像显示方法，其特征在于，所述基于所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，调整所述摄像头的视场角包括：
    根据所述全部人脸在水平方向的坐标的最小值和最大值所对应的所述全幅视场角图像中的水平角度位置，调整所述广角摄像头的水平视场角档位；
    根据所述全部人脸在垂直方向的坐标的最小值和最大值所对应的所述全幅视场角图像中的垂直角度位置，调整所述广角摄像头的垂直视场角档位。
  5. 根据权利要求4所述的视频图像显示方法，其特征在于，所述方法还包括：实时跟踪所述摄像头输出的视频图像中人脸的位置变化，动态调整所述水平视场角档位和垂直视场角档位。
  6. 根据权利要求1所述的视频图像显示方法，其特征在于，所述摄像头包括可旋转摄像头；其中，所述获取摄像头拍摄的最大视场角图像包括获取所述可旋转摄像头在水平和垂直方向旋转镜头可达的最大视场角图像。
  7. 根据权利要求6所述的视频图像显示方法，其特征在于，所述基于所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，调整 所述摄像头的视场角包括：
    根据所述全部人脸在水平方向的坐标的最小值和最大值所对应的所述可旋转摄像头的水平视场角，旋转所述可旋转摄像头的水平角度；
    根据所述全部人脸在垂直方向的坐标的最小值和最大值所对应的所述可旋转摄像头的垂直视场角，旋转所述可旋转摄像头的垂直角度。
  8. 根据权利要求7所述的视频图像显示方法，其特征在于，所述方法还包括：实时跟踪所述摄像头输出的视频图像中人脸的位置变化，动态旋转所述可旋转摄像头的水平角度和垂直角度。
  9. 根据权利要求1所述的视频图像显示方法，其特征在于，所述全部人脸在水平方向和垂直方向的坐标包括检测出的人脸矩形框的至少两个角点的坐标。
  10. 一种视频图像显示装置，其特征在于，包括：
    采集模块，被配置为获取摄像头拍摄的最大视场角图像；
    检测模块，被配置为检测所述最大视场角图像中全部人脸在水平方向和垂直方向的坐标；
    计算模块，被配置为计算所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值；
    调整模块，被配置为基于所述全部人脸在水平方向的坐标的最小值和最大值以及在垂直方向的坐标的最小值和最大值，调整所述摄像头的视场角，使得所述摄像头拍摄的全部人员最大化地显示在所述摄像头输出的视频图像中。
  11. 根据权利要求10所述的视频图像显示装置，其特征在于，所述摄像头包括广角摄像头；其中，所述采集模块被配置为获取所述广角摄像头拍摄的全幅视场角图像。
  12. 根据权利要求11所述的视频图像显示装置，其特征在于，所述广角摄像头的水平视场角和垂直视场角按照预定间隔分别被设置为多个档位。
  13. 根据权利要求12所述的视频图像显示装置，其特征在于，所述调整模块还被配置为：
    根据所述全部人脸在水平方向的坐标的最小值和最大值所对应的所述全幅视场角图像中的水平角度位置，调整所述广角摄像头的水平视场角档位；
    根据所述全部人脸在垂直方向的坐标的最小值和最大值所对应的所述全幅视场角图像中的垂直角度位置，调整所述广角摄像头的垂直视场角档位。
  14. 根据权利要求13所述的视频图像显示装置，其特征在于，所述装置还包括： 跟踪模块，被配置为实时跟踪所述摄像头输出的视频图像中人脸的位置变化，动态调整所述水平视场角档位和垂直视场角档位。
  15. 根据权利要求10所述的视频图像显示装置，其特征在于，所述摄像头包括可旋转摄像头；其中，所述采集模块被配置为获取所述可旋转摄像头在水平和垂直方向旋转镜头可达的最大视场角图像。
  16. 根据权利要求15所述的视频图像显示装置，其特征在于，所述调整模块还被配置为：
    根据所述全部人脸在水平方向的坐标的最小值和最大值对应的所述可旋转摄像头的水平视场角，旋转所述可旋转摄像头的水平角度；
    根据所述全部人脸在垂直方向的坐标的最小值和最大值对应的所述可旋转摄像头的垂直视场角，旋转所述可旋转摄像头的垂直角度。
  17. 根据权利要求16所述的视频图像显示装置，其特征在于，所述装置还包括：跟踪模块，被配置为实时跟踪所述摄像头输出的视频图像中人脸的位置变化，动态旋转所述可旋转摄像头的水平角度和垂直角度。
  18. 根据权利要求10所述的视频图像显示装置，其特征在于，所述全部人脸在水平方向和垂直方向的坐标包括检测出的人脸矩形框的至少两个角点的坐标。
PCT/CN2019/114027 2019-10-29 2019-10-29 视频图像显示方法和装置 WO2021081756A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US17/732,481 US20230146794A1 (en) 2019-10-29 2019-10-29 Video image display method and apparatus
PCT/CN2019/114027 WO2021081756A1 (zh) 2019-10-29 2019-10-29 视频图像显示方法和装置
CN201980101819.8A CN114641984A (zh) 2019-10-29 2019-10-29 视频图像显示方法和装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/114027 WO2021081756A1 (zh) 2019-10-29 2019-10-29 视频图像显示方法和装置

Publications (1)

Publication Number Publication Date
WO2021081756A1 true WO2021081756A1 (zh) 2021-05-06

Family

ID=75715679

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/114027 WO2021081756A1 (zh) 2019-10-29 2019-10-29 视频图像显示方法和装置

Country Status (3)

Country Link
US (1) US20230146794A1 (zh)
CN (1) CN114641984A (zh)
WO (1) WO2021081756A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117237438B (zh) * 2023-09-18 2024-06-28 共享数据(福建)科技有限公司 一种三维模型和无人机视频数据的范围匹配方法与终端

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100141772A1 (en) * 2008-12-04 2010-06-10 Ritsuo Inaguma Image processing device and method, image processing system, and image processing program
CN103248824A (zh) * 2013-04-27 2013-08-14 天脉聚源(北京)传媒科技有限公司 一种摄像头拍摄角度的确定方法、装置及摄像系统
CN103327250A (zh) * 2013-06-24 2013-09-25 深圳锐取信息技术股份有限公司 基于模式识别镜头控制方法
EP3096204A1 (en) * 2015-05-20 2016-11-23 Panasonic Intellectual Property Management Co., Ltd. Image display device and image processing device
CN106603912A (zh) * 2016-12-05 2017-04-26 科大讯飞股份有限公司 一种视频直播控制方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100141772A1 (en) * 2008-12-04 2010-06-10 Ritsuo Inaguma Image processing device and method, image processing system, and image processing program
CN103248824A (zh) * 2013-04-27 2013-08-14 天脉聚源(北京)传媒科技有限公司 一种摄像头拍摄角度的确定方法、装置及摄像系统
CN103327250A (zh) * 2013-06-24 2013-09-25 深圳锐取信息技术股份有限公司 基于模式识别镜头控制方法
EP3096204A1 (en) * 2015-05-20 2016-11-23 Panasonic Intellectual Property Management Co., Ltd. Image display device and image processing device
CN106603912A (zh) * 2016-12-05 2017-04-26 科大讯飞股份有限公司 一种视频直播控制方法及装置

Also Published As

Publication number Publication date
US20230146794A1 (en) 2023-05-11
CN114641984A (zh) 2022-06-17

Similar Documents

Publication Publication Date Title
US8390667B2 (en) Pop-up PIP for people not in picture
US8749607B2 (en) Face equalization in video conferencing
US9160966B2 (en) Imaging through a display screen
JP6077655B2 (ja) 撮影システム
US20230132407A1 (en) Method and device of video virtual background image processing and computer apparatus
WO2018103233A1 (zh) 基于虚拟现实技术的观景方法、装置及系统
CN112311965A (zh) 虚拟拍摄方法、装置、系统及存储介质
CN106020758B (zh) 一种荧幕拼接显示系统及方法
CN109981972B (zh) 一种机器人的目标跟踪方法、机器人及存储介质
CN111062234A (zh) 一种监控方法、智能终端及计算机可读存储介质
US10827117B2 (en) Method and apparatus for generating indoor panoramic video
CN106851094A (zh) 一种信息处理方法和装置
CN112907617B (zh) 一种视频处理方法及其装置
WO2021081756A1 (zh) 视频图像显示方法和装置
CN112601028B (zh) 摄像控制方法、装置、计算机设备和存储介质
TWI488503B (zh) 會議攝錄裝置及其方法
JP2023526806A (ja) 手振れ防止方法、手振れ防止装置及び電子機器
CN106488128B (zh) 一种自动拍照的方法及装置
WO2023036218A1 (zh) 视点宽度的确定方法及其装置
WO2022007681A1 (zh) 拍摄控制方法、移动终端和计算机可读存储介质
CN115065782A (zh) 一种场景采集方法、采集装置、摄像设备及存储介质
US20200252585A1 (en) Systems, Algorithms, and Designs for See-through Experiences With Wide-Angle Cameras
TW202211667A (zh) 全視角會議攝影裝置
CN106993157A (zh) 一种基于双摄像头的智能监控方法及装置
KR20190087942A (ko) 대상체 추적 장치 및 방법

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: 19950801

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19950801

Country of ref document: EP

Kind code of ref document: A1