公开(公告)号：US09392218B2

公开(公告)日：2016-07-12

申请号：US14972222

申请日：2015-12-17

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yanling Guo ,  Tian Wang ,  Dejun Zhang

IPC: H04N7/14 ,  H04N7/15 ,  H04N19/172 ,  H04N19/182 ,  H04N19/186 ,  H04N19/503 ,  G06T7/00

CPC classification number: H04N7/142 ,  G06T7/11 ,  G06T7/194 ,  G06T7/50 ,  G06T2207/10024 ,  G06T2207/10028 ,  H04N7/15 ,  H04N19/115 ,  H04N19/167 ,  H04N19/17 ,  H04N19/172 ,  H04N19/182 ,  H04N19/186 ,  H04N19/29 ,  H04N19/503 ,  H04N19/597

Abstract: An image processing method may include collecting a video image and a depth map of an object; segmenting, using the depth map, a video image frame corresponding to the video image at a same moment to obtain a contour of a foreground image in the video image frame; performing, according to the contour of the foreground image, first encoding on pixels of a video image inside the contour of the foreground image in the video image frame and second encoding on pixels of a video image outside the contour in the video image frame, where an encoding rate of the first encoding is higher than an encoding rate of the second encoding. According to the embodiments of the present disclosure, an occupation rate of network bandwidth in a video image transmission process can be lowered.

Abstract translation: 图像处理方法可以包括收集对象的视频图像和深度图; 使用深度图分割在同一时刻对应于视频图像的视频图像帧，以获得视频图像帧中的前景图像的轮廓; 根据前景图像的轮廓对视频图像帧中的前景图像的轮廓内的视频图像的像素进行第一编码，并对视频图像帧中的轮廓外的视频图像的像素进行第二编码，其中 第一编码的编码率高于第二编码的编码率。 根据本公开的实施例，可以降低视频图像传输处理中的网络带宽的占用率。

公开(公告)号：US20160381322A1

公开(公告)日：2016-12-29

申请号：US15262596

申请日：2016-09-12

Applicant: Huawei Technologies Co., Ltd.

Inventor： Tian Wang ,  Yanling Guo ,  Bo Liu

IPC: H04N7/15 ,  H04N7/14 ,  H04N5/04

CPC classification number: H04N7/15 ,  H04N5/04 ,  H04N7/142

Abstract: A method, device, and system for implementing a video conference includes obtaining in real time an image of a first scene from a main camera located in a first conference site, obtaining in real time an image of a second scene from an auxiliary camera located in the first conference site, the second scene is a part of the first scene, and the second scene includes a target object, generating a target image in real time according to the image of the first scene and the image of the second scene and based on a location of the target object in the first conference site, a location of the image of the second scene in the target image is corresponding to the location of the target object in the first conference site, and sending the target image in real time to a display device located in a second conference site.

Abstract translation: 用于实现视频会议的方法，设备和系统包括从位于第一会场的主摄像机实时获取第一场景的图像，实时地从位于第一会场的辅助摄像机获得第二场景的图像 所述第一会场，所述第二场景是所述第一场景的一部分，所述第二场景包括目标对象，根据所述第一场景的图像和所述第二场景的图像实时生成目标图像，并且基于 第一会场中的目标对象的位置，目标图像中的第二场景的图像的位置对应于第一会场中的目标对象的位置，并将目标图像实时发送到 显示设备位于第二个会场。

公开(公告)号：US09848168B2

公开(公告)日：2017-12-19

申请号：US15262596

申请日：2016-09-12

Applicant: Huawei Technologies Co., Ltd.

Inventor： Tian Wang ,  Yanling Guo ,  Bo Liu

IPC: H04N7/14 ,  H04N7/15 ,  H04N5/04

CPC classification number: H04N7/15 ,  H04N5/04 ,  H04N7/142

Abstract: A method, device, and system for implementing a video conference includes obtaining in real time an image of a first scene from a main camera located in a first conference site, obtaining in real time an image of a second scene from an auxiliary camera located in the first conference site, the second scene is a part of the first scene, and the second scene includes a target object, generating a target image in real time according to the image of the first scene and the image of the second scene and based on a location of the target object in the first conference site, a location of the image of the second scene in the target image is corresponding to the location of the target object in the first conference site, and sending the target image in real time to a display device located in a second conference site.

公开(公告)号：US20160105636A1

公开(公告)日：2016-04-14

申请号：US14972222

申请日：2015-12-17

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yanling Guo ,  Tian Wang ,  Dejun Zhang

IPC: H04N7/14 ,  H04N19/172 ,  G06T7/00 ,  H04N19/186 ,  H04N19/503 ,  H04N7/15 ,  H04N19/182

CPC classification number: H04N7/142 ,  G06T7/11 ,  G06T7/194 ,  G06T7/50 ,  G06T2207/10024 ,  G06T2207/10028 ,  H04N7/15 ,  H04N19/115 ,  H04N19/167 ,  H04N19/17 ,  H04N19/172 ,  H04N19/182 ,  H04N19/186 ,  H04N19/29 ,  H04N19/503 ,  H04N19/597

Abstract: An image processing method may include collecting a video image and a depth map of an object; segmenting, using the depth map, a video image frame corresponding to the video image at a same moment to obtain a contour of a foreground image in the video image frame; performing, according to the contour of the foreground image, first encoding on pixels of a video image inside the contour of the foreground image in the video image frame and second encoding on pixels of a video image outside the contour in the video image frame, where an encoding rate of the first encoding is higher than an encoding rate of the second encoding. According to the embodiments of the present disclosure, an occupation rate of network bandwidth in a video image transmission process can be lowered.

Abstract translation: 图像处理方法可以包括收集对象的视频图像和深度图; 使用深度图分割在同一时刻对应于视频图像的视频图像帧，以获得视频图像帧中的前景图像的轮廓; 根据前景图像的轮廓对视频图像帧中的前景图像的轮廓内的视频图像的像素进行第一编码，并对视频图像帧中的轮廓外的视频图像的像素进行第二编码，其中 第一编码的编码率高于第二编码的编码率。 根据本公开的实施例，可以降低视频图像传输处理中的网络带宽的占用率。