公开(公告)号：US11438549B2

公开(公告)日：2022-09-06

申请号：US17294568

申请日：2018-11-22

Applicant: Polycom, Inc.

Inventor： Tianran Wang ,  Wenxue He ,  Lidan Qin ,  Hai Xu

IPC: H04N7/15 ,  G06V40/10 ,  G06T7/20 ,  H04L12/18 ,  H04L65/1083

Abstract: A videoconferencing endpoint is described that uses a combination of face detection, motion detection, and upper body detection for selecting participants of a videoconference for group framing. Motion detection is used to remove fake faces as well as to detect motion in regions around detected faces during postprocessing. Upper body detection is used in conjunction with the motion detection in postprocessing to allow saving faces that have been initially detected by face detection for group framing even if the participant has turned away from the camera, allowing the endpoint to keep tracking the participants region better than would be possible based only on an unstable result coming from face detection.

公开(公告)号：US20220005162A1

公开(公告)日：2022-01-06

申请号：US17294565

申请日：2018-11-23

Applicant: Polycom, Inc.

Inventor： Tianran Wang ,  Hailin Song ,  Wenxue He

IPC: G06T5/00 ,  G06T7/11 ,  G06T3/00

Abstract: A method includes receiving, at a conference endpoint, video captured using a wide angle lens. The method further includes selecting a view region in a frame of the video. The method further includes selectively applying, based on a size of the view region, deformation correction or distortion correction to the view region to generate a corrected video frame. The method further includes transmitting the corrected video frame to a remote endpoint.

公开(公告)号：US20220006974A1

公开(公告)日：2022-01-06

申请号：US17294568

申请日：2018-11-22

Applicant: Polycom, Inc.

Inventor： Tianran Wang ,  Wenxue He ,  Lidan Qin ,  Hai Xu

IPC: H04N7/15 ,  H04L29/06 ,  H04L12/18 ,  G06T7/20 ,  G06K9/00

Abstract: A videoconferencing endpoint is described that uses a combination of face detection, motion detection, and upper body detection for selecting participants of a videoconference for group framing. Motion detection is used to remove fake faces as well as to detect motion in regions around detected faces during postprocessing. Upper body detection is used in conjunction with the motion detection in postprocessing to allow saving faces that have been initially detected by face detection for group framing even if the participant has turned away from the camera, allowing the endpoint to keep tracking the participants region better than would be possible based only on an unstable result coming from face detection.

公开(公告)号：US20210409645A1

公开(公告)日：2021-12-30

申请号：US17294573

申请日：2018-11-22

Applicant: Polycom, Inc.

Inventor： Hai Xu ,  Xi Lu ,  Yongkang Fan ,  Wenxue He

IPC: H04N7/15 ,  G06K9/00 ,  G06N3/04 ,  G06N3/08

Abstract: A videoconferencing endpoint is described that uses a cascading sequence of convolutional neural networks to perform face detection and upper body detection of participants in a videoconference at the endpoint, where at least one member of the sequence of neural networks performs upper body detection, and where the final member of the sequence of neural networks performs face detection based on the results of the upper body detection. The models of the neural networks are trained on both large datasets of faces well as images that have been distorted by a wide-angle camera of the videoconferencing endpoint.