Patents by Inventor Jinwei Feng

Jinwei Feng has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20190174068
    Abstract: A videoconference apparatus and method coordinates a stationary view obtained with a stationary camera to an adjustable view obtained with an adjustable camera. The stationary camera can be a web camera, while the adjustable camera can be a pan-tilt-zoom camera. As the stationary camera obtains video, participants are detected and localized by establishing a static perimeter around a participant in which no motion is detected. Thereafter, if no motion is detected in the perimeter, any personage objects such as head, face, or shoulders which are detected in the region bounded by the perimeter are determined to correspond to the participant.
    Type: Application
    Filed: December 20, 2018
    Publication date: June 6, 2019
    Inventors: Xiangdong Wang, Yibo Liu, Jinwei Feng, Edmund Thompson, Peter Chu
  • Publication number: 20190156849
    Abstract: A videoconference apparatus at a first location detects audio from a location and determines whether the sound should be included in an audio-video stream sent to a second location, or excluded as an interfering noise. Determining whether to include the audio involves using a face detector to see if there is a face at the source of the sound. If a face is present, the audio data from the location will be transmitted to the second location. If a face is not present, additional motion checks are performed to determine whether the sound corresponds to a person talking, (such as a presenter at a meeting), or whether the sound is instead unwanted noise.
    Type: Application
    Filed: November 2, 2018
    Publication date: May 23, 2019
    Inventors: Jinwei Feng, Peter Chu
  • Publication number: 20190158733
    Abstract: A system for ensuring that the best available view of a person's face is included in a video stream when the person's face is being captured by multiple cameras at multiple angles at a first endpoint. The system uses one or more microphone arrays to capture direct-reverberant ratio information corresponding to the views, and determines which view most closely matches a view of the person looking directly at the camera, thereby improving the experience for viewers at a second endpoint.
    Type: Application
    Filed: September 26, 2018
    Publication date: May 23, 2019
    Inventors: Jinwei Feng, Peter Chu
  • Patent number: 10206036
    Abstract: A method of detecting respective source locations of sounds in an audio signal. The method includes receiving the audio signal via a horizontal set of microphones and a vertical set of microphones. The respective source locations of the sounds in the audio signal are determined by analyzing the audio signal. Analysis is conducted with respect to the horizontal set of microphones and with respect to the vertical set of microphones, to determine a respective horizontal direction to the respective source locations of the sounds, and determine a respective vertical direction to the respective source locations of the sounds. The distance is calculated between the respective source locations of the sounds and the horizontal set of microphones and the vertical set of microphones.
    Type: Grant
    Filed: August 6, 2018
    Date of Patent: February 12, 2019
    Assignee: Alibaba Group Holding Limited
    Inventors: Jinwei Feng, Tao Yu
  • Patent number: 10187579
    Abstract: A videoconference apparatus and method coordinates a stationary view obtained with a stationary camera to an adjustable view obtained with an adjustable camera. The stationary camera can be a web camera, while the adjustable camera can be a pan-tilt-zoom camera. As the stationary camera obtains video, participants are detected and localized by establishing a static perimeter around a participant in which no motion is detected. Thereafter, if no motion is detected in the perimeter, any personage objects such as head, face, or shoulders which are detected in the region bounded by the perimeter are determined to correspond to the participant.
    Type: Grant
    Filed: June 30, 2017
    Date of Patent: January 22, 2019
    Assignee: Polycom, Inc.
    Inventors: Xiangdong Wang, Yibo Liu, Jinwei Feng, Edmund Thompson, Peter Chu
  • Publication number: 20190007623
    Abstract: A videoconference apparatus and method coordinates a stationary view obtained with a stationary camera to an adjustable view obtained with an adjustable camera. The stationary camera can be a web camera, while the adjustable camera can be a pan-tilt-zoom camera. As the stationary camera obtains video, participants are detected and localized by establishing a static perimeter around a participant in which no motion is detected. Thereafter, if no motion is detected in the perimeter, any personage objects such as head, face, or shoulders which are detected in the region bounded by the perimeter are determined to correspond to the participant.
    Type: Application
    Filed: June 30, 2017
    Publication date: January 3, 2019
    Inventors: Xiangdong Wang, Yibo Liu, Jinwei Feng, Edmund Thompson, Peter Chu
  • Patent number: 10134414
    Abstract: A videoconference apparatus at a first location detects audio from a location and determines whether the sound should be included in an audio-video stream sent to a second location, or excluded as an interfering noise. Determining whether to include the audio involves using a face detector to see if there is a face at the source of the sound. If a face is present, the audio data from the location will be transmitted to the second location. If a face is not present, additional motion checks are performed to determine whether the sound corresponds to a person talking, (such as a presenter at a meeting), or whether the sound is instead unwanted noise.
    Type: Grant
    Filed: June 30, 2017
    Date of Patent: November 20, 2018
    Assignee: Polycom, Inc.
    Inventors: Jinwei Feng, Peter Chu
  • Patent number: 10122972
    Abstract: A videoconferencing endpoint includes at least one processor a number of microphones and at least one camera. The endpoint can receive audio information and visual motion information during a teleconferencing session. The audio information includes one or more angles with respect to the microphone from a location of a teleconferencing session. The system evaluates the audio information is evaluated to determine at least one candidate angle corresponding to a possible location of an active talker. The candidate angle can be analyzed further with respect to the motion information to determine whether the candidate angle correctly corresponds to person who is speaking during the teleconferencing session. The person's face can then be framed within a frame view.
    Type: Grant
    Filed: November 9, 2017
    Date of Patent: November 6, 2018
    Assignee: Polycom, Inc.
    Inventor: Jinwei Feng
  • Patent number: 10091412
    Abstract: A system for ensuring that the best available view of a person's face is included in a video stream when the person's face is being captured by multiple cameras at multiple angles at a first endpoint. The system uses one or more microphone arrays to capture direct-reverberant ratio information corresponding to the views, and determines which view most closely matches a view of the person looking directly at the camera, thereby improving the experience for viewers at a second endpoint.
    Type: Grant
    Filed: June 30, 2017
    Date of Patent: October 2, 2018
    Assignee: Polycom, Inc.
    Inventors: Jinwei Feng, Peter Chu
  • Patent number: 9924252
    Abstract: A videoconferencing system has a plurality of displays arranged side-by-side. Top loudspeakers are arranged adjacent the tops of the displays, and bottom loudspeakers are arranged adjacent the bottoms of the displays. A control unit operatively coupled to the displays and the loudspeakers routes video to each of the displays and routes audio corresponding to each display to any of the top and bottom loudspeakers arranged adjacent the display. Thus, the top and bottom loudspeakers form a vertical pair of loudspeakers that output the corresponding audio for its respective display. In this way, the audio for the video of a given display is perceived by participants to originate from the center of the given display. If one of the loudspeakers is not provided, gain setting and mixing between adjacent sets of loudspeakers can produce a virtual loudspeaker for the one that is missing.
    Type: Grant
    Filed: March 7, 2014
    Date of Patent: March 20, 2018
    Assignee: Polycom, Inc.
    Inventors: Michael A. Pocino, Kwan K. Truong, Jinwei Feng, James M. Sharp
  • Publication number: 20180070053
    Abstract: A videoconferencing endpoint includes at least one processor a number of microphones and at least one camera. The endpoint can receive audio information and visual motion information during a teleconferencing session. The audio information includes one or more angles with respect to the microphone from a location of a teleconferencing session. The system evaluates the audio information is evaluated to determine at least one candidate angle corresponding to a possible location of an active talker. The candidate angle can be analyzed further with respect to the motion information to determine whether the candidate angle correctly corresponds to person who is speaking during the teleconferencing session. The person's face can then be framed within a frame view.
    Type: Application
    Filed: November 9, 2017
    Publication date: March 8, 2018
    Inventor: Jinwei Feng
  • Patent number: 9912908
    Abstract: A videoconferencing endpoint includes at least one processor a number of microphones and at least one camera. The endpoint can receive audio information and visual motion information during a teleconferencing session. The audio information includes one or more angles with respect to the microphone from a location of a teleconferencing session. The audio information is evaluated automatically to determine at least one candidate angle corresponding to a possible location of an active talker. The candidate angle can be analyzed further with respect to the motion information to determine whether the candidate angle correctly corresponds to person who is speaking during the teleconferencing session.
    Type: Grant
    Filed: December 5, 2016
    Date of Patent: March 6, 2018
    Assignee: Polycom, Inc.
    Inventor: Jinwei Feng
  • Patent number: 9723260
    Abstract: A videoconferencing apparatus automatically tracks speakers in a room and dynamically switches between a controlled, people-view camera and a fixed, room-view camera. When no one is speaking, the apparatus shows the room view to the far-end. When there is a dominant speaker in the room, the apparatus directs the people-view camera at the dominant speaker and switches from the room-view camera to the people-view camera. When there is a new speaker in the room, the apparatus switches to the room-view camera first, directs the people-view camera at the new speaker, and then switches to the people-view camera directed at the new speaker. When there are two near-end speakers engaged in a conversation, the apparatus tracks and zooms-in the people-view camera so that both speakers are in view.
    Type: Grant
    Filed: May 18, 2010
    Date of Patent: August 1, 2017
    Assignee: Polycom, Inc.
    Inventor: Jinwei Feng
  • Publication number: 20170085837
    Abstract: A videoconferencing endpoint includes at least one processor a number of microphones and at least one camera. The endpoint can receive audio information and visual motion information during a teleconferencing session. The audio information includes one or more angles with respect to the microphone from a location of a teleconferencing session. The audio information is evaluated automatically to determine at least one candidate angle corresponding to a possible location of an active talker. The candidate angle can be analyzed further with respect to the motion information to determine whether the candidate angle correctly corresponds to person who is speaking during the teleconferencing session.
    Type: Application
    Filed: December 5, 2016
    Publication date: March 23, 2017
    Inventor: Jinwei Feng
  • Patent number: 9542603
    Abstract: A videoconferencing endpoint includes at least one processor a number of microphones and at least one camera. The endpoint can receive audio information and visual motion information during a teleconferencing session. The audio information includes one or more angles with respect to the microphone from a location of a teleconferencing session. The audio information is evaluated automatically to determine at least one candidate angle corresponding to a possible location of an active talker. The candidate angle can be analyzed further with respect to the motion information to determine whether the candidate angle correctly corresponds to person who is speaking during the teleconferencing session.
    Type: Grant
    Filed: November 17, 2015
    Date of Patent: January 10, 2017
    Assignee: Polycom, Inc.
    Inventor: Jinwei Feng
  • Patent number: 9392221
    Abstract: A videoconferencing apparatus automatically tracks speakers in a room and dynamically switches between a controlled, people-view camera and a fixed, room-view camera. When no one is speaking, the apparatus shows the room view to the far-end. When there is a dominant speaker in the room, the apparatus directs the people-view camera at the dominant speaker and switches from the room-view camera to the people-view camera. When there is a new speaker in the room, the apparatus switches to the room-view camera first, directs the people-view camera at the new speaker, and then switches to the people-view camera directed at the new speaker. When there are two near-end speakers engaged in a conversation, the apparatus tracks and zooms-in the people-view camera so that both speakers are in view.
    Type: Grant
    Filed: March 5, 2013
    Date of Patent: July 12, 2016
    Assignee: Polycom, Inc.
    Inventors: Jinwei Feng, Peter Chu, Wayne Dunlap, Jonathan Gallmeier
  • Publication number: 20160140396
    Abstract: A videoconferencing endpoint includes at least one processor a number of microphones and at least one camera. The endpoint can receive audio information and visual motion information during a teleconferencing session. The audio information includes one or more angles with respect to the microphone from a location of a teleconferencing session. The audio information is evaluated automatically to determine at least one candidate angle corresponding to a possible location of an active talker. The candidate angle can be analyzed further with respect to the motion information to determine whether the candidate angle correctly corresponds to person who is speaking during the teleconferencing session.
    Type: Application
    Filed: November 17, 2015
    Publication date: May 19, 2016
    Inventor: Jinwei Feng
  • Patent number: 9282405
    Abstract: Methods and systems for cancellation of table noise in a speaker system used for video or audio conferencing are disclosed. Table noise is cancelled by using a vertical microphone array to distinguish the tilt angle of sound received by a microphone. If the sound is close to horizontal, the audio is muted. If the sound is above a given angle from horizontal, it is not muted, as this indicates a person speaking. This eliminates paper rustling, keyboard clicks and the like.
    Type: Grant
    Filed: April 17, 2013
    Date of Patent: March 8, 2016
    Assignee: Polycom, Inc.
    Inventors: Jinwei Feng, Peter L. Chu
  • Patent number: 9030520
    Abstract: In videoconference camera selection, audio inputs associated with cameras for a videoconference are each processed into first and second audio energies respectively for first and second frequency ranges. The selection then determines which of the audio inputs has a greatest ratio of the first audio energy to the second audio energy and selects the associated camera view for outputting video for the videoconference. The selection can also process video inputs from the cameras either alone or in combination with the audio processing. Either way, the selection processes each of the video inputs for at least one facial characteristic and determines which of the video inputs has a greatest likelihood of framing a human face. In the end, the selection selects the associated camera view for outputting video for the videoconference based at least in part on this video-based determination.
    Type: Grant
    Filed: June 20, 2011
    Date of Patent: May 12, 2015
    Assignee: Polycom, Inc.
    Inventors: Peter L. Chu, Jinwei Feng, Krishna Sai
  • Patent number: 8842161
    Abstract: A videoconference apparatus and method coordinates a stationary view obtained with a stationary camera to an adjustable view obtained with an adjustable camera. The stationary camera can be a web camera, while the adjustable camera can be a pan-tilt-zoom camera. As the stationary camera obtains video, faces of participants are detected, and a boundary in the view is determined to contain the detected faces. Absence and presences of motion associated with the detected face is used to verify whether a face is reliable. To then capture and output video of the participants for the videoconference, the view of the adjustable camera is adjusted to a framed view based on the determined boundary. In the end, active video captured in the framed view with the adjustable camera can be sent to a far-end for the videoconference.
    Type: Grant
    Filed: August 20, 2012
    Date of Patent: September 23, 2014
    Assignee: Polycom, Inc.
    Inventors: Jinwei Feng, Yibo Liu, Xiangdong Wang, Peter L. Chu