Abstract: Embodiments disclose systems and methods for transmitting user-extracted video and content more efficiently by recognizing that user-extracted video provides the potential to treat parts of a single frame of a user-extracted video differently. An alpha mask of the image part of the user-extracted video is used when encoding the image part so that it retains a higher quality upon transmission than the remainder of the user-extracted video.
Type:
Application
Filed:
December 31, 2013
Publication date:
July 2, 2015
Applicant:
Personify, Inc.
Inventors:
Quang Nguyen, Minh Do, Long Truong, Dennis Lin, Sumant Kowshik, Sanjay Patel
Abstract: Embodiments disclose extracting a user persona from a video of arbitrary duration and associating that persona with text for a chat session. Embodiments cause the persona to be extracted at the moment text is sent or received to convey the body language associated with the text.
Type:
Application
Filed:
December 18, 2013
Publication date:
June 18, 2015
Applicant:
Personify, Inc.
Inventors:
Dennis Lin, Sumant Kowshik, Sanjay Patel
Abstract: A color image and a depth image of a live video are received. A user is extracted from the information of the color image and the depth image. Spurious depth vales may be corrected. Points or pixels of an image as seen from a viewpoint of a reference camera at a reference camera location are mapped to points of the image as would be seen from a viewpoint of a virtual camera at a virtual camera location. As such, a transformed color image is generated. Disoccluded pixels may be processed to address any gaps within the transformed color image.
Type:
Grant
Filed:
April 29, 2011
Date of Patent:
June 9, 2015
Assignee:
PERSONIFY, INC.
Inventors:
Dennis Lin, Quang H. Nguyen, Minh N. Do, Sanjay J. Patel
Abstract: A system and method is disclosed for extracting a user persona from a video and embedding that persona into a background feed that may have other content, such as text, graphics, or additional video content. The extracted video and background feed are combined to create a composite video that comprises the display in a videoconference. Embodiments cause the user persona to be embedded at preset positions, or in preset formats, or both, depending on the configuration, position, or motion of the user's body.
Type:
Grant
Filed:
July 23, 2013
Date of Patent:
June 9, 2015
Assignee:
PERSONIFY, INC
Inventors:
Dennis Lin, David Scherba, Mert Dikmen, Sumant Kowshik, Sanjay Patel
Abstract: A system and method is disclosed for extracting a user persona from a video and embedding that persona into a background feed that may have other content, such as text, graphics, or additional video content. The extracted video and background feed are combined to create a composite video that comprises the display in a videoconference. Embodiments cause the user persona to be embedded at preset positions, or in preset formats, or both, depending on the configuration, position, or motion of the user's body.
Type:
Application
Filed:
July 23, 2013
Publication date:
January 29, 2015
Applicant:
Personify, Inc.
Inventors:
Dennis Lin, David Scherba, Mert Dikmen, Sumant Kowshik, Sanjay Patel
Abstract: A color image and a depth image of a live video are received. Each of the color image and the depth image are processed to identify a foreground, background, and an unknown region band of the live video. The unknown region band may comprise pixels between the foreground and the background. Further processing is performed to segment the pixels of the unknown region band between the foreground and the background. As such, processing is performed on the unknown region band in order to provide an improved user foreground video.
Type:
Grant
Filed:
April 8, 2011
Date of Patent:
August 26, 2014
Assignee:
Personify, Inc.
Inventors:
Quang H. Nguyen, Greg Meyer, Minh N. Do, Dennis Lin, Sanjay J. Patel