MULTIPLE REGION VIDEO CONFERENCE ENCODING

摘要

Systems and method may provide for a computing device that encodes multiple regions of a video frame at different quality levels. In particular, a first region of one or more frames containing a speaker's face maybe located and encoded at a first quality level. A second region containing a background, on the other hand, may be located and encoded at a second quality level. Optionally a third region containing additional faces maybe located and encoded at a third quality level and a fourth region maybe located and encoded at a fourth quality level.