In the past, media capture and access suffered primarily from a lack of storage and bandwidth. Today networked, multimedia devices are ubiquitous, and the core challenge has less to do with how to transmit more information than with how to capture and communicate the right information. Our first application to explore intelligent media capture was NudgeCam, which supports guided capture to better document problems, discoveries, or other situations in the field. Today we introduce another intelligent capture application: mVideoCast. mVideoCast lets people communicate meaningful video content from mobile phones while semi-automatically removing extraneous details. Specifically, the application can detect, segment, and stream content shown on screens or boards, faces, or arbitrary, user-selected regions. This can allow anyone to stream task-specific content without needing to develop hooks into external software (e.g., screen recorder software).
Check out the video demonstration below and read the paper for more details.