We have developed
a real-time software system for filtering live video content and then
adaptively streaming the video over resource limited networks or devices.
The rate adaptation is content-based and dynamically varied according
to the event structure and the video content. The system includes a content
analysis module for detecting important segments in the video, a variable-rate
encoding module, and a buffer management module for streaming the variable
rate video over low bandwidth networks. We have implemented a prototype
system, which performs real-time content detection and adaptation for
tennis and baseball with promising results.
S.-F. Chang, D. Zhong, and
R. Kumar, Real-Time
Content-Based Adaptive Streaming of Sports Video, IEEE Workshop on
Content-Based Access to Video/Image Library, Hawaii, Dec. 2001. Also in
Columbia University ADVENT Technical Report #121, July 2001. (PS.GZ/PDF)
D. Zhong and S.-F. Chang, Structure
Analysis of Sports Video Using Domain Models, IEEE Conference on Multimedia
and Exhibition, Tokyo, Japan, Aug. 22-25, 2001.
For problems or questions
regarding this web site contact The
Last updated: June 12, 2002.