Vision and Robotics Seminar
Department of Computer Science
Columbia University, NY
will speak on
Compact Video Summaries and Video Cross-Referencing
We present an approach for compact video summaries that allows fast and direct access to video data. We first segment a video into shots and inappropriate video genres into scenes. We use a memory-based buffer model of visual perception to model both shots and scenes transitions. A new concept that supports the hierarchical representation of video is presented, and is based on physical setting and camera locations. We use Mosaics to represent and cluster shots, and detect appropriate mosaics to represent scenes. In contrast to approaches to video indexing which are based on key-frames, our efficient mosaic-based scene representation allows fast clustering of scenes into physical settings, as well as further comparison of physical settings across videos. This enabled us to detect themes of different episodes in TV sitcoms and serves as a basis for indexing whole video sequences. In sports videos where settings are not as well defined, our approach allows classifying shots for characteristic events detection. We use a novel method for mosaic comparison and create a highly compact non-temporal representation of video.
This representation allows accurate comparison of scenes across different video data and serves as a basis for indexing video libraries.
The lecture will take place in the
Lecture Hall, Room 1, Ziskind Building
on Thursday, February 14, 2002