Automatic video indexing with incremental gallery creation: integration of recognition and knowledge acquisition
Kazunori Okada, C. von der Malsburg · 2003
A framework for integrating the processes of object recognition and knowledge acquisition is proposed and applied to solve a task of automatic video indexing based on personal appearance events in a video stream. Spatiotemporal segmentation using multiple cues and example based adaptation of a known person gallery are combined in a prototype system which demonstrated successful results in our preliminary experiments.