IEEE International Workshop on Performance Evaluation of Tracking and Surveillance In conjunction with ECCV'04. Automatic Tracking and Labeling of Human Activities in a Video Sequence

This paper presents a novel approach for tracking multiple objects and a statistical learning approach for detection of human activities in a video sequence. For the tracking, a � rigid transformation invariant appearance model combining color and edge information of the detected blob is proposed. For the activity detection, each activity label is regarded as a hypothesis. Given some labeled sequences, a group of features are first extracted from motion trajectories of each detected object and the likelihood of each feature under that hypothesis is calculated. A dynamic programming-based training algorithm is applied to get an optimal classifier for each feature. Then it selects the classifiers with the most discriminative power and combines them t