Detection and Tracking of Humans and Faces

We present a video analysis framework that integrates prior knowledge in object tracking to automatically detect humans and faces, and can be used to generate abstract representations of video (key-objects and object trajectories). The analysis framework is based on the fusion of external knowledge, incorporated in a person and in a face classifier, and low-level features, clustered using temporal and spatial segmentation. Lowlevel features, namely color and motion, are used as a reliability measure for the classification. The results of the classification are then integrated into a multi-target tracker based on a particle filter that uses color histograms and a zero–order motion model. The tracker uses efficient initialization and termination rules and updates the object model over time. We evaluate the proposed framework on standard datasets in terms of precision and accuracy of the detection and tracking results, and demonstrate the benefits of the integration of prior knowledge in the tracking process.