People Re-identification across a Camera Network People Re-identification across a Camera Network

The growth of computational capabilities together with the emergence of vision techniques have opened new opportunities for the development of new approaches for video-surveillance systems (people detection, tracking and recognition...). The current work addresses the issue of visual real-time people tracking within a multi-camera network. We studied three different techniques for visual signature and characterization of people: local descriptors such as SIFT points, color based descriptors, and a bayesian approach for image patch recognition.