People Detection and Tracking in High Resolution Panoramic Video Mosaic

We have designed a physical awareness system called CAMEO, the Camera Assisted Meeting Event Observer, which consists of a multi-camera omnidirectional vision system designed to be used in meeting environments. CAMEO is designed to monitor the activities of people in meetings so that it can generate a sematically-indexed summary of what occured in the meeting. In this paper, we focus on CAMEO's fast people detection and tracking module. This module makes use a combination of frame differencing, face detection, and adaptive color blob tracking based on mean shift analysis to track the position of people in the panoramic image. We describe this algorithm and present experimental results from captured meeting logs