Tracking People in Presence of Occlusion

Tracking humans is a diicult problem because of the non-rigid nature of the human body, and the frequent occlusion encountered among people. We present a framework to track multiple people in a xed camera situation. Our framework deals implicitly with occlusion, and is able to correctly label people during occlusion. We rst segment a person into classes of similar color using the Expectation Maximization algorithm. Then we use a maximum a posteriori probability approach to track these classes from frame to frame. The system deals well with partial and complete occlusion. Results are presented for an indoor sequence in an ooce environment.