In people tracking, one of the most challenging issues is occlusion handling. To cope with it, we introduce a Bayesian network which involves human 2D ellipse models and an extra hidden process for occlusion relation. The 2D ellipse model combines color and spatial information simultaneously by creating color histograms for serval sub-regions. The extra hidden process for occlusion indicates the depth information of people through occlusions. The tracking process is performed using a Condensation algorithm. Experiments show the effectiveness of the proposed method.