Understanding 3-dimensional dynamic environment fusing multiple images by mixed-state condensation algorithm

In this paper, we propose an efficient method for tracking multiple objects, which deals with occlusion situations in an image. We use the shape from silhouettes method to reconstruct objects 3D position using images taken from different directions. Then we track the objects' reconstructed 3D positions by using the mixed-state condensation algorithm. The experimental results show the tracking of multiple objects robustly.