RIGID-BODY SEGMENTATION AND SHAPE-DESCRIPTION FROM DENSE OPTICAL-FLOWUNDER WEAK PERSPECTIVE

We present an algorithm for identifying and tracking independently mov ing rigid objects from optical flow. Some pervious attempts at segment ation via optical flow have focused on finding discontinuities in the flow field. While discontinuities do indicate a change in scene depth, they do not in general signal a boundary between two separate objects . The proposed method uses the fact that each independently moving obj ect has a unique epipolar constraint associated with its motion. Thus motion discontinuities based on self-occlusion can be distinguished fr om those due to separate objects. The use of epipolar geometry allows for the determination of individual motion parameters for each object as well as the recovery of relative depth for each point on the object . The algorithm assumes an affine camera where perspective effects are limited to changes in overall scale. No camera calibration parameters are required. A Kalman filter based approach is used for tracking mot ion parameters with time.