Recovering a boundary-level structural description from dynamic stereo

We present a stereo algorithm to recursively compute a boundary-level structural description of a static scene, from a sequence of dynamic stereo images. This algorithm is based on connected line segments as the basic match primitive, which yields a description composed primarily of boundaries of objects in the scene. The algorithm is integrated into a dynamic stereo vision system to compute and incrementally refine such a structural description recursively, using belief measures. The approach is illustrated with a real dynamic stereo sequence.