TY - CONF T1 - A hierarchical approach for obtaining structure from two-frame optical flow T2 - Motion and Video Computing, 2002. Proceedings. Workshop on Y1 - 2002 A1 - Liu,Haiying A1 - Chellapa, Rama A1 - Rosenfeld, A. KW - algorithm; KW - aliasing; KW - analysis; KW - computer-rendered KW - depth KW - depth; KW - error KW - estimation; KW - extraction; KW - Face KW - feature KW - flow; KW - gesture KW - hierarchical KW - image KW - images; KW - inverse KW - iterative KW - methods; KW - MOTION KW - nonlinear KW - optical KW - parameter KW - processing; KW - real KW - recognition; KW - sequences; KW - signal KW - structure-from-motion; KW - system; KW - systems; KW - TIME KW - two-frame KW - variation; KW - video AB - A hierarchical iterative algorithm is proposed for extracting structure from two-frame optical flow. The algorithm exploits two facts: one is that in many applications, such as face and gesture recognition, the depth variation of the visible surface of an object in a scene is small compared to the distance between the optical center and the object; the other is that the time aliasing problem is alleviated at the coarse level for any two-frame optical flow estimate so that the estimate tends to be more accurate. A hierarchical representation for the relationship between the optical flow, depth, and the motion parameters is derived, and the resulting non-linear system is iteratively solved through two linear subsystems. At the coarsest level, the surface of the object tends to be flat, so that the inverse depth tends to be a constant, which is used as the initial depth map. Inverse depth and motion parameters are estimated by the two linear subsystems at each level and the results are propagated to finer levels. Error analysis and experiments using both computer-rendered images and real images demonstrate the correctness and effectiveness of our algorithm. JA - Motion and Video Computing, 2002. Proceedings. Workshop on M3 - 10.1109/MOTION.2002.1182239 ER -