Parametric estimation of optical flow from two perspective views

Since the detection of optical flow (two-dimensional motion field on an ima ge) from image sequences is essentially an ill-posed problem, most of the c onventional methods use a smoothness constraint for optical how heuristical ly and detect reasonable optical flow. However, little discussion exists re garding the degree of smoothness. Furthermore, to recover the relative thre e-dimensional motion and depth between a camera and a rigid object, in gene ral at first, the optical flow is detected without a rigid motion constrain t, and next, the motion and depth are: estimated using the detected optical flow. Rigorously speaking, the optical how should be detected with such a constraint, and consequently three-dimensional motion and depth should be d etermined. To solve these problems, in this paper, we apply a parametric mo del to an optical flow, and construct an estimation algorithm based on this model.