Motion from images: image matching, parameter estimation and intrinsic stability.

The authors first present an image-matching algorithm that uses multiple attributes associated with a pixel to yield a generally overdetermined system of constraints, taking into account possible structural discontinuities and occlusions. Both top-down and bottom-up data flows are used in a multiresolution computational structure. The matching algorithm computes dense displacement fields and the associated occlusion maps. The motion and structure parameters are estimated thorugh optimal estimation (e.g., maximal likelihood) using the solution of a linear algorithm as an initial guess. To investigate the intrinsic stability of the problem in the presence of noise, a theoretical lower bound on error variance of the estimates, the Cramer-Rao bound, is determined for motion parameters. Experiments showed that the performance of the proposed algorithm has essentially reached the bound. In addition, the bounds show that, intrinsically, motion estimation from two perspective views is a fairly stable problem if the image disparities are relatively large, but is unstable if the disparities are very small (as required by optical-flow approaches).