An algorithm for computing three-dimensional (3-D) velocity field and motion parameters from a range image sequence is presented. It is based on a new integral 3-D rigid motion invariant feature-the trace of a 3x3 "feature matrix" related to the moment of inertia tensor. This trace can be computed at every point of a moving surface and provides a quantitative measure of the local shape of the surface. Based on the feature's conservation along the trajectory of every moving point, a 3-D Flow Constraint Equation is formulated and solved for the velocity field. The robustness of the feature in presence of noise and discontinuity is analyzed.

The conventional Gabor transforms, complete and generalized, cannot be applied for image matrices received as different partitions. In practice, very large images are received in the form of submatrix partitions. Then, taking transform on different partitions (of the same image) at different times is of prime importance. The situation can be easily handled if the transformation algorithm is made recursive. The authors present a recursive Gabor transform (RGT) amenable for pipelining partitions of different images interleaved. Apriori knowledge of image size is not required for the RGT unlike the conventional Gabor Transform. A dedicated massively parallel architecture based on Pacube VLSI arrays is presented which achieves a high degree of pipelining with respect to different image matrices. The pipelining rate is proportional to the delay of a Pacube macrocell in mode 1 operation.

An algorithm for computing 3D motion (velocity field and motion parameters) from a sequence of range images is presented. The algorithm is based on a new integral 3D rigid motion invariant feature which can be computed locally at every point of the moving surface. This feature is the trace of a 3/spl times/3 matrix (referred to as "feature matrix" in the paper) which is closely related to the moment of inertia tenser in physics. This trace of the "feature matrix" at any point provides a quantitative measure of the local shape of the surface around that point. Since the trace feature is rigid motion invariant, it remains conserved along the trajectory of every moving point. Based on that, a 3D flow constraint equation is formulated at every point on the surface, which can be solved for the velocity at the point using optical flow techniques. Since the proposed feature is integral in nature, it is robust in terms of noise and discontinuity in the moving surface. Theoretical analysis is provided to justify these claims. Experimental results are also provided to justify the efficacy of the method.>