Parallel algorithm for determining motion vectors in ice floe images by matching edge features

A parallel algorithm which is implemented on the massively parallel processor (MPP) for locating corresponding objects based on their translationally and rotationally invariant features is described. The algorithm first approximates the edges in the images by polygons or sets of connected straight-line segments. Each such edge structure is then reduced to a seed point. Associated with each seed point are the descriptions (lengths, orientations, and sequence numbers) of the lines constituting the corresponding edge structure. A parallel matching algorithm is used to match packed arrays of such descriptions to identify corresponding seed points in the two images. The matching algorithm is designed so that fragmentation and merging of ice floes are taken into account by accepting partial matches. The technique is shown to be successful on synthetic test patterns and real image pairs (SAR images of the Arctic Ocean from Seasat) in times ranging from 0.5 to 0.7 s for 128*128 images.<>