Using Motion from Orthographic Views to Verify 3-D Point Matches

Identifying the correspondences between points is an important task. It finds applications in computer vision, photogrammetry, and robotics. An effective approach is to use the rigidity constraint on the distances between points and the angles between lines joining the points. However, the rigidity constraint is unable to disambiguate the true match of a point from the false matches when the underlying isotropic error approximation breaks down. In this paper, we present a new method for solving the problem. The method is based on the technique of motion analysis using orthographic views. It discards the noisy z (depth) coordinate and uses only the x and y coordinates of the points to verify a match. The effect of depth errors on the motion estimate is completely prevented. Results show that this method is substantially more effective than previous methods that use all three coordinates.