A nonlinear correlation algorithm for estimating the motion of multiple objects in an image sequence

A nonlinear correlation algorithm is presented for estimating the motion of objects from a pair of images. The algorithm presented requires no a priori information on the number, size, or shape of the moving objects, and does not require feature extraction or segmentation of either image. The algorithm directly yields information on the number of moving objects, the motion of the objects, and the size of the objects. Additional processing to yield the centroid of the objects (in either frame) is also presented.