The computational measurement of apparent motion: a recurrent pattern recognition strategy as an approach to solve...

In short, the model consists of a two-dimensional set of edge detecting units, modelled according to the zero-crossing detectors introduced first by Marr and Ullman (1981). These detectors are located peripherally in our synthetic vision system and are the input elements for an intelligent recurrent network. The purpose of that network is to recognize and categorize the previously detected contrast changes in a multi-resolution representation of the original image in such a manner that the original information will be decomposed into a relatively small number N of well-defined edge primitives. The advantage of such a construction is that time-consuming pattern recognition has no longer to be done on the originally complex motion-blurred images of moving objects, but on a limited number of categorized forms. Based on a number M of elementary feature attributes for each individual edge primitive, the model is then able to decompose each edge pattern into certain features. In this way an M-dimensional vector can be constructed for each edge. For each sequence of two successive frames a tensor can be calculated containing the distances (measured in M-dimensional feature space) between all features in both images. This procedure yields a set of K-1 tensors for a sequence of K images. After cross-correlation of all N x M feature attributes from image (i) with those from image (i + 1), where i = 1,...,K-1, probability distributions can be computed. The final step is to search for maxima in these probability functions and then to construct from these extremes an optimal motion field. A number of simulation examples will be presented.