Fast spatiotemporal filters

Computing optical flow from a given sequence of images is computationally a very expensive task. Spatio-temporal filtering technique is one of the approaches to this task. This approach requires convolution of 3-D input with several 3-D Gabor filters. An efficient technique to compute the responses of Gabor filters by utilizing the functional characteristics of the filters is proposed. The technique significantly reduces the time complexity of computing the spatio-temporal responses. The pyramid structure of Gabor filters is discussed, and an implementation to generate the pyramid of filter responses is described. A VLSI pipelined architecture which effectively utilizes the characteristics of Gabor filters is proposed.<>