RETIMAC: REal-TIme Motion Analysis Chip

Motion estimation is relevant for applications of both motion-compensated image sequence processing and dynamic scene analysis of computer vision. Different approaches and solutions have been proposed for these two applicative fields. In some cases, parallel architectures and dedicated chips for motion estimation in real-time have been developed. In this paper, a low-cost REal-TIme Motion Analysis Chip, RETIMAC, is presented, which is suitable for dynamic scene analysis in computer vision applications. This chip is capable of estimating optical flow fields in real-time, and has been especially developed for project OFCOMP (Optical Flow for COunting Moving People) DTM 45 ESPRIT III MEPI. It can be profitably used also for autonomous navigation, tracking, surveillance, counting moving objects, measuring velocity, etc., and for several computer vision applications which require as a first processing step the estimation of the apparent velocity of each pixel in the image plane (e.g., optical flow, velocity field). RETIMAC implements a gradient-based solution which has been demonstrated to be more reliable and precise with respect to several solutions proposed in the literature.