Modeling direction selective visual neural network with ON and OFF pathways for extracting motion cues from cluttered background

Abstract

The nature endows animals robust vision systems for extracting and recognizing different motion cues, detecting predators, chasing preys/mates in dynamic and cluttered environments. Direction selective neurons (DSNs), with preference to certain orientation visual stimulus, have been found in both vertebrates and invertebrates for decades. In this paper, with respect to recent biological research progress in motion-detecting circuitry, we propose a novel way to model DSNs for recognizing movements on four cardinal directions. It is based on an architecture of ON and OFF visual pathways underlies a theory of splitting motion signals into parallel channels, encoding brightness increments and decrements separately. To enhance the edge selectivity and speed response to moving objects, we put forth a bio-plausible spatial-temporal network structure with multiple connections of same polarity ON/OFF cells. Each pair-wised combination is filtered with dynamic delay depending on sampling distance. The proposed vision system was challenged against image streams from both synthetic and cluttered real physical scenarios. The results demonstrated three major contributions: first, the neural network fulfilled the characteristics of a postulated physiological map of conveying visual information through different neuropile layers; second, the DSNs model can extract useful directional motion cues from cluttered background robustly and timely, which hits at potential of quick implementation in vision-based micro mobile robots; moreover, it also represents better speed response compared to a state-of-the-art elementary motion detector.