We present a framework for real-time visual motion perception consisting of a novel analog VLSI optical flow sensor with reconfigurable pixels, connected in feedback with a controlling processor. The 2-D sensor array is composed of motion processing pixels that can be individually recruited to form dynamic ensembles that collectively compute visual motion. This flexible framework lends itself to the emulation of multi-layer recurrent network architectures for high-level processing of visual motion. In particular, attentional modulation can easily be incorporated in the visual motion processing. We show a simple example of visual tracking that demonstrates the potential of the framework.
reprint (pdf 244k)