ESTIMATING OPTICAL-FLOW WITH CELLULAR NEURAL NETWORKS

The cellular neural network is a locally interconnected neural network capable of high-speed computation when implemented in analog VLSI. Th is work describes a CNN algorithm for estimating the optical flow from an image sequence. The algorithm is based on the spatio-temporal filt ering approach to image motion analysis and is shown to estimate the o ptical how more accurately than a comparable approach proposed previou sly. Two innovative features of the algorithm are the exploitation of a biological model for hyperacuity and the development of a new class of spatio-temporal filter better suited for image motion analysis than the commonly used space-time Gabor filter. (C) 1998 John Wiley & Sons , Ltd.