FOCUS OF EXPANSION ESTIMATION BY AN ERROR BACKPROPAGATION NEURAL-NETWORK

In this work we consider the application context of planar passive nav igation in which the visual control of locomotion requires only the di rection of transkation, and not the full set of motion parameters. If the temporally changing optic arrays is represented as a vector field of optical velocities, the vectors form a radial pattern emanating fro m a centre point, called the Focus of Expansion (FOE), representing th e heading direction. The FOE position is independent of the distances of world surfaces, and does nor require assumptions about surface shap e and smoothness. We investigate the performance of an artificial neur al network for the computation of the image position of the FOE of an Optical Flow (OF) field induced by an observer translation relative to a static environment. The network is characterized by a feed-forward architecture, and is trained by a standard supervised back-propagation algorithm which receives as input the pattern of points where the lin es generated by 2D vectors are projected using the Hough transform. We present results obtained on a test set of synthetic noise optical flo ws and on optical flows computed from real image sequences.