PASSIVE NAVIGATION AS A PATTERN-RECOGNITION PROBLEM

The most basic visual capabilities found in living organisms are based on motion. Machine vision, of course, does not have to copy animal vi sion, but the existence of reliably functioning vision modules in natu re gives us some reason to believe that it is possible for an artifici al system to work in the same or a similar way. In this article it is argued that many navigational capabilities can be formulated as patter n recognition problems. An appropriate retinotopic representation of t he image would make it possible to extract the information necessary t o solve motion-related tasks through the recognition of a set of locat ions on the retina. This argument is illustrated by introducing a repr esentation of image motion by which an observer's egomotion could be d erived from information globally encoded in the image-motion field. In the past, the problem of determining a system's own motion from dynam ic imagery has been considered as one of the classical visual reconstr uction problems, wherein local constraints have been employed to compu te from exact 2-D image measurements (correspondence, optical flow) th e relative 3-D motion and structure of the scene in view. The approach introduced here is based on new global constraints defined on local n ormal-flow measurements-the spatio-temporal derivatives of the image-i ntensity function. Classifications are based on orientations of normal -flow vectors, which allows selection of vectors that form global patt erns in the image plane. The position of these patterns is related to the 3-D motion of the observer, and their localization provides the ax is of rotation and the direction of translation. The constraints intro duced are utilized in algorithmic procedures formulated as search tech niques. These procedures are very stable, since they are not affected by small perturbations in the image measurements. As a matter of fact, the solution to the two directions of translation and rotation is not affected, as long as the measurement of the sign of the normal flow i s correct.