Top-Down Gaze Targeting for Space-Variant Active Vision

The simultaneous need for a wide angle of eld and high resolution has led to the use of spatially variant sensors in active vision systems. The use of such sensors however necessitates the existence of gaze control mechanisms for guiding the foveal high resolution region of the sensor to points of interest in the visual world. While bottom-up alerting cues such as motion have previously been used for this purpose, tasks such as visual search are better facilitated by top-down guidance mechanisms. In this paper, we describe the use of iconic scene descriptions for top-down foveal targeting. These descriptions take the form of a vector of responses of a bank of steerable lters at multiple scales and orientations. Such a representation has a number of useful properties such as rotation and scale invariance, partial view-insensitivity and tolerance to occlusions. Top-down control of gaze for uniform resolution sensors is achieved by the process of backpro-jection which matches vectors of a previously foveated point to instances of the point in other possibly transformed images. The multiscale structure of representation can be exploited to extend this procedure to the space-variant case.