Data and model driven foveation

Abstract

A general framework for multiresolution visual recognition is introduced. The input is processed simultaneously at a coarse resolution throughout the image and at finer resolution within a small window. A novel approach for controlling the movement of the high-resolution window is described which allows for the unification of a variety of data and model-driven behavioral paradigms. Three modes have been implemented, one based on large unexplained areas in the data, one on conflicts in the object-model database, and one on a 2-D space-filling algorithm. It is argued that this kind of multiresolution processing is not only useful in limiting the computational time, but can also be a deciding factor in making the entire vision problem a tractable and stable one. To demonstrate the approach, a class of 3-D surface textures is introduced as a feature for recognition in the system considered. Surface texture recognition typically requires higher-resolution processing than required for the extraction of the underlying surface. As an example, surface texture is used to discriminate between a ping-pong ball and a golf ball.