SPACE-VARIANT ACTIVE VISION - DEFINITION, OVERVIEW AND EXAMPLES

The term space-variant vision was introduced in the late 1980s to refe r to sensor architectures based on a smooth variation of resolution ac ross the workspace, like that of the human visual system. The use of s uch sensor architectures is rapidly becoming an important factor in ma chine vision in which the constraints of size, weight, cost and perfor mance must be jointly optimized. The structure of this paper consists of four parts. A review of the four generic architectures for vision w ill be presented, providing a context for the term ''active vision'', and a justification for the importance, and the connection between, sp ace-variant architectures and active vision methods. A brief quantitat ive review of the specific space-variant properties of primate visual cortex topography will be provided, in the context of sensor design. T he engineering and algorithmic problems that are associated with explo iting space-variant systems will be stated. Examples of several recent ly constructed miniature space-variant active vision systems will be b riefly reviewed, along with a brief discussion of solutions to the bas ic problem areas in space-variant vision.