Space-variant active vision: Definition, overview and examples

-The term space-variant vision was introduced in the late 1980s to refer to sensor architectures based on a smooth variation of resolution across the workspace, like that of the human visual system. The use of such sensor architectures is rapidly becoming an important factor in machine vision in which the constraints of size, weight, cost and performance must be jointly optimized. The structure of this paper consists of four parts. A review of the four genetic architectures for vision will be presented, providing a context for the term "active vision", and a justification for the importance, and the connection between, space-variant architectures and active vision methods. A brief quantitative review of the specific space-variant properties of primate visual cortex topography will be provided, in the context of sensor design. The engineering and algorithmic problems that are associated with exploiting space-variant systems will be stated. Examples of several recently constructed miniature space-variant active vision systems will be briefly reviewed, along with a brief discussion of solutions to the basic problem areas in space-variant vision. Keywords---Fovea, Space-variant, Active vision, Pyramid, Computer vision, Visual cortex. 1. I N T R O D U C T I O N The term space-variant vision was introduced in the late 1980s (Schwartz et al., 1988; Yeshurun & Schwartz, 1989) to refer to sensor architectures based on a smooth variation of resolution across the workspace, like that of the human visual system. An alternative term that is also in use is "foveating vision systems". Space-variant architecture shares many features, and some important differences, with the "pyramid architecture" that is more familiar in