Exploratory Vision: The Active Eye (Springer Series in Perception Engineering)

Advances in sensing, signal processing, and computer technology during the past half century have stimulated numerous attempts to design general-purpose ma­ chines that see. These attempts have met with at best modest success and more typically outright failure. The difficulties encountered in building working com­ puter vision systems based on state-of-the-art techniques came as a surprise. Perhaps the most frustrating aspect of the problem is that machine vision sys­ tems cannot deal with numerous visual tasks that humans perform rapidly and effortlessly. In reaction to this perceived discrepancy in performance, various researchers (notably Marr, 1982) suggested that the design of machine-vision systems should be based on principles drawn from the study of biological systems. This "neuro­ morphic" or "anthropomorphic" approach has proven fruitful: the use of pyramid (multiresolution) image representation methods in image compression is one ex­ ample of a successful application based on principles primarily derived from the study of biological vision systems. It is still the case, however, that the perfor­ of computer vision systems falls far short of that of the natural systems mance they are intended to mimic, suggesting that it is time to look even more closely at the remaining differences between artificial and biological vision systems. Advances in sensing, signal processing, and computer technology during the past half century have stimulated numerous attempts to design general-purpose maƯ chines that see. These attempts have met with at best modest success and more typically outright failure. The difficulties encountered in building working comƯ puter vision systems based on state-of-the-art techniques came as a surprise. Perhaps the most frustrating aspect of the problem is that machine vision sysƯ tems cannot deal with numerous visual tasks that humans perform rapidly and effortlessly. In reaction to this perceived discrepancy in performance, various researchers (notably Marr, 1982) suggested that the design of machine-vision systems should be based on principles drawn from the study of biological systems. This "neuroƯ morphic" or "anthropomorphic" approach has proven fruitful: the use of pyramid (multiresolution) image representation methods in image compression is one exƯ ample of a successful application based on principles primarily derived from the study of biological vision systems. It is still the case, however, that the perforƯ of computer vision systems falls far short of that of the natural systems mance they are intended to mimic, suggesting that it is time to look even more closely at the remaining differences between artificial and biological vision systems Front Matter....Pages i-xviii Front Matter....Pages 1-1 Moveo Ergo Video: Natural Retinal Image Motion and its Effect on Vision....Pages 3-49 Cogito Ergo Moveo: Cognitive Control of Eye Movement....Pages 51-77 Front Matter....Pages 79-79 Robust Computational Vision....Pages 81-99 Eye Movements and the Complexity of Visual Processing....Pages 101-120 Exploratory Vision: Some Implications for Retinal Sampling and Reconstruction....Pages 121-156 Calibration of a Visual System with Receptor Drop-out....Pages 157-168 Peripheral Visual Field, Fixation and Direction of Heading....Pages 169-189 Local Qualitative Shape from Active Shading....Pages 191-202 Front Matter....Pages 203-203 The Synthesis of Vision and Action....Pages 205-240 A Framework for Information Assimilation....Pages 241-256 Task-Oriented Vision....Pages 257-277 Front Matter....Pages 279-279 Active Vision and Virtual Reality....Pages 281-318 A Novel Environment for Situated Vision and Behavior....Pages 319-331 Back Matter....Pages 333-344

This book is a dialogue between researchers who study biological visual and computer scientists and engineers who seek to build computer vision systems that actively explore the environment. By describing new and important ways to design robots analogous to biological visual systems, it provides deep insights into the problems and solutions of computer vision. The book is divided into four parts, each addressing a different aspect of exploratory or active vision in biological and machine vision systems. The chapters are written by a cross-disciplinary selection of leading researchers who study computer and biological vision. As a result, many researchers and students concerned with vision will find this an invaluable survey to this fast-moving field.