Role Of Active Vision In Scene Analysis And Representation

Visual perception is one of the most important sources of information for both humans and robots. A particular challenge is the acquisition and interpretation of complex unstructured scenes. This work contributes to active vision for humanoid robots. A semantic model of the scene is created, which is extended by successively changing the robot's view in order to explore interaction possibilities of the scene.

More than one third of the human brain is devoted to the processes of seeing - vision is after all the main way in which we gather information about the world. But human vision is a dynamic process during which the eyes continually sample the environment. Where most books on vision consider it as a passive activity, this book is unique in focusing on vision as an 'active' process. It goes beyond most accounts of vision where the focus is on seeing, to provide an integrated account of seeing AND looking. The book starts by pointing out the weaknesses in our traditional approaches to vision and the reason we need this new approach. It then gives a thorough description of basic details of the visual and oculomotor systems necessary to understand active vision. The book goes on to show how this approach can give a new perspective on visual attention, and how the approach has progressed in the areas of visual orienting, reading, visual search, scene perception and neuropsychology. Finally, the book summarises progress by showing how this approach sheds new light on the old problem of how we maintain perception of a stable visual world. Written by two leading vision scientists, this book will be valuable for vision researchers and psychology students, from undergraduate level upwards.

This book defines the emerging field of Active Perception which calls for studying perception coupled with action. It is devoted to technical problems related to the design and analysis of intelligent systems possessing perception such as the existing biological organisms and the "seeing" machines of the future. Since the appearance of the first technical results on active vision, researchers began to realize that perception -- and intelligence in general -- is not transcendental and disembodied. It is becoming clear that in the effort to build intelligent visual systems, consideration must be given to the fact that perception is intimately related to the physiology of the perceiver and the tasks that it performs. This viewpoint -- known as Purposive, Qualitative, or Animate Vision -- is the natural evolution of the principles of Active Vision. The seven chapters in this volume present various aspects of active perception, ranging from general principles and methodological matters to technical issues related to navigation, manipulation, recognition, learning, planning, reasoning, and topics related to the neurophysiology of intelligent systems.

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.

Cutting-edge research on the visual cognition of scenes, covering issues that include spatial vision, context, emotion, attention, memory, and neural mechanisms underlying scene representation. For many years, researchers have studied visual recognition with objects—single, clean, clear, and isolated objects, presented to subjects at the center of the screen. In our real environment, however, objects do not appear so neatly. Our visual world is a stimulating scenery mess; fragments, colors, occlusions, motions, eye movements, context, and distraction all affect perception. In this volume, pioneering researchers address the visual cognition of scenes from neuroimaging, psychology, modeling, electrophysiology, and computer vision perspectives. Building on past research—and accepting the challenge of applying what we have learned from the study of object recognition to the visual cognition of scenes—these leading scholars consider issues of spatial vision, context, rapid perception, emotion, attention, memory, and the neural mechanisms underlying scene representation. Taken together, their contributions offer a snapshot of our current knowledge of how we understand scenes and the visual world around us. Contributors Elissa M. Aminoff, Moshe Bar, Margaret Bradley, Daniel I. Brooks, Marvin M. Chun, Ritendra Datta, Russell A. Epstein, Michèle Fabre-Thorpe, Elena Fedorovskaya, Jack L. Gallant, Helene Intraub, Dhiraj Joshi, Kestutis Kveraga, Peter J. Lang, Jia Li Xin Lu, Jiebo Luo, Quang-Tuan Luong, George L. Malcolm, Shahin Nasr, Soojin Park, Mary C. Potter, Reza Rajimehr, Dean Sabatinelli, Philippe G. Schyns, David L. Sheinberg, Heida Maria Sigurdardottir, Dustin Stansbury, Simon Thorpe, Roger Tootell, James Z. Wang

T. Viéville: A Few Steps Towards 3D Active Vision appears as Vol. 33 in the Springer Series in Information Sciences. A specific problem in the field of active vision is analyzed, namely how suitable is it to explicitly use 3D visual cues in a reactive visual task? The author has collected a set of studies on this subject and has used these experimental and theoretical developments to propose a synthetic view on the problem, completed by some specific experiments. With this book scientists and graduate students will have a complete set of methods, algorithms, and experiments to introduce 3D visual cues in active visual perception mechanisms, e.g. autocalibration of visual sensors on robotic heads and mobile robots. Analogies with biological visual systems provide an easy introduction to this subject.

Computer Vision Systems is a collection of papers presented at the Workshop on Computer Vision Systems held at the University of Massachusetts in Amherst, Massachusetts, on June 1-3, 1977. Contributors discuss the breadth of problems that must be taken into account in the development of general computer vision systems. Topics covered include the application of system engineering techniques to the design of artificial intelligence systems; representation and segmentation of natural scenes; and pragmatic aspects of machine vision. Psychophysical measures of representation and interpretation are also considered. This monograph is divided into four sections: Issues and Research Strategies, Segmentation, Theory and Psychology, and Systems. The first chapter explores the problem of recovering the intrinsic characteristics of scenes from images, along with its implications for machine and human vision. The discussion then turns to special-purpose low-level vision systems that can be flexibly reconfigured as the need arises; design, development, and implementation of large systems from the human engineering point of view; and representation of visual information. The next section examines hierarchical relaxation for waveform parsing; the topology and semantics of intensity arrays; and visual images as spatial representations in active memory. The use of edge cues to recognize real-world objects is also analyzed. This text will be a useful resource for systems designers, computer engineers, and scientists as well as psychologists.