This book on autonomous road-following vehicles brings together twenty years of innovation in the field. The book uniquely details an approach to real-time machine vision for the understanding of dynamic scenes, viewed from a moving platform that begins with spatio-temporal representations of motion for hypothesized objects whose parameters are adjusted by well-known prediction error feedback and recursive estimation techniques.

Motion processing is an essential piece of the complex brain machinery that allows us to reconstruct the 3D layout of objects in the environment, to break camouflage, to perform scene segmentation, to estimate the ego movement, and to control our action. Although motion perception and its neural basis have been a topic of intensive research and modeling the last two decades, recent experimental evidences have stressed the dynamical aspects of motion integration and segmentation. This book presents the most recent approaches that have changed our view of biological motion processing. These new experimental evidences call for new models emphasizing the collective dynamics of large population of neurons rather than the properties of separate individual filters. Chapters will stress how the dynamics of motion processing can be used as a general approach to understand the brain dynamics itself.

This Element examines visual perception in the context of activities that involve moving about in complex, dynamic environments. A central theme is that the ability of humans and other animals to perceive their surroundings based on vision is profoundly shaped by the need to adaptively regulate locomotion to variations in the environment. As such, important new insights into what and how we perceive can be gleaned by investigating the connection between vision and the control of locomotion. I present an integrated summary of decades of research on the perception of self-motion and object motion based on optic flow, the perception of spatial layout and affordances, and the control strategies for guiding locomotion based on visual information. I also explore important theoretical issues and debates, including the question of whether visual control relies on internal models.

Since the classic studies of Woodworth (1899), the role of vision in the control of movement has been an important research topic in experimental psychology. While many early studies were concerned with the relative importance of vision and kinesthesis and/or the time it takes to use visual information, recent theoretical and technical developments have stimulated scientists to ask questions about how different sources of visual information contribute to motor control in different contexts. In this volume, articles are presented that provide a broad coverage of the current research and theory on vision and human motor learning and control. Many of the contributors are colleagues that have met over the years at the meetings and conferences concerned with human movement. They represent a wide range of affiliation and background including kinesiology, physical education, neurophysiology, cognitive psychology and neuropsychology. Thus the topic of vision and motor control is addressed from a number of different perspectives. In general, each author sets an empirical and theoretical framework for their topic, and then discusses current work from their own laboratory, and how it fits into the larger context. A synthesis chapter at the end of the volume identifies commonalities in the work and suggests directions for future experimentation.

The distinguished contributors to this volume have been set the problem of describing how we know where to move our eyes. There is a great deal of current interest in the use of eye movement recordings to investigate various mental processes. The common theme is that variations in eye movements indicate variations in the processing of what is being perceived, whether in reading, driving or scene perception. However, a number of problems of interpretation are now emerging, and this edited volume sets out to address these problems. The book investigates controversies concerning the variations in eye movements associated with reading ability, concerning the extent to which text is used by the guidance mechanism while reading, concerning the relationship between eye movements and the control of other body movements, the relationship between what is inspected and what is perceived, and concerning the role of visual control attention in the acquisition of complex perceptual-motor skills, in addition to the nature of the guidance mechanism itself. The origins of the volume are in discussions held at a meeting of the European Society for Cognitive Psychology (ESCOP) that was held in Wurzburg in September 1996. The discussions concerned the landing effect in reading, an effect, that if substantiated, would provide evidence of the use of parafoveal information in eye guidance, and these discussions were explored in more detail at a small meeting in Chamonix, in February 1997. Many of the contributors to this volume were present at the meeting, but the arguments were not resolved in Chamonix either. Other leaders in the field were invited to contribute to the discussion, and this volume is the product. The argument remains unresolved, but the problem is certainly clearer.

Face recognition is a task that the human vision system seems to perform almost effortlessly, yet the goal of building computer-based systems with comparable capabilities has proven to be difficult. The task implicitly requires the ability to locate and track faces through often complex and dynamic scenes. Recognition is difficult because of variations in factors such as lighting conditions, viewpoint, body movement and facial expression. Although evidence from psychophysical and neurobiological experiments provides intriguing insights into how we might code and recognise faces, its bearings on computational and engineering solutions are far from clear. The study of face recognition has had an almost unique impact on computer vision and machine learning research at large. It raises many challenging issues and provides a good vehicle for examining some difficult problems in vision and learning. Many of the issues raised are relevant to object recognition in general.This book describes the latest models and algorithms that are capable of performing face recognition in a dynamic setting. The key question is how to design computer vision and machine learning algorithms that can operate robustly and quickly under poorly controlled and changing conditions. Consideration of face recognition as a problem in dynamic vision is perhaps both novel and important. The algorithms described have numerous potential applications in areas such as visual surveillance, verification, access control, video-conferencing, multimedia and visually mediated interaction.The book will be of special interest to researchers and academics involved in machine vision, visual recognition and machine learning. It should also be of interest to industrial research scientists and managers keen to exploit this emerging technology and develop automated face and human recognition systems. It is also useful to postgraduate students studying computer science, electronic engineering, information or systems engineering, and cognitive psychology.

The goal of this project was to develop analytical and computational tools to make vision a viable sensor for the purpose of control. In order for unmanned vehicles to interact with a complex, unknown, uncertain and dynamic environment, they must be able to sense its shape (geometry), its reflectance properties (photometry) and its motion relative to the platform, along with the motion of independently moving objects and targets within (dynamics).