Computational Visual Attention Models

The human visual system has evolved to have the ability to selectively focus on the most relevant parts of a visual scene. This mechanism, referred to as visual attention, has been the focus of several neurological and psychological studies in the past few decades. These studies have inspired several computational visual attention models which have been successfully applied to problems in computer vision and robotics. Computational Visual Attention Models provides a comprehensive survey of the state-of-the-art in computational visual attention modeling with a special focus on the latest trends. By reviewing several models published since 2012, the theoretical advantages and disadvantages of each approach are discussed. In addition, existing methodologies to evaluate computational models through the use of eye-tracking data along with the visual attention performance metrics used are described. The shortcomings in existing approaches and approaches to overcome them are also covered. Finally, a subjective evaluation for benchmarking existing visual attention metrics is presented and open problems in visual attention are highlighted. This monograph provides the reader with an in-depth survey of the research conducted to date in computational visual attention models and provides the basis for further research in this exciting area.

Visual attention is a relatively new area of study combining a number of disciplines: artificial neural networks, artificial intelligence, vision science and psychology. The aim is to build computational models similar to human vision in order to solve tough problems for many potential applications including object recognition, unmanned vehicle navigation, and image and video coding and processing. In this book, the authors provide an up to date and highly applied introduction to the topic of visual attention, aiding researchers in creating powerful computer vision systems. Areas covered include the significance of vision research, psychology and computer vision, existing computational visual attention models, and the authors' contributions on visual attention models, and applications in various image and video processing tasks. This book is geared for graduates students and researchers in neural networks, image processing, machine learning, computer vision, and other areas of biologically inspired model building and applications. The book can also be used by practicing engineers looking for techniques involving the application of image coding, video processing, machine vision and brain-like robots to real-world systems. Other students and researchers with interdisciplinary interests will also find this book appealing. Provides a key knowledge boost to developers of image processing applications Is unique in emphasizing the practical utility of attention mechanisms Includes a number of real-world examples that readers can implement in their own work: robot navigation and object selection image and video quality assessment image and video coding Provides codes for users to apply in practical attentional models and mechanisms

The derivation, exposition, and justification of the Selective Tuning model of vision and attention. Although William James declared in 1890, "Everyone knows what attention is," today there are many different and sometimes opposing views on the subject. This fragmented theoretical landscape may be because most of the theories and models of attention offer explanations in natural language or in a pictorial manner rather than providing a quantitative and unambiguous statement of the theory. They focus on the manifestations of attention instead of its rationale. In this book, John Tsotsos develops a formal model of visual attention with the goal of providing a theoretical explanation for why humans (and animals) must have the capacity to attend. He takes a unique approach to the theory, using the full breadth of the language of computation—rather than simply the language of mathematics—as the formal means of description. The result, the Selective Tuning model of vision and attention, explains attentive behavior in humans and provides a foundation for building computer systems that see with human-like characteristics. The overarching conclusion is that human vision is based on a general purpose processor that can be dynamically tuned to the task and the scene viewed on a moment-by-moment basis. Tsotsos offers a comprehensive, up-to-date overview of attention theories and models and a full description of the Selective Tuning model, confining the formal elements to two chapters and two appendixes. The text is accompanied by more than 100 illustrations in black and white and color; additional color illustrations and movies are available on the book's Web site.

This monograph presents a complete computational system for visual attention and object detection. VOCUS (Visual Object detection with a Computational attention System) represents a major step forward on integrating data-driven and model-driven information into a single framework. Additionally, the volume contains an extensive review of the literature on visual attention, detailed evaluations of VOCUS in different settings, and applications of the system.

Learn how to apply cognitive principles to the problems of computer vision Computational Models for Cognitive Vision formulates the computational models for the cognitive principles found in biological vision, and applies those models to computer vision tasks. Such principles include perceptual grouping, attention, visual quality and aesthetics, knowledge-based interpretation and learning, to name a few. The author’s ultimate goal is to provide a framework for creation of a machine vision system with the capability and versatility of the human vision. Written by Dr. Hiranmay Ghosh, the book takes readers through the basic principles and the computational models for cognitive vision, Bayesian reasoning for perception and cognition, and other related topics, before establishing the relationship of cognitive vision with the multi-disciplinary field broadly referred to as “artificial intelligence”. The principles are illustrated with diverse application examples in computer vision, such as computational photography, digital heritage and social robots. The author concludes with suggestions for future research and salient observations about the state of the field of cognitive vision. Other topics covered in the book include: · knowledge representation techniques · evolution of cognitive architectures · deep learning approaches for visual cognition Undergraduate students, graduate students, engineers, and researchers interested in cognitive vision will consider this an indispensable and practical resource in the development and study of computer vision.

This book constitutes the refereed proceedings of the Second International Workshop on Biologically Motivated Computer Vision, BMCV 2002, held in Tübingen, Germany, in November 2002. The 22 revised full papers and 37 revised short papers presented together with 6 invited papers were carefully reviewed and selected from 97 submissions. The papers are organized in topical sections on neurons and features, motion, mid-level vision, recognition - from scenes to neurons, attention, robotics, and cognitive vision.

The more than twenty contributions in this book, all new and previously unpublished, provide an up-to-date survey of contemporary research on computational modeling of the visual system. The approaches represented range from neurophysiology to psychophysics, and from retinal function to the analysis of visual cues to motion, color, texture, and depth. The contributions are linked thematically by a consistent consideration of the links between empirical data and computational models in the study of visual function. An introductory chapter by Edward Adelson and James Bergen gives a new and elegant formalization of the elements of early vision. Subsequent sections treat receptors and sampling, models of neural function, detection and discrimination, color and shading, motion and texture, and 3D shape. Each section is introduced by a brief topical review and summary. ContributorsEdward H. Adelson, Albert J. Ahumada, Jr., James R. Bergen, David G. Birch, David H. Brainard, Heinrich H. Bülthoff, Charles Chubb, Nancy J. Coletta, Michael D'Zmura, John P. Frisby, Norma Graham, Norberto M. Grzywacz, P. William Haake, Michael J. Hawken, David J. Heeger, Donald C. Hood, Elizabeth B. Johnston, Daniel Kersten, Michael S. Landy, Peter Lennie, J. Stephen Mansfield, J. Anthony Movshon, Jacob Nachmias, Andrew J. Parker, Denis G. Pelli, Stephen B. Pollard, R. Clay Reid, Robert Shapley, Carlo L. M. Tiana, Brian A. Wandell, Andrew B. Watson, David R. Williams, Hugh R. Wilson, Yuede. Yang, Alan L. Yuille

This book constitutes the thoroughly refereed post-proceedings of the Second International Workshop on Attention and Performance in Computational Vision, WAPCV 2004, held in Prague, Czech Republic in May 2004. The 16 revised full papers presented together with an invited paper were carefully selected during two rounds of reviewing and improvement. The papers are organized in topical sections on attention in object and scene recognition, architectures for sequential attention, biologically plausible models for attention, and applications of attentive vision.