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.

As the state-of-the-art imaging technologies became more and more advanced, yielding scientific data at unprecedented detail and volume, the need to process and interpret all the data has made image processing and computer vision increasingly important. Sources of data that have to be routinely dealt with today's applications include video transmission, wireless communication, automatic fingerprint processing, massive databanks, non-weary and accurate automatic airport screening, robust night vision, just to name a few. Multidisciplinary inputs from other disciplines such as physics, computational neuroscience, cognitive science, mathematics, and biology will have a fundamental impact in the progress of imaging and vision sciences. One of the advantages of the study of biological organisms is to devise very different type of computational paradigms by implementing a neural network with a high degree of local connectivity. This is a comprehensive and rigorous reference in the area of biologically motivated vision sensors. The study of biologically visual systems can be considered as a two way avenue. On the one hand, biological organisms can provide a source of inspiration for new computational efficient and robust vision models and on the other hand machine vision approaches can provide new insights for understanding biological visual systems. Along the different chapters, this book covers a wide range of topics from fundamental to more specialized topics, including visual analysis based on a computational level, hardware implementation, and the design of new more advanced vision sensors. The last two sections of the book provide an overview of a few representative applications and current state of the art of the research in this area. This makes it a valuable book for graduate, Master, PhD students and also researchers in the field.

It is our great pleasure and honor to organize the First IEEE Computer Society International Workshop on Biologically Motivated Computer Vision (BMCV 2000). The workshop BMCV 2000 aims to facilitate debates on biologically motivated vision systems and to provide an opportunity for researchers in the area of vision to see and share the latest developments in state-of-the-art technology. The rapid progress being made in the field of computer vision has had a tremendous impact on the modeling and implementation of biologically motivated computer vision. A multitude of new advances and findings in the domain of computer vision will be presented at this workshop. By December 1999 a total of 90 full papers had been submitted from 28 countries. To ensure the high quality of workshop and proceedings, the program committee selected and accepted 56 of them after a thorough review process. Of these papers 25 will be presented in 5 oral sessions and 31 in a poster session. The papers span a variety of topics in computer vision from computational theories to their implementation. In addition to these excellent presentations, there will be eight invited lectures by distinguished scientists on “hot” topics. We must add that the program committee and the reviewers did an excellent job within a tight schedule.

This book introduces neural mechanisms of biological vision and how artificial intelligence algorithms learn to interpret images.

It is our great pleasure and honor to organize the First IEEE Computer Society International Workshop on Biologically Motivated Computer Vision (BMCV 2000). The workshop BMCV 2000 aims to facilitate debates on biologically motivated vision systems and to provide an opportunity for researchers in the area of vision to see and share the latest developments in state-of-the-art technology. The rapid progress being made in the field of computer vision has had a tremendous impact on the modeling and implementation of biologically motivated computer vision. A multitude of new advances and findings in the domain of computer vision will be presented at this workshop. By December 1999 a total of 90 full papers had been submitted from 28 countries. To ensure the high quality of workshop and proceedings, the program committee selected and accepted 56 of them after a thorough review process. Of these papers 25 will be presented in 5 oral sessions and 31 in a poster session. The papers span a variety of topics in computer vision from computational theories to their implementation. In addition to these excellent presentations, there will be eight invited lectures by distinguished scientists on “hot” topics. We must add that the program committee and the reviewers did an excellent job within a tight schedule.

Under the title "Probabilistic and Biologically Inspired Feature Representations," this text collects a substantial amount of work on the topic of channel representations. Channel representations are a biologically motivated, wavelet-like approach to visual feature descriptors: they are local and compact, they form a computational framework, and the represented information can be reconstructed. The first property is shared with many histogram- and signature-based descriptors, the latter property with the related concept of population codes. In their unique combination of properties, channel representations become a visual Swiss army knife—they can be used for image enhancement, visual object tracking, as 2D and 3D descriptors, and for pose estimation. In the chapters of this text, the framework of channel representations will be introduced and its attributes will be elaborated, as well as further insight into its probabilistic modeling and algorithmic implementation will be given. Channel representations are a useful toolbox to represent visual information for machine learning, as they establish a generic way to compute popular descriptors such as HOG, SIFT, and SHOT. Even in an age of deep learning, they provide a good compromise between hand-designed descriptors and a-priori structureless feature spaces as seen in the layers of deep networks.

"This book examines modern artificial intelligence to display how it may be applied to computer games. It spans the divide that exists between the academic research community working with advanced artificial intelligence and the games programming community which must create and release new and interesting games, creating an invaluable collection supporting both technological research and the gaming industry"--Provided by publisher.

This book explains the theory and application of evolutionary computer vision, a new paradigm where challenging vision problems can be approached using the techniques of evolutionary computing. This methodology achieves excellent results for defining fitness functions and representations for problems by merging evolutionary computation with mathematical optimization to produce automatic creation of emerging visual behaviors. In the first part of the book the author surveys the literature in concise form, defines the relevant terminology, and offers historical and philosophical motivations for the key research problems in the field. For researchers from the computer vision community, he offers a simple introduction to the evolutionary computing paradigm. The second part of the book focuses on implementing evolutionary algorithms that solve given problems using working programs in the major fields of low-, intermediate- and high-level computer vision. This book will be of value to researchers, engineers, and students in the fields of computer vision, evolutionary computing, robotics, biologically inspired mechatronics, electronics engineering, control, and artificial intelligence.

Many approaches have been proposed to solve the problem of finding the optic flow field of an image sequence. Three major classes of optic flow computation techniques can discriminated (see for a good overview Beauchemin and Barron IBeauchemin19951): gradient based (or differential) methods; phase based (or frequency domain) methods; correlation based (or area) methods; feature point (or sparse data) tracking methods; In this chapter we compute the optic flow as a dense optic flow field with a multi scale differential method. The method, originally proposed by Florack and Nielsen [Florack1998a] is known as the Multiscale Optic Flow Constrain Equation (MOFCE). This is a scale space version of the well known computer vision implementation of the optic flow constraint equation, as originally proposed by Horn and Schunck [Horn1981]. This scale space variation, as usual, consists of the introduction of the aperture of the observation in the process. The application to stereo has been described by Maas et al. [Maas 1995a, Maas 1996a]. Of course, difficulties arise when structure emerges or disappears, such as with occlusion, cloud formation etc. Then knowledge is needed about the processes and objects involved. In this chapter we focus on the scale space approach to the local measurement of optic flow, as we may expect the visual front end to do. 17. 2 Motion detection with pairs of receptive fields As a biologically motivated start, we begin with discussing some neurophysiological findings in the visual system with respect to motion detection.

Biological systems are a source of inspiration in the development of small autonomous sensor nodes. The two major types of optical vision systems found in nature are the single aperture human eye and the compound eye of insects. The latter are among the most compact and smallest vision sensors. The eye is a compound of individual lenses with their own photoreceptor arrays. The visual system of insects allows them to fly with a limited intelligence and brain processing power. A CMOS image sensor replicating the perception of vision in insects is discussed and designed in this book for industrial (machine vision) and medical applications. The CMOS metal layer is used to create an embedded micro-polarizer able to sense polarization information. This polarization information is shown to be useful in applications like real time material classification and autonomous agent navigation. Further the sensor is equipped with in pixel analog and digital memories which allow variation of the dynamic range and in-pixel binarization in real time. The binary output of the pixel tries to replicate the flickering effect of the insect’s eye to detect smallest possible motion based on the change in state. An inbuilt counter counts the changes in states for each row to estimate the direction of the motion. The chip consists of an array of 128x128 pixels, it occupies an area of 5 x 4 mm2 and it has been designed and fabricated in an 180nm CMOS CIS process from UMC.