The science associated with the development of artificial sen sory systems is occupied primarily with determining how information about the world can be extracted from sensory data. For example, computational vision is, for the most part, concerned with the de velopment of algorithms for distilling information about the world and recognition of various objects in the environ (e. g. localization ment) from visual images (e. g. photographs or video frames). There are often a multitude of ways in which a specific piece of informa tion about the world can be obtained from sensory data. A subarea of research into sensory systems has arisen which is concerned with methods for combining these various information sources. This field is known as data fusion, or sensor fusion. The literature on data fusion is extensive, indicating the intense interest in this topic, but is quite chaotic. There are no accepted approaches, save for a few special cases, and many of the best methods are ad hoc. This book represents our attempt at providing a mathematical foundation upon which data fusion algorithms can be constructed and analyzed. The methodology that we present in this text is mo tivated by a strong belief in the importance of constraints in sensory information processing systems. In our view, data fusion is best un derstood as the embedding of multiple constraints on the solution to a sensory information processing problem into the solution pro cess."

Information theory has proved to be effective for solving many computer vision and pattern recognition (CVPR) problems (such as image matching, clustering and segmentation, saliency detection, feature selection, optimal classifier design and many others). Nowadays, researchers are widely bringing information theory elements to the CVPR arena. Among these elements there are measures (entropy, mutual information...), principles (maximum entropy, minimax entropy...) and theories (rate distortion theory, method of types...).

This book explores and introduces the latter elements through an incremental complexity approach at the same time where CVPR problems are formulated and the most representative algorithms are presented. Interesting connections between information theory principles when applied to different problems are highlighted, seeking a comprehensive research roadmap. The result is a novel tool both for CVPR and machine learning researchers, and contributes to a cross-fertilization of both areas.

Information theory has proved to be effective for solving many computer vision and pattern recognition (CVPR) problems (such as image matching, clustering and segmentation, saliency detection, feature selection, optimal classifier design and many others). Nowadays, researchers are widely bringing information theory elements to the CVPR arena. Among these elements there are measures (entropy, mutual information...), principles (maximum entropy, minimax entropy...) and theories (rate distortion theory, method of types...). This book explores and introduces the latter elements through an incremental complexity approach at the same time where CVPR problems are formulated and the most representative algorithms are presented. Interesting connections between information theory principles when applied to different problems are highlighted, seeking a comprehensive research roadmap. The result is a novel tool both for CVPR and machine learning researchers, and contributes to a cross-fertilization of both areas.

Motion analysis is central to both human and machine vision. It involves the interpretation of image data over time and is crucial for a range of motion tasks suchasobstacledetection,depthestimation,videoanalysis,sceneinterpretation, videocompressionandotherapplications. Motionanalysisis unsolvedbecauseit requires modeling of the complicated relationships between the observed image data and the motion of objects and motion patterns (e. g. , falling rain) in the visual scene. The Dagstuhl Seminar 08291 on Statistical and Geometrical Approaches to Visual Motion Analysis was held during July 13-18, 2008 at the International Conference and Research Center (IBFI), Schloss Dagstuhl, near Wadern in G- many. The workshop focused on critical aspects of motion analysis, including motion segmentation, the modeling of motion patterns and the di?erent te- niques used. These techniques include variationalapproaches,level set methods, probabilistic models, graph cut approaches, factorization techniques, and neural networks. All these techniques can be subsumed within statistical and geomet- cal frameworks. We further involved experts in the study of human and primate vision. Primatevisualsystemsareextremely sophisticatedat processingmotion, thus there is much to be learnt from studying them. In particular, we discussed how to relate the computational models of primate visual systems to those - veloped for machine vision. In total, 15 papers were accepted for these proceedings after the workshop. We werecarefulto ensurea high standardof qualityfor the accepted papers. All submissions were double-blind reviewed by at least two experts.

This book constitutes the refereed proceedings of the 6th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition, EMMCVPR 2007, held in Ezhou, China in August 2007.

The 22 revised full papers and 15 poster papers presented were carefully reviewed and selected from 140 submissions. The papers are organized in topical sections on algorithms, applications, image parsing, image processing, motion, shape, and three-dimensional processing.

Active Vision explores important themes emerging from the active vision paradigm, which has only recently become an established area of machine vision. In four parts the contributions look in turn at tracking, control of vision heads, geometric and task planning, and architectures and applications, presenting research that marks a turning point for both the tasks and the processes of computer vision.The eighteen chapters in Active Vision draw on traditional work in computer vision over the last two decades, particularly in the use of concepts of geometrical modeling and optical flow; however, they also concentrate on relatively new areas such as control theory, recursive statistical filtering, and dynamical modeling.Active Vision documents a change in emphasis, one that is based on the premise that an observer (human or computer) may be able to understand a visual environment more effectively and efficiently if the sensor interacts with that environment, moving through and around it, culling information selectively, and analyzing visual sensory data purposefully in order to answer specific queries posed by the observer. This method is in marked contrast to the more conventional, passive approach to computer vision where the camera is supposed to take in the whole scene, attempting to make sense of all that it sees.Andrew Blake is Lecturer in Engineering Science at the University of Oxford Alan Yuille is Associate Professor in the Division of Applied Sciences at Harvard University.