Traditionally, scientific fields have defined boundaries, and scientists work on research problems within those boundaries. However, from time to time those boundaries get shifted or blurred to evolve new fields. For instance, the original goal of computer vision was to understand a single image of a scene, by identifying objects, their structure, and spatial arrangements. This has been referred to as image understanding. Recently, computer vision has gradually been making the transition away from understanding single images to analyz ing image sequences, or video understanding. Video understanding deals with understanding of video sequences, e. g. , recognition of gestures, activities, fa cial expressions, etc. The main shift in the classic paradigm has been from the recognition of static objects in the scene to motion-based recognition of actions and events. Video understanding has overlapping research problems with other fields, therefore blurring the fixed boundaries. Computer graphics, image processing, and video databases have obvious overlap with computer vision. The main goal of computer graphics is to gener ate and animate realistic looking images, and videos. Researchers in computer graphics are increasingly employing techniques from computer vision to gener ate the synthetic imagery. A good example of this is image-based rendering and modeling techniques, in which geometry, appearance, and lighting is de rived from real images using computer vision techniques. Here the shift is from synthesis to analysis followed by synthesis.

Nonholonomic Motion Planning grew out of the workshop that took place at the 1991 IEEE International Conference on Robotics and Automation. It consists of contributed chapters representing new developments in this area. Contributors to the book include robotics engineers, nonlinear control experts, differential geometers and applied mathematicians. Nonholonomic Motion Planning is arranged into three chapter groups: Controllability: one of the key mathematical tools needed to study nonholonomic motion. Motion Planning for Mobile Robots: in this section the papers are focused on problems with nonholonomic velocity constraints as well as constraints on the generalized coordinates. Falling Cats, Space Robots and Gauge Theory: there are numerous connections to be made between symplectic geometry techniques for the study of holonomies in mechanics, gauge theory and control. In this section these connections are discussed using the backdrop of examples drawn from space robots and falling cats reorienting themselves. Nonholonomic Motion Planning can be used either as a reference for researchers working in the areas of robotics, nonlinear control and differential geometry, or as a textbook for a graduate level robotics or nonlinear control course.

Data visualization is currently a very active and vital area of research, teaching and development. The term unites the established field of scientific visualization and the more recent field of information visualization. The success of data visualization is due to the soundness of the basic idea behind it: the use of computer-generated images to gain insight and knowledge from data and its inherent patterns and relationships. A second premise is the utilization of the broad bandwidth of the human sensory system in steering and interpreting complex processes, and simulations involving data sets from diverse scientific disciplines and large collections of abstract data from many sources.
These concepts are extremely important and have a profound and widespread impact on the methodology of computational science and engineering, as well as on management and administration. The interplay between various application areas and their specific problem solving visualization techniques is emphasized in this book. Reflecting the heterogeneous structure of Data Visualization, emphasis was placed on these topics:

-Visualization Algorithms and Techniques;
-Volume Visualization;
-Information Visualization;
-Multiresolution Techniques;
-Interactive Data Exploration.

Data Visualization: The State of the Art" "presents the state of the art in scientific and information visualization techniques by experts in this field. It can serve as an overview for the inquiring scientist, and as a basic foundation for developers. This edited volume contains chapters dedicated to surveys of specific topics, and a great deal of original work not previously published illustrated by examples from a wealth of applications. The book will also provide basic material for teaching the state of the art techniques in data visualization.

Data Visualization: The State of the Art is designed to meet the needs of practitioners and researchers in scientific and information visualization. This book is also suitable as a secondary text for graduate level students in computer science and engineering.

Multimedia Mining: A Highway to Intelligent Multimedia Documents brings together experts in digital media content analysis, state-of-art data mining and knowledge discovery in multimedia database systems, knowledge engineers and domain experts from diverse applied disciplines. Multimedia documents are ubiquitous and often required, if not essential, in many applications today. This phenomenon has made multimedia documents widespread and extremely large. There are tools for managing and searching within these collections, but the need for tools to extract hidden useful knowledge embedded within multimedia objects is becoming pressing and central for many decision-making applications. The tools needed today are tools for discovering relationships between objects or segments within multimedia document components, such as classifying images based on their content, extracting patterns in sound, categorizing speech and music, and recognizing and tracking objects in video streams.

One of the most intriguing questions in image processing is the problem of recovering the desired or perfect image from a degraded version. In many instances one has the feeling that the degradations in the image are such that relevant information is close to being recognizable, if only the image could be sharpened just a little. This monograph discusses the two essential steps by which this can be achieved, namely the topics of image identification and restoration. More specifically the goal of image identifi cation is to estimate the properties of the imperfect imaging system (blur) from the observed degraded image, together with some (statistical) char acteristics of the noise and the original (uncorrupted) image. On the basis of these properties the image restoration process computes an estimate of the original image. Although there are many textbooks addressing the image identification and restoration problem in a general image processing setting, there are hardly any texts which give an indepth treatment of the state-of-the-art in this field. This monograph discusses iterative procedures for identifying and restoring images which have been degraded by a linear spatially invari ant blur and additive white observation noise. As opposed to non-iterative methods, iterative schemes are able to solve the image restoration problem when formulated as a constrained and spatially variant optimization prob In this way restoration results can be obtained which outperform the lem. results of conventional restoration filters."

Mathematical morphology (MM) is a theory for the analysis of spatial structures. It is called morphology since it aims at analysing the shape and form of objects, and it is mathematical in the sense that the analysis is based on set theory, topology, lattice algebra, random functions, etc. MM is not only a theory, but also a powerful image analysis technique. The purpose of the present book is to provide the image analysis community with a snapshot of current theoretical and applied developments of MM. The book consists of forty-five contributions classified by subject. It demonstrates a wide range of topics suited to the morphological approach.

This book constitutes the refereed proceedings of the 5th International Workshop on Motion in Games, held in Rennes, France, in November 2012. The 23 revised full papers presented together with 9 posters and 5 extended abstracts were carefully reviewed and selected from numerous submissions. The papers are organized in topical sections on planning, interaction, physics, perception, behavior, virtual humans, locomotion, and motion capture.

Vision chips, or smart visual sensors, are those sensors that have integrated image acquisition and parallel processing, often at the pixel level, using dedicated analog and digital circuits. Vision Chips presents a systematic approach to the design and analysis of vision chips using analog VLSL. * It presents algorithmic level implementation issues, from both the VLSI and computer vision points of view. * It reviews the VLSI technologies and general analog VLSI design methodologies, in the context of suitability for vision chips. * It describes chip-level architectural issues, including tessellation structures, pixel-processor interaction, and data read-out. * It presents detailed analysis of building-blocks necessary in vision chips, including photodetectors, photocircuits, and spatial and temporal processing circuits. * It addresses other important design issues, such as testing, digital noise, and mismatch. In addition Vision Chips reviews some of the past and existing implementations of smart vision sensors. It contains condensed information on more than fifty vision chips, designed by research laboratories all over the world.Novel and interesting features of each vision chip have been highlighted through informative diagrams and concise descriptions. This book is a valuable asset for researchers in the area, engineers working on the design of vision sensors, graduate students working in analog VLSI and vision, and computer vision and biological vision researchers and scientists.

Physics-Based Deformable Models presents a systematic physics-based framework for modeling rigid, articulated, and deformable objects, their interactions with the physical world, and the estimate of their shape and motion from visual data. This book presents a large variety of methods and associated experiments in computer vision, graphics and medical imaging that help the reader better to understand the presented material. In addition, special emphasis has been given to the development of techniques with interactive or close to real-time performance. Physics-Based Deformable Models is suitable as a secondary text for graduate level courses in Computer Graphics, Computational Physics, Computer Vision, Medical Imaging, and Biomedical Engineering. In addition, this book is appropriate as a reference for researchers and practitioners in the above-mentioned fields.

Proceedings of the Fifth International School on Neural Networks "E.R. Caianiello" on Visual Attention MechaProceedings of the Fifth International School on Neural Networks "E.R. Caianiello" on Visual Attention Mechanisms, held 23-28 October 2000 in Vietri sul Mare, Italy.nisms, held 23-28 October 2000 in Vietri sul Mare, Italy. The book covers a number of broad themes relevant to visual attention, ranging from computer vision to psychology and physiology of vision. The main theme of the book is the attention processes of vision systems and it aims to point out the analogies and the divergences of biological vision with the frameworks introduced by computer scientists in artificial vision.

The material of this book encompasses many disciplines, including visible,

infrared, far infrared, millimeter wave, microwave, radar, synthetic aperture radar, and

electro-optical sensors as well as the very dynamic topics of image processing, computer

vision and pattern recognition.

This book is composed of six parts:

* Advanced background modeling for surveillance

* Advances in Tracking in Infrared imagery

* Methods for Pose estimation in Ultrasound and LWIR imagery

* Recognition in multi-spectral and synthetic aperture radar

* Fusion of disparate sensors

* Smart Sensors

This book presents theories and techniques for perception of textures by computer. Texture is a homogeneous visual pattern that we perceive in surfaces of objects such as textiles, tree barks or stones. Texture analysis is one of the first important steps in computer vision since texture provides important cues to recognize real-world objects. A major part of the book is devoted to two-dimensional analysis of texture patterns by extracting statistical and structural features. It also deals with the shape-from-texture problem which addresses recovery of the three-dimensional surface shapes based on the geometry of projection of the surface texture to the image plane. Perception is still largely mysterious. Realizing a computer vision system that can work in the real world requires more research and ex periment. Capability of textural perception is a key component. We hope this book will contribute to the advancement of computer vision toward robust, useful systems. vVe would like to express our appreciation to Professor Takeo Kanade at Carnegie Mellon University for his encouragement and help in writing this book; to the members of Computer Vision Section at Electrotechni cal Laboratory for providing an excellent research environment; and to Carl W. Harris at Kluwer Academic Publishers for his help in preparing the manuscript."

The two volumes set LNCS 7653 and 7654 constitutes the refereed proceedings of the 4th International Conference on Computational Collective Intelligence, ICCCI, held in Ho Chi Minh City, Vietnam, in November 2012.

The 113 revised full papers presented were carefully reviewed and selected from 397 submissions. The papers are organized in topical sections on (Part I) knowledge integration; data mining for collective processing; fuzzy, modal, and collective systems; nature inspired systems; language processing systems; social networks and semantic web; agent and multi-agent systems; classification and clustering methods; modeling and optimization techniques for business intelligence; (Part II) multi-dimensional data processing; web systems; intelligent decision making; methods for scheduling; collective intelligence in web systems web systems analysis; advanced data mining techniques and applications; cooperative problem solving; computational swarm intelligence; and semantic methods for knowledge discovery and communication

"

Biological visual systems employ massively parallel processing to perform real-world visual tasks in real time. A key to this remarkable performance seems to be that biological systems construct representations of their visual image data at multiple scales. A Pyramid Framework for Early Vision describes a multiscale, or 'pyramid', approach to vision, including its theoretical foundations, a set of pyramid-based modules for image processing, object detection, texture discrimination, contour detection and processing, feature detection and description, and motion detection and tracking. It also shows how these modules can be implemented very efficiently on hypercube-connected processor networks. A Pyramid Framework for Early Vision is intended for both students of vision and vision system designers; it provides a general approach to vision systems design as well as a set of robust, efficient vision modules.

Mobile robots operating in real-world, outdoor scenarios depend on dynamic scene understanding for detecting and avoiding obstacles, recognizing landmarks, acquiring models, and for detecting and tracking moving objects. Motion understanding has been an active research effort for more than a decade, searching for solutions to some of these problems; however, it still remains one of the more difficult and challenging areas of computer vision research. Qualitative Motion Understanding describes a qualitative approach to dynamic scene and motion analysis, called DRIVE (Dynamic Reasoning from Integrated Visual Evidence). The DRIVE system addresses the problems of (a) estimating the robot's egomotion, (b) reconstructing the observed 3-D scene structure; and (c) evaluating the motion of individual objects from a sequence of monocular images. The approach is based on the FOE (focus of expansion) concept, but it takes a somewhat unconventional route. The DRIVE system uses a qualitative scene model and a fuzzy focus of expansion to estimate robot motion from visual cues, to detect and track moving objects, and to construct and maintain a global dynamic reference model.

Although there has been much progress in developing theories, models and systems in the areas of Natural Language Processing (NLP) and Vision Processing (VP) there has heretofore been little progress on integrating these subareas of Artificial Intelligence (AI). This book contains a set of edited papers addressing computational models and systems for the integration of NLP and VP. The papers focus on site descriptions such as that of the large Japanese $500 million Real World Computing (RWC) project, on historical philosophical issues, on systems which have been built and which integrate the processing of visual scenes together with language about them, and on spatial relations which appear to be the key to integration. The U.S.A., Japan and the EU are well reflected, showing up the fact that integration is a truly international issue. There is no doubt that all of this will be necessary for the InformationSuperHighways of the future.

A number of important aspects of intelligent machine vision in one volume, describing the state of the art and current developments in the field, including: fundamentals of 'intelligent'image processing for machine vision systems; algorithm optimisation; implementation in high-speed electronic digital hardware; implementation in an integrated high-level software environment and applications for industrial product quality and process control. Backed by numerous illustrations, created using the authors IP software, this book will be of interest to researchers in the field of machine vision wishing to understand the discipline and develop new techniques. Also useful for under- and postgraduates.

The two volumes set LNCS 7653 and 7654 constitutes the refereed proceedings of the 4th International Conference on Computational Collective Intelligence, ICCCI, held in Ho Chi Minh City, Vietnam, in November 2012. The 113 revised full papers presented were carefully reviewed and selected from 397 submissions. The papers are organized in topical sections on (Part I) knowledge integration; data mining for collective processing; fuzzy, modal, and collective systems; nature inspired systems; language processing systems; social networks and semantic web; agent and multi-agent systems; classification and clustering methods; modeling and optimization techniques for business intelligence; (Part II) multi-dimensional data processing; web systems; intelligent decision making; methods for scheduling; collective intelligence in web systems - web systems analysis; advanced data mining techniques and applications; cooperative problem solving; computational swarm intelligence; and semantic methods for knowledge discovery and communication

Goals of the Book Overthelast thirty yearsthere has been arevolutionindiagnostic radiology as a result oftheemergenceofcomputerized tomography (CT), which is the process of obtaining the density distribution within the human body from multiple x-ray projections. Since an enormous variety of possible density values may occur in the body, a large number of projections are necessary to ensure the accurate reconstruction oftheir distribution. There are other situations in which we desire to reconstruct an object from its projections, but in which we know that the object to be recon structed has only a small number of possible values. For example, a large fraction of objects scanned in industrial CT (for the purpose of nonde structive testing or reverse engineering) are made of a single material and so the ideal reconstruction should contain only two values: zero for air and the value associated with the material composing the object. Similar as sumptions may even be made for some specific medical applications; for example, in angiography ofthe heart chambers the value is either zero (in dicating the absence of dye) or the value associated with the dye in the chamber. Another example arises in the electron microscopy of biological macromolecules, where we may assume that the object to be reconstructed is composed of ice, protein, and RNA. One can also apply electron mi croscopy to determine the presenceor absence ofatoms in crystallinestruc tures, which is again a two-valued situation."

This book contains the proceedings of the workshop Uncertainty in Geomet ric Computations that was held in Sheffield, England, July 5-6, 2001. A total of 59 delegates from 5 countries in Europe, North America and Asia attended the workshop. The workshop provided a forum for the discussion of com putational methods for quantifying, representing and assessing the effects of uncertainty in geometric computations. It was organised around lectures by invited speakers, and presentations in poster form from participants. Computer simulations and modelling are used frequently in science and engi neering, in applications ranging from the understanding of natural and artificial phenomena, to the design, test and manufacturing stages of production. This widespread use necessarily implies that detailed knowledge of the limitations of computer simulations is required. In particular, the usefulness of a computer simulation is directly dependent on the user's knowledge of the uncertainty in the simulation. Although an understanding of the phenomena being modelled is an important requirement of a good computer simulation, the model will be plagued by deficiencies if the errors and uncertainties in it are not consid ered when the results are analysed. The applications of computer modelling are large and diverse, but the workshop focussed on the management of un certainty in three areas : Geometric modelling, computer vision, and computer graphics.

In June 1998 the Fourth International Workshop on Digital Mammography was held in Nijmegen, The Netherlands, where it was hosted by the department of Radiology of the University Hospital Nijmegen. This series of meetings was initiated at the 1993 SPIE Biomedical Image Processing Conference in San Jose, USA, where a number of sessions were entirely devoted to mammographic image analysis. At very successful subsequent workshops held in York, UK (1994) and Chicago, USA (1996), the scope of the conference was broadened, establishing a platform for presentation and discussion of new developments in digital mammog raphy. Topics that are addressed at these meetings are computer-aided diagnosis, image processing, detector development, system design, observer performance and clinical evaluation. The goal is to bring researchers from universities, breast cancer experts, and engineers together, to exchange information and present new scientific developments in this rapidly evolving field. This book contains all the scientific papers and posters presented at the work shop in Nijmegen. Contributions came from as many as 20 different countries and 190 participants attended the meeting. At a technical exhibit companies demon strated new products and work in progress. Abstracts of all papers were reviewed by members of the scientific committee. Many of the accepted papers had excellent quality, but due to limited space not all of them could be included as full papers in these proceedings. Papers that were rated high by the reviewers are included as long or short papers, others appear as extended abstracts in the last chapter.

Rapid development of remote sensing technology in recent years has greatly increased availability of high-resolution satellite image data. However, detailed analysis of such large data sets also requires innovative new techniques in image and signal processing.

This important text/reference presents a comprehensive review of image processing methods, for the analysis of land use in residential areas. Combining a theoretical framework with highly practical applications, making use of both well-known methods and cutting-edge techniques in computer vision, the book describes a system for the effective detection of single houses and streets in very high resolution.

Topics and features: with a Foreword by Prof. Dr. Peter Reinartz of the German Aerospace Center; provides end-of-chapter summaries and review questions; presents a detailed review on remote sensing satellites; examines the multispectral information that can be obtained from satellite images, with a focus on vegetation and shadow-water indices; investigates methods for land-use classification, introducing precise graph theoretical measures over panchromatic images; addresses the problem of detecting residential regions; describes a house and street network-detection subsystem; concludes with a summary of the key ideas covered in the book.

This pioneering work on automated satellite and aerial image-understanding systems will be of great interest to researchers in both remote sensing and computer vision, highlighting the benefit of interdisciplinary collaboration between the two communities. Urban planners and policy makers will also find considerable value in the proposed system."

Machine Learning: Discriminative and Generative covers the main contemporary themes and tools in machine learning ranging from Bayesian probabilistic models to discriminative support-vector machines. However, unlike previous books that only discuss these rather different approaches in isolation, it bridges the two schools of thought together within a common framework, elegantly connecting their various theories and making one common big-picture. Also, this bridge brings forth new hybrid discriminative-generative tools that combine the strengths of both camps. This book serves multiple purposes as well. The framework acts as a scientific breakthrough, fusing the areas of generative and discriminative learning and will be of interest to many researchers. However, as a conceptual breakthrough, this common framework unifies many previously unrelated tools and techniques and makes them understandable to a larger portion of the public. This gives the more practical-minded engineer, student and the industrial public an easy-access and more sensible road map into the world of machine learning. Machine Learning: Discriminative and Generative is designed for an audience composed of researchers & practitioners in industry and academia. The book is also suitable as a secondary text for graduate-level students in computer science and engineering.

This book constitutes the refereed conference proceedings of the 9th International Conference on Advances in Computer Entertainment, ACE 2012, held in Kathmandu, Nepal, in November 2012. The 10 full paper and 19 short papers presented together with 5 papers from the special track Arts and Culture and 35 extended abstracts were carefully reviewed and selected from a total of 140 submissions in all categories. The papers cover topics across a wide spectrum of disciplines including computer science, design, arts, sociology, anthropology, psychology, and marketing. Focusing on all areas related to interactive entertainment they aim at stimulating discussion in the development of new and compelling entertainment computing and interactive art concepts and applications.

Analyzing Video Sequences of Multiple Humans: Tracking, Posture Estimation and Behavior Recognition describes some computer vision-based methods that analyze video sequences of humans. More specifically, methods for tracking multiple humans in a scene, estimating postures of a human body in 3D in real-time, and recognizing a person's behavior (gestures or activities) are discussed. For the tracking algorithm, the authors developed a non-synchronous method that tracks multiple persons by exploiting a Kalman filter that is applied to multiple video sequences. For estimating postures, an algorithm is presented that locates the significant points which determine postures of a human body, in 3D in real-time. Human activities are recognized from a video sequence by the HMM (Hidden Markov Models)-based method that the authors pioneered. The effectiveness of the three methods is shown by experimental results.