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.

After a slow and somewhat tentative beginning, machine vision systems are now finding widespread use in industry. So far, there have been four clearly discernible phases in their development, based upon the types of images processed and how that processing is performed: (1) Binary (two level) images, processing in software (2) Grey-scale images, processing in software (3) Binary or grey-scale images processed in fast, special-purpose hardware (4) Coloured/multi-spectral images Third-generation vision systems are now commonplace, although a large number of binary and software-based grey-scale processing systems are still being sold. At the moment, colour image processing is commercially much less significant than the other three and this situation may well remain for some time, since many industrial artifacts are nearly monochrome and the use of colour increases the cost of the equipment significantly. A great deal of colour image processing is a straightforward extension of standard grey-scale methods. Industrial applications of machine vision systems can also be sub divided, this time into two main areas, which have largely retained distinct identities: (i) Automated Visual Inspection (A VI) (ii) Robot Vision (RV) This book is about a fifth generation of industrial vision systems, in which this distinction, based on applications, is blurred and the processing is marked by being much smarter (i. e. more "intelligent") than in the other four generations."

This volume constitutes the refereed proceedings of the 15th International Workshop on Combinatorial Image Analysis, IWCIA 2012, held in Austin, TX, USA in November 2012. The 23 revised full papers presented were carefully reviewed and selected from numerous submissions. The topics covered include digital geometry, combinatorics in digital spaces, digital curves and surfaces; digital topologyl grammars, transformation, applications; grammars and models in image analysis; picture transformations, morphologic operations, image segmentation; and discrete tomography, applications.

Designing inclusively is no longer an option for companies. It is a business essential. Global populations are getting older, legislation is increasingly prohibitive of unnecessary exclusion and consumer attitudes are beginning to change. Exclusivity is out, inclusivity is in. Research communities the world over are responding to this change in design emphasis. Conferences such as the Cambridge Workshops on Universal Access and Assistive Technology (CWUAAT) offer a forum for researchers from diverse and varied disciplines to bring their perspectives on inclusive design together. This book has been inspired by the second CWUAAT, held in Cambridge, England in March 2004. It contains chapters from an international group of leading researchers in this field. Contributions focus on the following topics: design issues for universal access and assistive technology; enabling computer access and new technologies; and, assistive technology and rehabilitation robotics. This series of conferences is aimed at a broad range of interests, with a general focus on the development of products and solutions. Numerous case studies are used to raise awareness of the challenges faced in developing truly inclusive products, along with examples of good practice for design for a more inclusive world.

The application of intelligent imaging techniques to industrial vision problems is an evolving aspect of current machine vision research. Machine vision is a relatively new technology, more concerned with systems engineering than with computer science, and with much to offer the manufacturing industry in terms of improving efficiency, safety and product quality. Beginning with an introductory chapter on the basic concepts, the authors develop these ideas to describe intelligent imaging techniques for use in a new generation of industrial imaging systems. Sections cover the application of AI languages such as Prolog, the use of multi-media interfaces and multi-processor systems, external device control, and colour recognition. The text concludes with a discussion of several case studies that illustrate how intelligent machine vision techniques can be used in industrial applications.

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."

Sampling, wavelets, and tomography are three active areas of contemporary mathematics sharing common roots that lie at the heart of harmonic and Fourier analysis. The advent of new techniques in mathematical analysis has strengthened their interdependence and led to some new and interesting results in the field. This state-of-the-art book not only presents new results in these research areas, but it also demonstrates the role of sampling in both wavelet theory and tomography. Specific topics covered include: * Robustness of Regular Sampling in Sobolev Algebras * Irregular and Semi-Irregular Weyl-Heisenberg Frames * Adaptive Irregular Sampling in Meshfree Flow Simulation * Sampling Theorems for Non-Bandlimited Signals * Polynomial Matrix Factorization, Multidimensional Filter Banks, and Wavelets * Generalized Frame Multiresolution Analysis of Abstract Hilbert Spaces * Sampling Theory and Parallel-Beam Tomography * Thin-Plate Spline Interpolation in Medical Imaging * Filtered Back-Projection Algorithms for Spiral Cone Computed Tomography Aimed at mathematicians, scientists, and engineers working in signal and image processing and medical imaging, the work is designed to be accessible to an audience with diverse mathematical backgrounds. Although the volume reflects the contributions of renowned mathematicians and engineers, each chapter has an expository introduction written for the non-specialist. One of the key features of the book is an introductory chapter stressing the interdependence of the three main areas covered. A comprehensive index completes the work. Contributors: J.J. Benedetto, N.K. Bose, P.G. Casazza, Y.C. Eldar, H.G. Feichtinger, A. Faridani, A. Iske, S. Jaffard, A. Katsevich, S. Lertrattanapanich, G. Lauritsch, B. Mair, M. Papadakis, P.P. Vaidyanathan, T. Werther, D.C. Wilson, A.I. Zayed

This book constitutes the refereed proceedings of the 9th International Forum on Digital TV and Wireless Multimedia Communication, IFTC 2012, Shanghai, China, November. The 69 revised full papers presented were carefully reviewed and selected from numerous submissions. The papers are organized in topical sections on image processing and pattern recognition; image and video analysis; image quality assessment; text image and speech processing; content retrieval and security; source coding; multimedia communication; new advances in broadband multimedia; human computer interface; 3D video.

This book constitutes the refereed proceedings of the First International Symposium on Communicability, Computer Graphics and Innovative Design for Interactive Systems, held in Cordoba, Spain, in June 2011. The 13 revised full papers presented were carefully reviewed and selected from various submissions. They examine latest breakthroughs and future trends within the communicability, computer graphics, and innovative design of interactive systems.

The five volume set LNCS 7663, LNCS 7664, LNCS 7665, LNCS 7666 and LNCS 7667 constitutes the proceedings of the 19th International Conference on Neural Information Processing, ICONIP 2012, held in Doha, Qatar, in November 2012. The 423 regular session papers presented were carefully reviewed and selected from numerous submissions. These papers cover all major topics of theoretical research, empirical study and applications of neural information processing research. The 5 volumes represent 5 topical sections containing articles on theoretical analysis, neural modeling, algorithms, applications, as well as simulation and synthesis.

In the current age of information technology, the issues of distributing and utilizing images efficiently and effectively are of substantial concern. Solutions to many of the problems arising from these issues are provided by techniques of image processing, among which segmentation and compression are topics of this book. Image segmentation is a process for dividing an image into its constituent parts. For block-based segmentation using statistical classification, an image is divided into blocks and a feature vector is formed for each block by grouping statistics of its pixel intensities. Conventional block-based segmentation algorithms classify each block separately, assuming independence of feature vectors. Image Segmentation and Compression Using Hidden Markov Models presents a new algorithm that models the statistical dependence among image blocks by two dimensional hidden Markov models (HMMs). Formulas for estimating the model according to the maximum likelihood criterion are derived from the EM algorithm. To segment an image, optimal classes are searched jointly for all the blocks by the maximum a posteriori (MAP) rule. The 2-D HMM is extended to multiresolution so that more context information is exploited in classification and fast progressive segmentation schemes can be formed naturally. The second issue addressed in the book is the design of joint compression and classification systems using the 2-D HMM and vector quantization. A classifier designed with the side goal of good compression often outperforms one aimed solely at classification because overfitting to training data is suppressed by vector quantization. Image Segmentation and Compression Using Hidden Markov Models is an essential reference source for researchers and engineers working in statistical signal processing or image processing, especially those who are interested in hidden Markov models. It is also of value to those working on statistical modeling.

As Lord Kelvin said, "Fourier's theorem is not only one of the most beautiful results of modern analysis, but it may be said to furnish an indispensable instrument in the treatment of nearly every recondite question in modern physics." This has remained durable knowledge for a century, and has extended its applicability to topics as diverse as medical imaging (CT scanning), the presentation of images on screens and their digital transmission, remote sensing, geophysical exploration, and many branches of engineering. Fourier Analysis and Imaging is based on years of teaching a course on the Fourier Transform at the senior or early graduate level, as well as on Prof. Bracewell's 1995 text Two-Dimensional Imaging. It is an excellent textbook and will also be a welcome addition to the reference library of those many professionals whose daily activities involve Fourier analysis in its many guises.

Action recognition technology has many real-world applications in human-computer interaction, surveillance, video retrieval, retirement home monitoring, and robotics. The commoditization of depth sensors has also opened up further applications that were not feasible before. This text focuses on feature representation and machine learning algorithms for action recognition from depth sensors. After presenting a comprehensive overview of the state of the art, the authors then provide in-depth descriptions of their recently developed feature representations and machine learning techniques, including lower-level depth and skeleton features, higher-level representations to model the temporal structure and human-object interactions, and feature selection techniques for occlusion handling. This work enables the reader to quickly familiarize themselves with the latest research, and to gain a deeper understanding of recently developed techniques. It will be of great use for both researchers and practitioners.

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."

From the reviews: "This book offers a coherent treatment, at the graduate textbook level, of the field that has come to be known in the last decade or so as computational geometry. ... ... The book is well organized and lucidly written; a timely contribution by two founders of the field. It clearly demonstrates that computational geometry in the plane is now a fairly well-understood branch of computer science and mathematics. It also points the way to the solution of the more challenging problems in dimensions higher than two." #Mathematical Reviews#1 "... This remarkable book is a comprehensive and systematic study on research results obtained especially in the last ten years. The very clear presentation concentrates on basic ideas, fundamental combinatorial structures, and crucial algorithmic techniques. The plenty of results is clever organized following these guidelines and within the framework of some detailed case studies. A large number of figures and examples also aid the understanding of the material. Therefore, it can be highly recommended as an early graduate text but it should prove also to be essential to researchers and professionals in applied fields of computer-aided design, computer graphics, and robotics." #Biometrical Journal#2

Since the study of wavelets is a relatively new area, much of the research coming from mathematicians, most of the literature uses terminology, concepts and proofs that may, at times, be difficult and intimidating for the engineer. Wavelet Basics has therefore been written as an introductory book for scientists and engineers. The mathematical presentation has been kept simple, the concepts being presented in elaborate detail in a terminology that engineers will find familiar. Difficult ideas are illustrated with examples which will also aid in the development of an intuitive insight. Chapter 1 reviews the basics of signal transformation and discusses the concepts of duals and frames. Chapter 2 introduces the wavelet transform, contrasts it with the short-time Fourier transform and clarifies the names of the different types of wavelet transforms. Chapter 3 links multiresolution analysis, orthonormal wavelets and the design of digital filters. Chapter 4 gives a tour d'horizon of topics of current interest: wavelet packets and discrete time wavelet transforms, and concludes with applications in signal processing.

Time-of-flight (TOF) cameras provide a depth value at each pixel, from which the 3D structure of the scene can be estimated. This new type of active sensor makes it possible to go beyond traditional 2D image processing, directly to depth-based and 3D scene processing. Many computer vision and graphics applications can benefit from TOF data, including 3D reconstruction, activity and gesture recognition, motion capture and face detection. It is already possible to use multiple TOF cameras, in order to increase the scene coverage, and to combine the depth data with images from several colour cameras. Mixed TOF and colour systems can be used for computational photography, including full 3D scene modelling, as well as for illumination and depth-of-field manipulations. This work is a technical introduction to TOF sensors, from architectural and design issues, to selected image processing and computer vision methods.

This volume contains the proceedings of the 12th Italian Workshop on Neural Nets WIRN VIETRI-Ol, jointly organized by the International Institute for Advanced Scientific Studies "Eduardo R. Caianiello" (IIASS), the Societa Italiana Reti Neuroniche (SIREN), the IEEE NNC Italian RIG and the Italian SIG of the INNS. Following the tradition of previous years, we invited three foreign scientists to the workshop, Dr. G. Indiveri and Professors A. Roy and R. Sun, who respectively presented the lectures "Computation in Neuromorphic Analog VLSI Systems", "On Connectionism and Rule Extraction", "Beyond Simple Rule Extraction: Acquiring Planning Knowledge from Neural Networks" (the last two papers being part of the special session mentioned below). In addition, a review talk was presented, dealing with a very up-to-date topic: "NeuroJuzzy Approximator based on Mamdani's Model". A large part of the book contains original contributions approved by referees as oral or poster presentations, which have been assembled for reading convenience into three sections: Architectures and Algorithms, Image and Signal Processing, and Applications. The last part of the books contains the papers of the special Session "From Synapses to Rules". Our thanks go to Prof. B. Apolloni, who organized this section. Furthermore, two sections are dedicated to the memory of two great scientists who were friends in life, Professors Mark Aizerman and Eduardo R. Caianiello. The editors would like to thank the invited speakers, the review lecturers and all the contributors whose highly qualified papers helped with the success of the workshop.

Geometric constraint programming increases flexibility in CAD design specifications and leads to new conceptual design paradigms.
This volume features a collection of work by leading researchers developing the various aspects of constraint-based product modeling.
In an introductory chapter the role of constraints in CAD systems of the future and their implications for the STEP data exchange format are discussed. The main part of the book deals with the application of constraints to conceptual and collaborative design, as well as state-of-the-art mathematical and algorithmic methods for constraint solving.

This book constitutes the refereed proceedings of the International Conference on Artificial Intelligence and Computational Intelligence, AICI 2012, held in Chengdu, China, in October 2012. The 163 revised full papers presented were carefully reviewed and selected from 724 submissions. The papers are organized in topical sections on applications of artificial intelligence; applications of computational intelligence; data mining and knowledge discovering; evolution strategy; intelligent image processing; machine learning; neural networks; pattern recognition.

This book is a collection of several tutorials from the EUROGRAPHICS '90 conference in Montreux. The conference was held under the motto "IMAGES: Synthesis, Analysis and Interaction", and the tutorials, partly presented in this volume, reflect the conference theme. As such, this volume provides a unique collection of advanced texts on 'traditional' com puter graphics as well as of tutorials on image processing and image reconstruction. As with all the volumes of the series "Advances in Computer Graphics", the contributors are leading experts in their respective fields. The chapter Design and Display of Solid Models provides an extended introduction to interactive graphics techniques for design, fast display, and high-quality rendering of solid models. The text focuses on techniques for Constructive Solid Geometry (CSG). The follow ing topics are treated in depth: interactive design techniques (specification of curves, surfaces and solids; graphical user interfaces; procedural languages and direct manipulation) and display techniques (depth-buffer, scan-line and ray-tracing techniques; CSG classification techniques; efficiency-improving methods; software and hardware implementations).

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.

Monitoring of public and private sites is increasingly becoming a very important and critical issue, especially after the recent flurry of terrorist attacks including the one on the Word Trade Center in September 2001. It is, therefore, imperative that effective multisensor surveillance systems be developed to protect the society from similar attacks in the future. The new generation of surveillance systems to be developed have a specific requirement: they must be able to automatically identify criminal and terrorist activity without sacrificing individual privacy to the extent possible. Privacy laws concerning monitoring and surveillance systems vary from country to country but, in general, they try to protect the privacy of their citizens. Monitoring and visual surveillance has numerous other applications. It can be employed to help invalids or handicapped and to monitor the activities of elderly people. It can be used to monitor large events such as sporting events, as well. Nowadays, monitoring is employ d in several different contexts including transport applications, such as monitoring of railway stations and airports, dangerous environments like nuclear facilities or traffic flows on roads and bridges. The latest generation of surveillance systems mainly rely on hybrid analog-digital, or completely digital video communications and processing methods and take advantage of the greater of flexibility offered by video processing algorithms that are capable focusing a human operator's attention on a set of interesting situations.

This book constitutes the proceedings of the First International Conference on Intelligent Robotics and Manufacturing, IRAM 2012, held in Kuala Lumpur, Malaysia, in November 2012. The 64 revised full papers included in this volume were carefully reviewed and selected from 102 initial submissions. The papers are organized in topical sections named: mobile robots, intelligent autonomous systems, robot vision and robust, autonomous agents, micro, meso and nano-scale automation and assembly, flexible manufacturing systems, CIM and micro-machining, and fabrication techniques.

This book constitutes the refereed proceedings of the 24th International Symposium on Algorithms and Computation, ISAAC 2013, held in Hong Kong, China in December 2013. The 67 revised full papers presented together with 2 invited talks were carefully reviewed and selected from 177 submissions for inclusion in the book. The focus of the volume in on the following topics: computation geometry, pattern matching, computational complexity, internet and social network algorithms, graph theory and algorithms, scheduling algorithms, fixed-parameter tractable algorithms, algorithms and data structures, algorithmic game theory, approximation algorithms and network algorithms.