This book presents a comprehensive treatise on Riemannian geometric computations and related statistical inferences in several computer vision problems. This edited volume includes chapter contributions from leading figures in the field of computer vision who are applying Riemannian geometric approaches in problems such as face recognition, activity recognition, object detection, biomedical image analysis, and structure-from-motion. Some of the mathematical entities that necessitate a geometric analysis include rotation matrices (e.g. in modeling camera motion), stick figures (e.g. for activity recognition), subspace comparisons (e.g. in face recognition), symmetric positive-definite matrices (e.g. in diffusion tensor imaging), and function-spaces (e.g. in studying shapes of closed contours).

The central object of this book is the measure of geometric quantities describing N a subset of the Euclidean space (E ,), endowed with its standard scalar product. Let us state precisely what we mean by a geometric quantity. Consider a subset N S of points of the N-dimensional Euclidean space E , endowed with its standard N scalar product. LetG be the group of rigid motions of E . We say that a 0 quantity Q(S) associated toS is geometric with respect toG if the corresponding 0 quantity Q[g(S)] associated to g(S) equals Q(S), for all g?G . For instance, the 0 diameter ofS and the area of the convex hull ofS are quantities geometric with respect toG . But the distance from the origin O to the closest point ofS is not, 0 since it is not invariant under translations ofS. It is important to point out that the property of being geometric depends on the chosen group. For instance, ifG is the 1 N group of projective transformations of E , then the property ofS being a circle is geometric forG but not forG , while the property of being a conic or a straight 0 1 line is geometric for bothG andG . This point of view may be generalized to any 0 1 subsetS of any vector space E endowed with a groupG acting on it.

Digital geometry emerged as an independent discipline in the second half of the last century. It deals with geometric properties of digital objects and is developed with the unambiguous goal to provide rigorous theoretical foundations for devising new advanced approaches and algorithms for various problems of visual computing. Different aspects of digital geometry have been addressed in the literature. This book is the first one that explicitly focuses on the presentation of the most important digital geometry algorithms. Each chapter provides a brief survey on a major research area related to the general volume theme, description and analysis of related fundamental algorithms, as well as new original contributions by the authors. Every chapter contains a section in which interesting open problems are addressed.

This book provides a survey of deep learning approaches to domain adaptation in computer vision. It gives the reader an overview of the state-of-the-art research in deep learning based domain adaptation. This book also discusses the various approaches to deep learning based domain adaptation in recent years. It outlines the importance of domain adaptation for the advancement of computer vision, consolidates the research in the area and provides the reader with promising directions for future research in domain adaptation. Divided into four parts, the first part of this book begins with an introduction to domain adaptation, which outlines the problem statement, the role of domain adaptation and the motivation for research in this area. It includes a chapter outlining pre-deep learning era domain adaptation techniques. The second part of this book highlights feature alignment based approaches to domain adaptation. The third part of this book outlines image alignment procedures for domain adaptation. The final section of this book presents novel directions for research in domain adaptation. This book targets researchers working in artificial intelligence, machine learning, deep learning and computer vision. Industry professionals and entrepreneurs seeking to adopt deep learning into their applications will also be interested in this book.

This book is a collection of articles presented by researchers and practitioners, including engineers, biologists, health professionals and informatics/computer scientists, interested in both theoretical advances and applications of information systems, artificial intelligence, signal processing, electronics and other engineering tools in areas related to biology and medicine in the All India Seminar on Biomedical Engineering 2012 (AISOBE 2012), organized by The Institution of Engineers (India), Jabalpur Local Centre, Jabalpur, India during November 3-4, 2012. The content of the book is useful to doctors, engineers, researchers and academicians as well as industry professionals.

This book introduces time-stretch quantitative phase imaging (TS-QPI), a high-throughput label-free imaging flow cytometer developed for big data acquisition and analysis in phenotypic screening. TS-QPI is able to capture quantitative optical phase and intensity images simultaneously, enabling high-content cell analysis, cancer diagnostics, personalized genomics, and drug development. The authors also demonstrate a complete machine learning pipeline that performs optical phase measurement, image processing, feature extraction, and classification, enabling high-throughput quantitative imaging that achieves record high accuracy in label -free cellular phenotypic screening and opens up a new path to data-driven diagnosis.

This book provides an overview of model-based environmental visual perception for humanoid robots. The visual perception of a humanoid robot creates a bidirectional bridge connecting sensor signals with internal representations of environmental objects. The objective of such perception systems is to answer two fundamental questions: What & where is it? To answer these questions using a sensor-to-representation bridge, coordinated processes are conducted to extract and exploit cues matching robot's mental representations to physical entities. These include sensor & actuator modeling, calibration, filtering, and feature extraction for state estimation. This book discusses the following topics in depth: * Active Sensing: Robust probabilistic methods for optimal, high dynamic range image acquisition are suitable for use with inexpensive cameras. This enables ideal sensing in arbitrary environmental conditions encountered in human-centric spaces. The book quantitatively shows the importance of equipping robots with dependable visual sensing. * Feature Extraction & Recognition: Parameter-free, edge extraction methods based on structural graphs enable the representation of geometric primitives effectively and efficiently. This is done by eccentricity segmentation providing excellent recognition even on noisy & low-resolution images. Stereoscopic vision, Euclidean metric and graph-shape descriptors are shown to be powerful mechanisms for difficult recognition tasks. * Global Self-Localization & Depth Uncertainty Learning: Simultaneous feature matching for global localization and 6D self-pose estimation are addressed by a novel geometric and probabilistic concept using intersection of Gaussian spheres. The path from intuition to the closed-form optimal solution determining the robot location is described, including a supervised learning method for uncertainty depth modeling based on extensive ground-truth training data from a motion capture system. The methods and experiments are presented in self-contained chapters with comparisons and the state of the art. The algorithms were implemented and empirically evaluated on two humanoid robots: ARMAR III-A & B. The excellent robustness, performance and derived results received an award at the IEEE conference on humanoid robots and the contributions have been utilized for numerous visual manipulation tasks with demonstration at distinguished venues such as ICRA, CeBIT, IAS, and Automatica.

This book provides readers with a selection of high-quality chapters that cover both theoretical concepts and practical applications of image feature detectors and descriptors. It serves as reference for researchers and practitioners by featuring survey chapters and research contributions on image feature detectors and descriptors. Additionally, it emphasizes several keywords in both theoretical and practical aspects of image feature extraction. The keywords include acceleration of feature detection and extraction, hardware implantations, image segmentation, evolutionary algorithm, ordinal measures, as well as visual speech recognition.

The field of robotic vision has advanced dramatically recently with the development of new range sensors. Tremendous progress has been made resulting in significant impact on areas such as robotic navigation, scene/environment understanding, and visual learning. This edited book provides a solid and diversified reference source for some of the most recent important advancements in the field of robotic vision. The book starts with articles that describe new techniques to understand scenes from 2D/3D data such as estimation of planar structures, recognition of multiple objects in the scene using different kinds of features as well as their spatial and semantic relationships, generation of 3D object models, approach to recognize partially occluded objects, etc. Novel techniques are introduced to improve 3D perception accuracy with other sensors such as a gyroscope, positioning accuracy with a visual servoing based alignment strategy for microassembly, and increasing object recognition reliability using related manipulation motion models. For autonomous robot navigation, different vision-based localization and tracking strategies and algorithms are discussed. New approaches using probabilistic analysis for robot navigation, online learning of vision-based robot control, and 3D motion estimation via intensity differences from a monocular camera are described. This collection will be beneficial to graduate students, researchers, and professionals working in the area of robotic vision.

This book discusses computer vision, a noncontact as well as a nondestructive technique involving the development of theoretical and algorithmic tools for automatic visual understanding and recognition which finds huge applications in agricultural productions. It also entails how rendering of machine learning techniques to computer vision algorithms is boosting this sector with better productivity by developing more precise systems. Computer vision and machine learning (CV-ML) helps in plant disease assessment along with crop condition monitoring to control the degradation of yield, quality, and severe financial loss for farmers. Significant scientific and technological advances have been made in defect assessment, quality grading, disease recognition, pests, insects, fruits, and vegetable types recognition and evaluation of a wide range of agricultural plants, crops, leaves, and fruits. The book discusses intelligent robots developed with the touch of CV-ML which can help farmers to perform various tasks like planting, weeding, harvesting, plant health monitoring, and so on. The topics covered in the book include plant, leaf, and fruit disease detection, crop health monitoring, applications of robots in agriculture, precision farming, assessment of product quality and defects, pest, insect, fruits, and vegetable types recognition.

Many computer scientists, engineers, applied mathematicians, and physicists use geometry theory and geometric computing methods in the design of perception-action systems, intelligent autonomous systems, and man-machine interfaces. This handbook brings together the most recent advances in the application of geometric computing for building such systems, with contributions from leading experts in the important fields of neuroscience, neural networks, image processing, pattern recognition, computer vision, uncertainty in geometric computations, conformal computational geometry, computer graphics and visualization, medical imagery, geometry and robotics, and reaching and motion planning. For the first time, the various methods are presented in a comprehensive, unified manner.

This handbook is highly recommended for postgraduate students and researchers working on applications such as automated learning; geometric and fuzzy reasoning; human-like artificial vision; tele-operation; space maneuvering; haptics; rescue robots; man-machine interfaces; tele-immersion; computer- and robotics-aided neurosurgery or orthopedics; the assembly and design of humanoids; and systems for metalevel reasoning.

An Advanced Research Workshop (ARW) "Data Fusion Technologies for Harbour Protection" was held in Tallinn, Estonia 27 June-1 July, 2005. This workshop was organized by request of the NATO Security Through Science Programme and the Defence Investment Division. An ARW is one of many types of funded group support mechanisms established by the NATO Science Committee to contribute to the critical assessment of existing knowledge on new important topics, to identify directions for future research, and to promote close working relationships between scientists from different countries and with different professional experiences. The NATO Science Committee was approved at a meeting of the Heads of Government of the Alliance in December 1957, subsequent to the 1956 recommendation of "Three Wise Men" - Foreign Ministers Lange (Norway), Martino (Italy) and Pearson (Canada) on Non-Military Cooperation in NATO. The NATO Science Committee established the NATO Science Programme in 1958 to encourage and support scientific collaboration between individual scientists and to foster scientific development in its member states. In 1999, following the end of the Cold War, the Science Programme was transformed so that support is now devoted to collaboration between Partner-country and NATO-country scientists or to contributing towards research support in Partner countries. Since 2004, the Science Programme was further modified to focus exclusively on NATO Priority Research Topics (i. e. Defence Against Terrorism or Countering Other Threats to Security) and also preferably on a Partner country priority area.

The deployment of surveillance systems has captured the interest of both the research and the industrial worlds in recent years. The aim of this effort is to increase security and safety in several application domains such as national security, home and bank safety, traffic monitoring and navigation, tourism, and military applications. The video surveillance systems currently in use share one feature: A human operator must monitor them at all times, thus limiting the number of cameras and the area under surveillance and increasing cost. A more advantageous system would have continuous active warning capabilities, able to alert security officials during or even before the happening of a crime.

Existing automated surveillance systems can be classified into categories according to:

• The environment they are primarily designed to observe;
• The number of sensors that the automated surveillance system can handle;
• The mobility of sensor.

The primary concern of this book is surveillance in an outdoor urban setting, where it is not possible for a single camera to observe the complete area of interest. Multiple cameras are required to observe such large environments. This book discusses and proposes techniques for development of an automated multi-camera surveillance system for outdoor environments, while identifying the important issues that a system needs to cope with in realistic surveillance scenarios. The goal of the research presented in this book is to build systems that can deal effectively with these realistic surveillance needs.

Markov random field (MRF) theory provides a basis for modeling contextual constraints in visual processing and interpretation. It enables us to develop optimal vision algorithms systematically when used with optimization principles. This book presents a comprehensive study on the use of MRFs for solving computer vision problems. Various vision models are presented in a unified framework, including image restoration and reconstruction, edge and region segmentation, texture, stereo and motion, object matching and recognition, and pose estimation. This third edition includes the most recent advances and has new and expanded sections on topics such as: Bayesian Network; Discriminative Random Fields; Strong Random Fields; Spatial-Temporal Models; Learning MRF for Classification. This book is an excellent reference for researchers working in computer vision, image processing, statistical pattern recognition and applications of MRFs. It is also suitable as a text for advanced courses in these areas.

Demand continues to grow worldwide, from both government and commerce, for technologies capable of automatically selecting and identifying object/human behaviour.

This accessible text/reference presents a comprehensive and unified treatment of visual analysis of behaviour from computational-modelling and algorithm-design perspectives. The book provides in-depth discussion on computer vision and statistical machine learning techniques, in addition to reviewing a broad range of behaviour modelling problems. A mathematical background is not required to understand the content, although readers will benefit from modest knowledge of vectors and matrices, eigenvectors and eigenvalues, linear algebra, optimisation, multivariate analysis, probability, statistics and calculus.

Topics and features: provides a thorough introduction to the study and modelling of behaviour, and a concluding epilogue; covers learning-group activity models, unsupervised behaviour profiling, hierarchical behaviour discovery, learning behavioural context, modelling rare behaviours, and man-in-the-loop active learning of behaviours; examines multi-camera behaviour correlation, person re-identification, and connecting-the-dots for global abnormal behaviour detection; discusses Bayesian information criterion, Bayesian networks, bag-of-words representation, canonical correlation analysis, dynamic Bayesian networks, Gaussian mixtures, and Gibbs sampling; investigates hidden conditional random fields, hidden Markov models, human silhouette shapes, latent Dirichlet allocation, local binary patterns, locality preserving projection, and Markov processes; explores probabilistic graphical models, probabilistic topic models, space-time interest points, spectral clustering, and support vector machines; includes a helpful list of acronyms.

A valuable resource for both researchers in computer vision and machine learning, and for developers of commercial applications, the book can also serve as a useful reference for postgraduate students of computer science and behavioural science. Furthermore, policymakers and commercial managers will find this an informed guide on intelligent video analytics systems.

One of the world s leading problems in the field of national security is protection of borders and borderlands. This book addresses multiple issues on advanced innovative methods of multi-level control of both ground (UGVs) and aerial drones (UAVs). Those objects combined with innovative algorithms become autonomous objects capable of patrolling chosen borderland areas by themselves and automatically inform the operator of the system about potential place of detection of a specific incident. This is achieved by using sophisticated

methods of generation of non-collision trajectory for those types of objects and enabling automatic integration of both ground and aerial unmanned vehicles.

The topics included in this book also cover presentation of complete information and communication technology (ICT) systems capable of control, observation and detection of various types of incidents and threats. This book is a valuable source of information for constructors and developers of such solutions for uniformed services. Scientists and researchers involved in computer vision, image processing, data fusion, control algorithms or IC can find many valuable suggestions and solutions. Multiple challenges for such systems are also presented. "

This open access handbook provides the first comprehensive overview of biometrics exploiting the shape of human blood vessels for biometric recognition, i.e. vascular biometrics, including finger vein recognition, hand/palm vein recognition, retina recognition, and sclera recognition. After an introductory chapter summarizing the state of the art in and availability of commercial systems and open datasets/open source software, individual chapters focus on specific aspects of one of the biometric modalities, including questions of usability, security, and privacy. The book features contributions from both academia and major industrial manufacturers.

The fields of computer vision and image processing are constantly evolving as new research and applications in these areas emerge. Staying abreast of the most up-to-date developments in this field is necessary in order to promote further research and apply these developments in real-world settings. Computer Vision and Image Processing in Intelligent Systems and Multimedia Technologies features timely and informative research on the design and development of computer vision and image processing applications in intelligent agents as well as in multimedia technologies. Covering a diverse set of research in these areas, this publication is ideally designed for use by academicians, technology professionals, students, and researchers interested in uncovering the latest innovations in the field.

This book is both a reference for engineers and scientists and a teaching resource, featuring tutorial chapters and research papers on feature extraction. Its CD-ROM includes the data of the NIPS 2003 Feature Selection Challenge and sample Matlab code. Until now there has been insufficient consideration of feature selection algorithms, no unified presentation of leading methods, and no systematic comparisons.

This volume comprises some of the key work presented at two IMA Workshops on Computer Vision during fall of 2000. Recent years have seen significant advances in the application of sophisticated mathematical theories to the problems arising in image processing. Basic issues include image smoothing and denoising, image enhancement, morphology, image compression, and segmentation (determining boundaries of objectsùincluding problems of camera distortion and partial occlusion). Several mathematical approaches have emerged, including methods based on nonlinear partial differential equations, stochastic and statistical methods, and signal processing techniques, including wavelets and other transform theories. Shape theory is of fundamental importance since it is the bottleneck between high and low level vision, and formed the bridge between the two workshops on vision. The recent geometric partial differential equation methods have been essential in throwing new light on this very difficult problem area. Further, stochastic processes, including Markov random fields, have been used in a Bayesian framework to incorporate prior constraints on smoothness and the regularities of discontinuities into algorithms for image restoration and reconstruction. A number of applications are considered including optical character and handwriting recognizers, printed-circuit board inspection systems and quality control devices, motion detection, robotic control by visual feedback, reconstruction of objects from stereoscopic view and/or motion, autonomous road vehicles, and many others.

The book is about Gentzen calculi for (the main systems of) modal logic. It is divided into three parts. In the first partwe introduce and discuss the main philosophical ideas related to proof theory, and we try to identify criteria for distinguishing good sequent calculi. In the second part we present the several attempts made from the 50's until today to provide modal logic with Gentzen calculi. In the third and and final part we analyse new calculi for modal logics, called tree-hypersequent calculi, which were recently introduced by the author. We show in a precise and clear way the main results that can be proved with and about them.

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 edited book presents essential findings in the research fields of artificial intelligence and computer vision, with a primary focus on new research ideas and results for mathematical problems involved in computer vision systems. The book provides an international forum for researchers to summarize the most recent developments and ideas in the field, with a special emphasis on the technical and observational results obtained in the past few years.

This book explores the application of deep learning techniques within a particularly difficult computational type of computer vision (CV) problem super-resolution (SR). The authors present and discuss ways to apply computational intelligence (CI) methods to SR. The volume also explores the possibility of using different kinds of CV techniques to develop and enhance the tools/processes related to SR. The application areas covered include biomedical engineering, healthcare applications, medicine, histology, and material science. The book will be a valuable reference for anyone concerned with multiple multimodal images, especially professionals working in remote sensing, nanotechnology and immunology at research institutes, healthcare facilities, biotechnology institutions, agribusiness services, veterinary facilities, and universities.

The past decades have seen significant improvements in 3D imaging where the related techniques and technologies have advanced to a mature state. These exciting developments have sparked increasing interest in the challenges and opportunities afforded by 3D sensing. As a consequence, the emerging area of safety and security related imaging incorporates these important new technologies beyond the limitations of 2D image processing.This book presents the thoroughly revised versions of lectures given by leading researchers during the Workshop on Advanced 3D Imaging for Safety and Security in conjunction with the International Conference on Computer Vision and Pattern Recognition CVPR 2005, held in San Diego, CA, USA in June 2005.It covers the current state of the art in 3D imaging for safety and security.