This book constitutes the thoroughly refereed post-proceedings of the 10th International Workshop on Theoretical Foundations of Computer Vision, held at Dagstuhl Castle, Germany, in March 2000.
The 20 revised full papers presented have been through two rounds of reviewing, selection, and revision and give a representative assessment of the foundational issues in multiple-image processing. The papers are organized in topical sections on 3D data acquisition and sensor design, multi-image analysis, data fusion in 3D scene description, and applied 3D vision and virtual reality.

Following the highly successful International Conference on Computer Vision - stems held in Las Palmas, Spain (ICVS'99), this second International Workshop on Computer Vision Systems, ICVS 2001 was held as an associated workshop of the International Conference on Computer Vision in Vancouver, Canada. The organization of ICVS'99 and ICVS 2001 was motivated by the fact that the - jority of computer vision conferences focus on component technologies. However, Computer Vision has reached a level of maturity that allows us not only to p- form research on individual methods and system components but also to build fully integrated computer vision systems of signi cant complexity. This opens a number of new problems related to system architecture, methods for system synthesis and veri cation, active vision systems, control of perception and - tion, knowledge and system representation, context modeling, cue integration, etc. By focusing on methods and concepts for the construction of fully integrated vision systems, ICVS aims to bring together researchers interested in computer vision systems. Similar to the previous event in Las Palmas, ICVS 2001 was organized as a single-track workshop consisting of high-quality, previously unpublished papers on new and original research on computer vision systems. All contributions were presented orally. A total of 32 papers were submitted and reviewed thoroughly by program committee members. Twenty of them have been selected for p- sentation. We would like to thank all members of the organizing and program committee for their help in putting together a high-quality workshop.

A collection of original contributions by researchers who work at the forefront of a new field, lying at the intersection of computer vision and computer graphics. Several original approaches are presented to the integration of computer vision and graphics techniques to aid in the realistic modelling of objects and scenes, interactive computer graphics, augmented reality, and virtual studios. Numerous applications are also discussed, including urban and archaeological site modelling, modelling dressed humans, medical visualisation, figure and facial animation, real-time 3D teleimmersion telecollaboration, augmented reality as a new user interface concept, and augmented reality in the understanding of underwater scenes.

This book presents a unique collection of articles on shape, contour and grouping in computer vision. Besides revised versions of research papers originally presented at a workshop, the book contains expository articles introducing the area to a broader audience and surveying the state of the art.The 19 articles presented were carefully reviewed. They are organized in the following sections: introduction; shape; shading; grouping; representation and recognition; and statistics,learning and recognition.

There is often a great deal of discussion these days about multi-disciplinary research and the value of exchanging ideas and methods across traditional discipline boundaries. Indeed, it could be justifiably argued that many of the advances in science and engineering take place because the ideas, methods and the tools of thought from one discipline become re-applied in others. Sadly, it is also the case that many subject areas develop specialised vocabularies and concepts and indeed may also approach more general problems in fairly narrow subject-specific ways. As a result barriers develop between disciplines that prevent the free flow of ideas and the collaborations that could often bring success. This workshop is intended to break down such barriers. This volume contains papers written by researchers in the many varied disciplines that are actively investigating visual representations and interpretations.

Computer Vision has now reached a level of maturity that allows us not only to perform research on individual methods but also to build fully integrated computer vision systems of a signi cant complexity. This opens up a number of new problems related to architectures, systems integration, validation of - stems using benchmarking techniques, and so on. So far, the majority of vision conferences have focused on component technologies, which has motivated the organization of the First International Conference on Computer Vision Systems (ICVS). It is our hope that the conference will allow us not only to see a number of interesting new vision techniques and systems but hopefully also to de ne the research issues that need to be addressed to pave the way for more wide-scale use of computer vision in a diverse set of real-world applications. ICVS is organized as a single-track conference consisting of high-quality, p- viously unpublished, contributed papers on new and original research on c- puter vision systems. All contributions will be presented orally. A total of 65 papers were submitted for consideration by the conference. All papers were - viewed by three reviewers from the program committee. Thirty-two of the papers were selected for presentation. ICVS'99 is being held at the Alfredo Kraus Auditorium and Convention Centre, in Las Palmas, on the lovely Canary Islands, Spain. The setting is spri- like, which seems only appropriate as the basis for a new conference.

C 2 - E C - (EC '99) , $ % & , E , % 26 29, 1999. + . + 1997. + % % - , , , , % . A % % , - , , ? % % % % . 35 % . E % % . B % - 17 % . % . + , - , , , , , . % % . F , ? % . F, % % . % % % : . C , . D ,;. D, F. F , <. < , E. = ,. = , >. . A . ? % A% % @ - >; C @ . A & % % % ?- @ - F . % B . 1999 E Program Co Chairs E . UniversityofYork,UK UniversityofVenice,Italy Program Committee B INRIA,France B UniversityofBonn,Germany F InstitutoSuperiorTecnico,Portugal D < NewYorkUniversity,USA A . MichiganStateUniversity,USA % UniversityofSurrey,UK @ . > NanyangTechnologicalUniversity,Singapore UniversityofSurrey,UK A YaleUniversity,USA @ McGillUniversity,Canada @ $ TheWeizmannInstituteofScience,Israel > UniversityofNewMexico,USA A >. & Smith KettlewellEyeResearchInstitute,USA INRIA,France @ . YaleUniversity,USA

The contributions in this volume give an overview of state-of-the-art results presented at the Workshop on 3D Structure from Multiple Images of Lar- scale Environments (SMILE). This workshop was held in conjunction with the Fifth European Conference on Computer Vision 1998 in Freiburg, Germany. SMILE was a joint e ort of the European ACTS projects VANGUARD and PANORAMA and the Esprit projectCUMULI, all of which are involved in the analysis and reconstruction of 3D scenes from image sequences. The potential for 3D reconstructions of scenes and objects is tremendous. Much of the work reported here is to be seen especially against the background of a convergence between computer vision and computer graphics, and of a shift from signal-based to content-based image analysis in telecommunications. - cordingly, the requirementsfor 3D modelsand acquisitionsystemsarealso shi- ing. Visualization rather than mensuration is the primary issue. The perceptual qualityofthe models, the?exibility ofthe acquisition, andthe costofthe system are three driving forces in the search for new methods. The last few years have seen important steps toward genuine ?exibility. A case in point is the use of multiple images to generate 3D models, without an explicit knowledgeof the relativeposition of the camerasor the camera settings. The same developments also hold good promise to make 3D acquisition cheaper and more widely availab

Image-based rendering, as an area of overlap between computer graphics and computer vision, uses computer vision techniques to aid in sythesizing new views of scenes. Image-based rendering methods are having a substantial impact on the field of computer graphics, and also play an important role in the related field of multimedia systems, for applications such as teleconferencing, remote instruction and surgery, virtual reality and entertainment.
The book develops a novel way of formalizing the view synthesis problem under the full perspective model, yielding a clean, linear warping equation. It shows new techniques for dealing with visibility issues such as partial occlusion and "holes." Furthermore, the author thoroughly re-evaluates the requirements that view synthesis places on stereo algorithms and introduces two novel stereo algorithms specifically tailored to the application of view synthesis.

This computer vision textbook describes the reconstruction of object surfaces and the analysis of distances between camera and objects. Main topics are static and dynamic stereo analysis, shape from shading, photometric stereo analysis, and structured illumination. The selected procedures, e.g., complex algorithms as Tsai calibration, Frankot-Chellapa depth map generation, or Lee-Rosenfield shape from shading, are discussed at a detailed level such that implementations can follow the given descriptions. Fundamentals are given for these application oriented approaches with respect to camera modeling and calibration, to geometric surface modeling, and to surface reflectance models. New research and laboratory results in shape reconstruction and depth analysis, e.g., based on color images have been included. The text is suitable for graduate courses in computer science, in several engineering disciplines, or in applied mathematics. Theoretical and applied excercises accompany each chapter.

Written by world-renowned authors, this unique compendium presents the most updated progress in pattern recognition and computer vision (PRCV), fully reflecting the strong international research interests in the artificial intelligence arena.Machine learning has been the key to current developments in PRCV. This useful comprehensive volume complements the previous five editions of the book. It places great emphasis on the use of deep learning in many aspects of PRCV applications, not readily available in other reference text.

This two-volume set constitutes the refereed proceedings of the 5th European Conference on Computer Vision, ECCV'98, held in Freiburg, Germany, in June 1998.
The 42 revised full papers and 70 revised posters presented were carefully selected from a total of 223 papers submitted. The papers are organized in sections on multiple-view geometry, stereo vision and calibration, geometry and invariances, structure from motion, colour and indexing, grouping and segmentation, tracking, condensation, matching and registration, image sequences and video, shape and shading, motion and flow, medical imaging, appearance and recognition, robotics and active vision, and motion segmentation.

These two volumes constitute the refereed proceedings of the Third Asian Conference on Computer Vision, ACCV'98, held in Hong Kong, China, in January 1998. The volumes present together a total of 58 revised full papers and 112 revised posters selected from over 300 submissions. The papers are organized in topical sections on biometry, physics-based vision, color vision, robot vision and navigation, OCR and applications, low-level processing, active vision, face and hand posture recognition, segmentation and grouping, computer vision and virtual reality, motion analysis, and object recognition and modeling.

Computer vision solutions used to be very specific and difficult to adapt to different or even unforeseen situations. The current development is calling for simple to use yet robust applications that could be employed in various situations. This trend requires the reassessment of some theoretical issues in computer vision. A better general understanding of vision processes, new insights and better theories are needed. The papers selected from the conference staged in Dagstuhl in 1996 to gather scientists from the West and the former eastern-block countries address these goals and cover such fields as 2D images (scale space, morphology, segmentation, neural networks, Hough transform, texture, pyramids), recovery of 3-D structure (shape from shading, optical flow, 3-D object recognition) and how vision is integrated into a larger task-driven framework (hand-eye calibration, navigation, perception-action cycle).

These two volumes constitute the refereed proceedings of the Third Asian Conference on Computer Vision, ACCV'98, held in Hong Kong, China, in January 1998. The volumes present together a total of 58 revised full papers and 112 revised posters selected from over 300 submissions. The papers are organized in topical sections on biometry, physics-based vision, color vision, robot vision and navigation, OCR and applications, low-level processing, active vision, face and hand posture recognition, segmentation and grouping, computer vision and virtual reality, motion analysis, and object recognition and modeling.

This two-volume set constitutes the refereed proceedings of the 5th European Conference on Computer Vision, ECCV'98, held in Freiburg, Germany, in June 1998.
The 42 revised full papers and 70 revised posters presented were carefully selected from a total of 223 papers submitted. The papers are organized in sections on multiple-view geometry, stereo vision and calibration, geometry and invariances, structure from motion, colour and indexing, grouping and segmentation, tracking, condensation, matching and registration, image sequences and video, shape and shading, motion and flow, medical imaging, appearance and recognition, robotics and active vision, and motion segmentation.

The collection of articles presented here, emerged from the Block Island Workshop on Vision and Control that brought together pioneering researchers from around the world. Discussions of new theoretical developments and the empirical validation of techniques and applications, are recorded in this book. Over recent years, robotics, computer vision and control theory researchers have addressed theoretical issues of: real-time vision, visual tracking, the active focus of attention and vision-based control of motion. At the same time, these theoretical insights have been used in applications such as: vision-based autonomous driving, vision-based grasping, human-computer interfaces, control of MEMS systems and medical image processing. From this book the reader will gain an overview of the latest thinking in vision and control, as well as an introduction to many of the techniques used in this area.

The book constitutes the refereed proceedings of the International Workshop on Algebraic Frames for the Perception-Action Cycle, AFPAC '97, held in Kiel, Germany, in September 1997.
The volume presents 12 revised full papers carefully reviewed and selected for inclusion in the book. Also included are 10 full invited papers by leading researchers in the area providing a representative state-of-the-art assessment of this rapidly growing field. The papers are organized in topical sections on PAC systems, low level and early vision, recognition of visual structure, processing of 3D visual space, representation and shape perception, inference and action, and visual and motor neurocomputation.

This book constitutes the refereed proceedings of the First International Conference on Scale-Space Theory for Computer Vision, Scale-Space '97, held in Utrecht, The Netherlands, in July 1997.
The volume presents 21 revised full papers selected from a total of 41 submissions. Also included are 2 invited papers and 13 poster presentations. This book is the first comprehensive documentation of the application of Scale-Space techniques in computer vision and, in the broader context, in image processing and pattern recognition.

This book constitutes the refereed proceedings of the International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, EMMCVPR'97, held in Venice, Italy, in May 1997.
The book presents 29 revised full papers selected from a total of 62 submissions. Also included are four full invited papers and a keynote paper by leading researchers. The volume is organized in sections on contours and deformable models, Markov random fields, deterministic methods, object recognition, evolutionary search, structural models, and applications. The volume is the first comprehensive documentation of the application of energy minimization techniques in the areas of compiler vision and pattern recognition.

OpenVX is the computer vision API adopted by many high-performance processor vendors. It is quickly becoming the preferred way to write fast and power-efficient code on embedded systems. OpenVX Programming Guidebook presents definitive information on OpenVX 1.2 and 1.3, the Neural Network, and other extensions as well as the OpenVX Safety Critical standard. This book gives a high-level overview of the OpenVX standard, its design principles, and overall structure. It covers computer vision functions and the graph API, providing examples of usage for the majority of the functions. It is intended both for the first-time user of OpenVX and as a reference for experienced OpenVX developers.

This book constitutes the refereed proceedings of the First International Conference on Audio- and Video-based Biometric Person Authentication, AVBPA'97, held in Crans-Montana, Switzerland, in March 1997.
The 49 revised papers presented were carefully reviewed and selected by the program committee for inclusion in the book; also included are four invited contributions. The papers are organized in sections on facial features localisation, lip and facial motion, visual non-face biometrics, face-based authentication, text-dependent speaker authentication, text-independent authentication, audio-video features and fusion, and systems and applications.

This book presents the theoretical aspects and practical development of a computer vision system for searching an image for a specified model object; this system is reliable, tolerates imperfections in the image and model, and is fast enough for real-world applications.
A number of search techniques are evaluated. The capabilities of the author's image search system are demonstrated on a variety of examples, and applications using it to track moving objects and navigate mobile robots are shown. This book is essential reading for anybody interested in model-based object recognition.

Progress in Gestural Interaction contains papers presented at the first Gesture Workshop, which was designed to bring together researchers working on gesture-based interfaces and gestural interaction and to provide a forum for the presentation and exchange of ideas and research currently in progress. It encompassed all aspects of gestural interaction, including:- what are gestures?; appropriateness of gestures used in interfaces; interactional issues; suitable applications; sign-language recognition. Papers are presented from the UK, France, Germany, Italy, USA and Ireland to provide an international viewpoint and the book will be of interest to researchers in the fields of gestural interaction, human-computer interaction, multi-modal interfaces, automatic sign language interpretation and pattern recognition. It could also be a useful supplementary text for courses on multi-modal human-computer interaction.

This book constitutes the strictly refereed post-workshop proceedings of the second International Workshop on Object Representation in Computer Vision, held in conjunction with ECCV '96 in Cambridge, UK, in April 1996.
The 15 revised full papers contained in the book were selected from 45 submissions for presentation at the workshop. Also included are three invited contributions based on the talks by Takeo Kanade, Jan Koenderink, and Ram Nevatia as well as a workshop report by the volume editors summarizing several panel discussions and the general state of the art in the area.