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.

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.

This book provides a modern, algorithmic introduction to digital image p- cessing, designed to be used both by learners desiring a ?rm foundation on which to build and practitioners in search of critical analysis and modern - plementations of the most important techniques. This updated and enhanced paperbackedition ofourcomprehensivetextbookDigital Image Processing: An Algorithmic Approach Using Java packages the original material into a series of compactvolumes, therebysupporting a ?exiblesequenceofcoursesindigital image processing. Tailoring the contents to the scope of individual semester courses is also an attempt to provide a?ordable (and "backpack-compatible") textbooks without comprimising the quality and depth of content. Oneapproachtolearninganewlanguageistobecomeconversantinthecore vocabulary and to start using it right away. At ?rst, you may only know how to ask for directions, order co?ee, and so on, but once you become con?dent with the core, you will start engaging others in "conversations" and rapidly learn how to get things done. This step-by-step approach works equally well in many areas of science and engineering. In this ?rst volume, ostentatiously titled Fundamental Techniques,wehave attemptedtocompilethecore"vocabulary" ofdigitalimageprocessing,starting from the basic concepts and elementary properties of digital images through simple statistics and point operations, fundamental ? ltering techniques, loc- ization of edges and contours, and basic operations on color images. Mastering these most commonly used techniques and algorithms will enable you to start being productive right away.

This modern, self-contained textbook provides an accessible introduction to the field from the perspective of a practicing programmer, supporting a detailed presentation of the fundamental concepts and techniques with practical exercises and fully worked out implementation examples. This much-anticipated 3rd edition of the definitive textbook on Digital Image Processing has been completely revised and expanded with new content, improved illustrations and teaching material. Topics and features: Contains new chapters on fitting of geometric primitives, randomized feature detection (RANSAC), and maximally stable extremal regions (MSER). Includes exercises for most chapters and provides additional supplementary materials and software implementations at an associated website. Uses ImageJ for all examples, a widely used open source imaging environment that can run on all major platforms. Describes each solution in a stepwise manner in mathematical form, as abstract pseudocode algorithms, and as complete Java programs that can be easily ported to other programming languages. Presents suggested outlines for a one- or two-semester course in the preface. Advanced undergraduate and graduate students will find this comprehensive and example-rich textbook will serve as the ideal introduction to digital image processing. It will also prove invaluable to researchers and professionals seeking a practically focused self-study primer.

This is the second volume of a book series that provides a modern, algori- mic introduction to digital image processing. It is designed to be used both by learners desiring a ?rm foundation on which to build and practitioners in search of critical analysis and modern implementations of the most important techniques. This updated and enhanced paperback edition of our compreh- sive textbook Digital Image Processing: An Algorithmic Approach Using Java packages the original material into a series of compact volumes, thereby s- porting a ?exible sequence of courses in digital image processing. Tailoring the contents to the scope of individual semester courses is also an attempt to p- vide a?ordable (and "backpack-compatible") textbooks without comprimising the quality and depth of content. This second volume, titled Core Algorithms, extends the introductory - terial presented in the ?rst volume (Fundamental Techniques) with additional techniques that are, nevertheless, part of the standard image processing to- box. A forthcomingthird volume(Advanced Techniques) will extendthis series and add important material beyond the elementary level, suitable for an - vanced undergraduate or even graduate course.

Der "Klassiker" der Bildverarbeitung liefert eine fundierte und anwendungsgerechte Einfuhrung in die wichtigsten Methoden und in ausgewahlte Verfahren. Seine besondere Starke: grosse Detailgenauigkeit, prazise algorithmische Beschreibung sowie die unmittelbare Verbindung zwischen mathematischer Beschreibung und konkreter Implementierung. UEbungsaufgaben und Code-Beispiele runden die Darstellungen ab. Source Code und erganzende Materialien finden sich auf der Internetseite www.imagingbook.com. Die Neuauflage wurde uberarbeitet und erweitert.