ebook img

Geometric Invariance in Computer Vision PDF

557 Pages·1992·49.511 MB·English
Save to my drive
Quick download
Download
Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.

Preview Geometric Invariance in Computer Vision

Geometric Invariance in Computer Vision Edited by Joseph L. Mundy and Andrew Zisserman Geometric Invariance in Computer Vision Geometric Invariance in Computer Vision edited by Joseph L. Mundy and Andrew Zisserman The MIT Press Cambridge, Massachusetts London, England © 1992 Massachusetts Institute of Technology All rights reserved. No part of this book may be reproduced in any form by any electronic or mechanical means (including photocopying, recording, or information storage and retrieval) without permission in writing from the publisher. This book was set in by the authors. Camera-ready copy was produced by Chiron, Inc. This book was printed and bound in the United States of America. Library of Congress Cataloging-in-Publication Data Geometric invariance in computer vision / edited by Joseph Mundy, Andrew Zisserman. p. cm. — (Artificial intelligence) "Mainly a result of a joint DARPA-ESPRIT workshop . . . held in Reylgavik, Iceland, March 26-28,1991M—Pref. Includes bibliographical references (p. ) and index. ISBN 0-262-13286-0 1. Computer vision. 2. Invariants. I. Mundy, Joseph L. II. Zisserman, Andrew. III. Series: Artificial intelligence (Cambridge, Mass.) TA1632.G46 1992 621.39’9—dc20 92-1336 CIP 0262132850 MUNDY GEOM INVAR COMP VAR Contents Series Foreword ix Preface xi 1 Introduction — Towards a New Framework for Vision 1 Joseph L. Mundy and Andrew Zisserman 1 FOUNDATIONS Ia ALGEBRAIC INVARIANTS 2 Invariant Theory and Enumerative Combinatorics of Young Tableaux 45 Shreeram S. Abhyankar 3 Geometric Interpretation of Joint Conic Invariants 77 Joseph L. Mundy, Deepak Kapur, Stephen J. Maybank, Patrick Gros and Long Quan 4 An Experimental Evaluation of Projective Invariants 87 Christopher Coelho, Aaron Heller, Joseph L. Mundy, David A. Forsyth and Andrew Zisserman 5 The Projection of Two Non-Coplanar Conics 105 Stephen J. Maybank 6 The Non-Existence of General-Case View-Invariants 120 J. Brian Burns, Richard S. Weiss and Edward M. Riseman Ib invariants of non-algebraic CURVES 7 Noise Resistant Invariants of Curves 135 Isaac Weiss 8 Semi-Differential Invariants 157 Luc J. Van Gool, Theo Moons, Eric Pauwels and Andre Onsterlinrk VI Contents 9 Projective Invariants for Curves in Two and Three Dimensions 193 Michael H. Brill, Eamon B. Barrett and Paul M. Payton 10 Numerical Evaluation of Differential and Semi-Differential Invariants 215 Christopher Brown 11 Recognizing General Curved Objects Efficiently 228 Andrew Zisserman, David A. Forsyth, Joseph L. Mundy and Charles A. Rothwell 12 Fitting Affine Invariant Conics to Curves 252 Deepak Kapur and Joseph L. Mundy 13 Projectively Invariant Decomposition of Planar Shapes 267 Stefan Carlsson Ic INVARIANTS FROM MULTIPLE VIEWS 14 Invariant Linear Methods in Photogrammetry and Model-Matching 277 Eamon B. Barrett, Michael H. Brill, Nils N. Haag and Paul M. Payton 15 Semi-Differential Invariants for Nonplanar Curves 293 Luc J. Van Gool, Michael H. Brill, Eamon B. Barrett, Theo Moons and Eric Pauwels 16 Disambiguating Stereo Matches with Spatio-Temporal Surfaces 310 Olivier Faugeras and Theo Papadopoulo II APPLICATIONS 17 Transformation Invariant Indexing 335 Haim J. Wolfson and Yehezkel Lamdan 18 Affine Invariants for Model-Based Recognition 354 John E. Hopcroft, Daniel P. Huttenlocher and Peter C. Wayner Contents vii 19 Object Recognition Based on Moment (or Algebraic) Invariants 375 Gabriel Taubin and David B. Cooper 20 Fast Recognition Using Algebraic Invariants 398 Charles A. Rothwell, Andrew Zisserman, David A. Forsyth and Joseph L. Mundy 21 Toward 3D Curved Object Recognition from Image Contours 408 Jean Ponce and David J. Kriegman 22 Relative Positioning with Uncalibrated Cameras 440 Roger Mohr, Luce Morin and Enrico Grosso III APPENDIX 23 Appendix — Projective Geometry for Machine Vision 463 Joseph L. Mundy and Andrew Zisserman References 521 List of Contributors 535 Index 538 Series Foreword Artificial intelligence is the study of intelligence using the ideas and methods of computation. Unfortunately, a definition of intelligence seems impossible at the moment because intelligence appears to be an amalgam of so many information processing and information represen¬ tation abilities. Of course psychology, philosophy, linguistics, and related disciplines offer various perspectives and methodologies for studying intelligence. For the most part, however, the theories proposed in these fields are too incomplete and too vaguely stated to be realized in computational terms. Something more is needed, even though valuable ideas, relationships, and constraints can be gleaned from traditional studies of what are, after all, impressive existence proofs that intelligence is in fact possible. Artificial intelligence offers a new perspective and a new methodology. Its central goal is to make computers intelligent, both to make them more useful and to understand the principles that make intelligence possible. That intelligent computers will be extremely useful is obvious. The more profound point is that artificial intelligence aims to understand intelligence using the ideas and methods of computation, thus offering a radically new and different basis for theory formation. Most of the people doing work in artificial intelligence believe that these theories will apply to any intelligent information processor, whether biological or solid state. There are side effects that deserve attention, too. Any program that will successfully model even a small part of intelligence will be inher¬ ently massive and complex. Consequently, artificial intelligence contin¬ ually confronts the limits of computer science technology. The problems encountered have been hard enough and interesting enough to seduce artificial intelligence people into working on them with enthusiasm. It is natural, then, that there has been a steady flow of ideas from artificial intelligence to computer science, and the flow shows no sign of abating. The purpose of this series in artificial intelligence is to provide people in many areas, both professionals and students, with timely, detailed information about what is happening on the frontiers in research centers all over the world. J. Michael Brady Daniel Bobrow Randall Davis

See more

The list of books you might like

Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.