Appropriate for upper-division undergraduate and graduate level courses in computer vision found in departments of computer science, computer engineering and electrical engineering, this book offers a treatment of modern computer vision methods. This accessible presentation gives both a general view of the computer vision enterprise and also offers detail for students aiming to build applications. The various topics included either reflect practical significance or are of theoretical relevance, providing a synthesis of viewpoints and techniques for building applications. Application surveys describe application areas such as image-based rendering and digital libraries. Algorithms are broken down and illustrated in pseudo code, and worked examples, exercises, programming assignments, and illustrations are integrated throughout the text. Each copy of the text includes a CD-ROM, which contains the source code for programming assignments, colour images, and illustrative movies.

Table of Contents

I. IMAGE FORMATION AND IMAGE MODELS. 1. Cameras. 2. Geometric Camera Models. 3. Geometric Camera Calibration. 4. Radiometry - Measuring Light. 5. Sources, Shadows and Shading. 6. Color. II. EARLY VISION: JUST ONE IMAGE. 7. Linear Filters. 8. Edge Detection. 9. Texture. III. EARLY VISION: MULTIPLE IMAGES. 10. The Geometry of Multiple Views. 11. Stereopsis. 12. Affine Structure from Motion. 13. Projective Structure from Motion. IV. MID-LEVEL VISION. 14. Segmentation By Clustering. 15. Segmentation By Fitting a Model. 16. Segmentation and Fitting Using Probabilistic Methods. 17. Tracking with Linear Dynamic Models. V. HIGH-LEVEL VISION: GEOMETRIC MODELS. 18. Model-Based Vision. 19. Smooth Surfaces and Their Outlines. 20. Aspect Graphs. 21. Range Data. VI. HIGH-LEVEL VISION: PROBABILISTIC AND INFERENTIAL METHODS. 22. Finding Templates Using Classifiers. 23. Recognition By Relations Between Templates. 24. Geometric Templates From Spatial Relations. VII. APPLICATIONS. 25. Application: Finding in Digital Libraries. 26. Application: Image-Based Rendering.

About the Author

David A. Forsyth received the D.Phil. degree in computer science from Oxford University. He is currently a Professor in the Computer Science Division at the University of California at Berkeley. He has co-authored over eighty technical papers on computer vision, computer graphics and machine learning and has co-edited two books. Jean Ponce received the Ph.D. degree in Computer Science from the University of Paris Orsay. He is currently a Professor in the Department of Computer Science and the Beckman Institute at the University of Illinois at Urbana Champaign. Professor Ponce has written over a hundred conference and journal papers and co-edited two books on a range of subjects including computer vision and robotics.