Three-Dimensional Computer Vision (Artificial Intelligence) [Hardcover]

Olivier Faugeras (Author)

Book Description

Publication Date: November 19, 1993 | ISBN-10: 0262061589 | ISBN-13: 978-0262061582

This monograph by one of the world's leading vision researchers provides a thorough, mathematically rigorous exposition of a broad and vital area in computer vision: the problems and techniques related to three-dimensional (stereo) vision and motion. The emphasis is on using geometry to solve problems in stereo and motion, with examples from navigation and object recognition.Faugeras takes up such important problems in computer vision as projective geometry, camera calibration, edge detection, stereo vision (with many examples on real images), different kinds of representations and transformations (especially 3-D rotations), uncertainty and methods of addressing it, and object representation and recognition. His theoretical account is illustrated with the results of actual working programs.Three-Dimensional Computer Vision proposes solutions to problems arising from a specific robotics scenario in which a system must perceive and act. Moving about an unknown environment, the system has to avoid static and mobile obstacles, build models of objects and places in order to be able to recognize and locate them, and characterize its own motion and that of moving objects, by providing descriptions of the corresponding three-dimensional motions. The ideas generated, however, can be used indifferent settings, resulting in a general book on computer vision that reveals the fascinating relationship of three-dimensional geometry and the imaging process.Olivier Faugeras is Research Director of the Computer Vision and Robotics Laboratory at INRIA Sophia-Antipolis and a Professor of Applied Mathematics at the Ecole Polytechnique in Paris.

Editorial Reviews

Review

"A magnificant tour de force. Three-Dimensional Computer Vision deals with an extremely broad and important chunk of computer vision and covers the area with excellent breadth. It provides examples of the described techniques being applied to real images, and it is built on the kind of solid mathematical underpinnings that are essential if the field is to move from the 'black art' stage to a real science. Anyone who claims to be serious about research in this area absolutely must be aware of this work." W. Eric L. Grimson, AI Laboratory, M.I.T.

About the Author

Olivier Faugeras is Research Director and head of a computer vision group at INRIA and Adjunct Professor of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology. He is the author of Three-Dimensional Computer Vision (MIT Press, 1993).

Product Details

• Hardcover: 695 pages
• Publisher: The MIT Press (November 19, 1993)
• Language: English
• ISBN-10: 0262061589
• ISBN-13: 978-0262061582
• Product Dimensions: 9.4 x 8.4 x 2 inches
• Shipping Weight: 3.7 pounds (View shipping rates and policies)
• Average Customer Review: 3.5 out of 5 stars  See all reviews (2 customer reviews)
• Amazon Best Sellers Rank: #362,650 in Books (See Top 100 in Books)
  • #7 in Books > Computers & Technology > Computer Science > Artificial Intelligence > Computer Vision
  • #47 in Books > Computers & Technology > Computer Science > Artificial Intelligence > Theory of Computing
  • #100 in Books > Computers & Technology > Computer Science > Artificial Intelligence > Robotics

More About the Author

Discover books, learn about writers, read author blogs, and more.

Customer Reviews

Most Helpful Customer Reviews

12 of 14 people found the following review helpful:

5.0 out of 5 stars A good introduction to geometry in computer vision., May 26, 2000

By A Customer

This review is from: Three-Dimensional Computer Vision (Artificial Intelligence) (Hardcover)

If you are a beginner in computer vision and can't understand geometry in it, you need a copy of this book. It is the most comprehensive book I have ever seen and answers nearly every question you could have about geometry in computer vision. Especially for those who have familiar with image proceeing. It really coincide with its subtitle "A Geometric Viewpoint". It also emphasize on mathematics and formulate clearly. Before I read the book,I have nothing about the camera calibration and epipolar geometry, now I am familiar with them. I always recommend it to my friends in computer vision. In a word, it is a bible of computer vision.

9 of 14 people found the following review helpful:

2.0 out of 5 stars Not that good, March 6, 2001

By A Customer

This review is from: Three-Dimensional Computer Vision (Artificial Intelligence) (Hardcover)

During my master thesis I read parts of this book. One thing I can say about it, is that if you don't know projective geometry when beginning to read this book, you will not learn it from here. Yes, Faugeras probably has a very intuitive feel for this field of science but he does not explain his ideas in a pedagogical manner. My advise is, read the book and get the idea, then read some other book to do it. Faugeras will not tell you how.

I got this confirmed from two other sources as well, after discovering it myself.