Product Description

This book gives senior undergraduate and beginning graduate students and researchers in computer vision, applied mathematics, computer graphics, and robotics a self-contained introduction to the geometry of 3D vision; that is the reconstruction of 3D models of objects from a collection of 2D images. Following a brief introduction, Part I provides background materials for the rest of the book. The two fundamental transformations, namely rigid body motion and perspective projection are introduced and image formation and feature extraction discussed. Part II covers the classic theory of two view geometry based on the so-called epipolar constraint. Part III shows that a more proper tool for studying the geometry of multiple views is the so- called rank considtion on the multiple view matrix. Part IV develops practical reconstruction algorithms step by step as well as discusses possible extensions of the theory. Exercises are provided at the end of each chapter. Software for examples and algorithms are available on the author's website.

Product Details

• Amazon Sales Rank: #161492 in Books
• Published on: 2005-06-17
• Original language: English
• Number of items: 1
• Binding: Hardcover
• 552 pages

Review

From the reviews:

"Computer vision is invading our daily lives … . Covering all the aspects would be too vast an area to cover in one book, so here, the authors concentrated on the specific goal of recovering the geometry of a 3D object … . The 22 pages of references form a good guide to the literature. The authors found an excellent balance between a thorough mathematical treatment and the applications themselves. … the text will be a pleasure to read for students … ." (Adhemar Bultheel, Bulletin of the Belgian Mathematical Society, Vol. 12 (2), 2005)

"This is primarily a textbook of core principles, taking the reader from the most basic concepts of machine vision … to detailed applications, such as autonomous vehicle navigation. … It is a clearly written book … . Everything that is required is introduced … . an entirely self-contained work. … The book is aimed at graduate or advanced undergraduate students in electrical engineering, computer science, applied mathematics, or indeed anyone interested in machine vision … . is highly recommended." (D.E. Holmgren, The Photogrammetric Record, 2004)

"This very interesting book is a great book teaching how to go from two-dimensional (2D)-images to three-dimensional (3D)-models of the geometry of a scene. … A good part of this book develops the foundations of an appropriate mathematical approach necessary for solving those difficult problems. … Exercises (drill exercises, advanced exercises and programming exercises) are provided at the end of each chapter." (Hans-Dietrich Hecker, Zentralblatt MATH, Vol. 1043 (18), 2004)

"This book gives senior undergraduate and beginning graduate students and researchers in computer vision, applied mathematics, computer graphics, and robotics a self-contained introduction to the geometry of 3D vision. That is the reconstruction of 3D models of objects from a collection of 2D images. … Exercises are provided at the end of each chapter. Software for examples and algorithms are available on the author’s website." (Daniel Leitner, Simulation News Europe, Vol. 16 (1), 2006)

Customer Reviews

Good 3-D vision book with emphasis on applications
I really liked this book. However, I use it for vision issues as they relate to robotics rather than as an introductory text on 3D vision. If a general or introductory textbook on 3D computer vision is what you desire, then you might be better off with "Multiple View Geometry in Computer Vision" by Hartley or my personal favorite, "Introductory Techniques for 3-D Computer Vision" by Trucco and Verri. For individuals studying robotic vision, many parts of this book are useful not only for characterizing vision, but for putting together algorithms and equations that are useful for describing robotic motion in general. For example, chapter two of the book collects equations and algorithms that are very useful in describing forward kinematics. Chapters five through ten cover all of the considerations and algorithms needed to produce a 3D image from a collection of images taken from different viewpoints. Chapter eleven applies this knowledge with sequential instructions on building a 3D image from a group of images. Chapter twelve has a second application that shows how to perform autonomous control of a moving vehicle via video feedback. The appendices have some very good information on linear algebra as it relates to computer vision as well as details on the Kalman filter, which is also of great interest to those of us who are interested in computational robotics. Algorithms are blocked out and explained in logical steps throughout the book, and it also has very good exercises at the end of each chapter as well as short examples throughout each chapter, although the notation can sometimes be a little confusing. I would therefore recommend this book especially to those readers who are interested in merging their knowledge of robotics with their knowledge of basic computer vision into creating sophisticated applications. However, this book is by no means an introduction to computer vision. The table of contents is as follows:
Ch 1 - Introduction
Ch 2 - Representation of a 3D Moving Scene
Ch 3 - Image Formation
Ch 4 - Image Primitives and Correspondence
Ch 5 - Reconstruction from Two Calibrated Views
Ch 6 - Reconstruction from Two Uncalibrated Views
Ch 7 - Segmentation of Multiple Moving Objects from Two Views
Ch 8 - Multiple View Geometry of Points and Lines
Ch 9 - Extension to General Incidence Relations
Ch 10- Geometry and Reconstruction From Symmetry
Ch 11- Step by Step Building of a 3D Model from Images
Ch 12- Visual Feedback

A Poor Rewrite of the book: Multiple View Geometry, by Hartley & Zisserman
This is a poor rewrite of a much better book, Multiple View Geometry in Computer Vision, by Hartley & Zisserman. It fails to clarify any of the more difficult concepts presented by Hartley & Zisserman and is far less complete in the treatment of the subject matter. I can not recommend this book when a better written, more thorough treatment is already available from Hartley & Zisserman.

a must-have book for computer vision students & researchers
The authors do an outstanding job of balancing theory and practice in this book. In particular, Ch. 11 (Step-by-Step Building of a 3-D Model from Images) is a gem. The new student of computer vision that finds Structure from Motion (SFM) daunting should read this chapter first to build motivation by means of seeing concrete examples.
What's most notable about this book is its thoroughness. The authors humbly get their hands dirty with crucial low-level matters like interest point detection and feature tracking. In Ch. 5 and 6 (calibrated and uncalibrated reconstruction) you'll get an excellent treatment of the necessary background in these areas, along with numerous new insights and `nuggets.' This is particularly true in their treatment of homographies. Ch. 2 has all the material on rigid body motion and the exponential map that students used to need to get from Murray, Li and Sastry, once again with substantial added value.
The exercises in all the chapters are very well thought out, and they -- together with the clearly written Algorithm Boxes -- greatly simplify the job of the instructor. (I am currently using this as the text for my graduate level class this quarter.) The appendices (especially the one on Linear Algebra) also help to make this a self-contained resource for SFM.
I haven't gotten into the material on multi-body motion and n>2 views, so I can't comment on those parts(...)In summary, this is a great book, well worth the money.