- Paperback: 670 pages
- Publisher: Cambridge University Press; 2 edition (April 19, 2004)
- Language: English
- ISBN-10: 0521540518
- ISBN-13: 978-0521540513
- Product Dimensions: 6.8 x 1.4 x 9.7 inches
- Shipping Weight: 4.1 pounds (View shipping rates and policies)
- Average Customer Review: 27 customer reviews
- Amazon Best Sellers Rank: #242,980 in Books (See Top 100 in Books)
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
Multiple View Geometry in Computer Vision 2nd Edition
Use the Amazon App to scan ISBNs and compare prices.
Frequently bought together
Customers who bought this item also bought
Customers who viewed this item also viewed
"The authors have succeeded very well in describing the main techniques in mainstream multiple view geometry, both classical and modern, in a clear and consistent way....I heartily recommend this book." Computing Reviews
A basic problem in computer vision is to understand the structure of a real world scene given several images of it. Recent major developments in the theory and practice of scene reconstruction are described in detail in a unified framework. The book covers the geometric principles and how to represent objects algebraically so they can be computed and applied. The authors provide comprehensive background material and explain how to apply the methods and implement the algorithms directly.
Top customer reviews
There was a problem filtering reviews right now. Please try again later.
When I began working on 3D surface reconstruction 5 years ago, I had close to zero background on stereophotogrammetry, or even in projective geometry, however I had good background in linear algebra, image processing using matlab, and Engineering. It was painful to read through the book the first time because 1) I had very little background of the particular topic, 2) like one of the other reviewer said: " this book just seems more focused on providing complete proofs than giving you a feel for how you would approach a real problem". But later on when I had more deeper knowledge of this research field, I have to disagree with that comments. There are significant amount of algorithms presented in this book. When I finished reading the book the first time, I was frustrated because I am not very clear on where is a practical solution for the problem. Then I read some other books such as Introductory Techniques for 3-D Computer Vision. That book is a good start and did help me making a better understanding of the 3D surface reconstruction techniques. But it doesn't cover the research topic thoroughly like Hartley and Zisserman's book on stereophotogrammetry. It is very important to follow through the proofs to obtain a clear picture of solving problems and implementing algorithms presented in Hartley and Zisserman's book.
And this book provides clear and easily implemented algorithms in both matlab and C++ (with help from open source libraries such as openCV).
I taught a similar course again at IIT Gandhinagar last semester. This book is really a treasure as the algorithms mentioned can be implemented with minimal effort. Students would love the way the material is presented in the book. But one has to use other books for covering topics related to feature detection and description (SIFT, SURF etc). That connection is missing in this book.