Customer Reviews

Robot Vision (MIT Electrical Engineering and Computer Science)

5 star:		(6)
4 star:		(0)
3 star:		(0)
2 star:		(0)
1 star:		(0)

 

 

When I first picked up Robot Vision, I was a bit concerned at the age of the book: the field of computer/machine/robot vision progresses at a fantastic pace, and it would seem a given that such a book would be so out of date as to be useless.

However, while this book might not reflect the latest research, especially the tight interweaving of computer graphics and computer vision as exists now or in areas such as active vision, it is a rich presentation of the core ideas of machine vision. In particular, it provides a mathematically rigorous presentation, focusing on core notions of geometric optics and calibration, as well as classic approaches to segmentation, edge detection, signal filtering, and the like.

I would strongly suggest this book as a text that every serious computer vision, robotics, or computer graphics researcher should own; of course, it isn't the _only_ book you should own, and the bibliography certainly won't let you in on the latest trends in vision. Nonetheless, I think the book is so well written that it will remain useful for many years to come.

This book does a good job of introducing the readers to the basics of computer vision - it really has nothing to do with robots outside of the last chapter, other than if you build one and need to give it vision capabilities, you need to know the information in this book. Physics equations via calculus and ODE are used to describe how light intereacts with solid objects and also with image sensors, the latter tieing in to the subject of robot vision. Therefore, the reader should have a good knowledge of first-year university physics as well as multi-variable calculus. As a reference for the geometrical and physical mathematics of light interacting with surfaces and the camera, it is particularly excellent.

Horn does a great job of deriving and providing the equations you need, and brings it all together with excellent narrative and very good illustrations. The book goes all the way from the basics of image formation, to simple matrix operations such as edge detection, to some more advanced topics such as shape from shading. The final chapter, on picking parts out of a bin, uses the ideas developed in previous chapters to come up with the basic design of a robot hand-eye system that is capable of picking up specific parts from a parts bin. It really is a very good unifying capstone to the entire book. The only drawback I can see in the book is that it pretty much stays in the domain of continuous mathematics. There is not much in the way of explicit algorithm steps - the author expects the reader to be able to do that based on his explanation and equations, and given the high quality of the text this is really not too rash of an assumption.

Because of its age it doesn't have some of the more modern techniques and algorithms, but if I had to choose between this older book and that more recently published waste of trees, "Computer Vision: A Modern Approach", give me this book every time. You get a firm foundation in the basics, plus a good understanding of some more advanced topics too.

I have to admit that I read this book many years ago. This is not a book that should be read as a way to keep oneself updated on the latest research in the field. It should be seen as a comprehensive, but systematic introduction to basic machine vision techniques. As such, it is a great book, maybe a classic. Its focus is on such topics as Binary Image Processing, Optics, Image formation, Transforms, Filtering, Stereo vision, Optical flow, Noise reduction, etc. It is well organized, and it covers the fundamentals of many useful techniques.

If anyone wants to learn the basics of Computer Vision, this book must be the starting point. No other go.. This speaks of the exceptional treatment of the concepts in this classic book. I very strongly recommend this indispensible book to anyone who wants to learn Computer Vision.

A classic book covering all the fundmentals. Recommend to those who want to know something about vision before doing some real research.

This book is a classic, I knew what I was getting, mid 90's mathmatical review of vision within robotic guidance technology. The impressive part of this order was the books condition New as advertised and the seller packed it well with easy to read address and return. Bottom line is Amazon provides a great service to a some high caliber providers of stuff we need and want. Well done by all.
Dennis