Over the last forty years, researchers have made great strides in elucidating the laws of image formation, processing, and understanding by animals, humans, and machines. This book describes the state of knowledge in one subarea of vision, the geometric laws that relate different views of a scene. Geometry, one of the oldest branches of mathematics, is the natural language for describing three-dimensional shapes and spatial relations. Projective geometry, the geometry that best models image formation, provides a unified framework for thinking about many geometric problems relevant to vision. The book formalizes and analyzes the relations between multiple views of a scene from the perspective of various types of geometries. A key feature is that it considers Euclidean and affine geometries as special cases of projective geometry.
Images play a prominent role in computer communications. Producers and users of images, in particular three-dimensional images, require a framework for stating and solving problems. The book offers a number of conceptual tools and theoretical results useful for the design of machine vision algorithms. It also illustrates these tools and results with many examples of real applications.
About the Authors
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).
Quang-Tuan Luong is a computer scientist in the Artifical Intelligence Center at SRI International, California.
"This is a novel, well-written, thorough presentation of a topic of clear interest in the computer vision field."--Eric Grimson, Bernard Gordon Professor of Medical Engineering, MIT
"This is an excellent book that will be widely read and should serve as a useful reference for the machine vision and computer graphics communities."--Seth Teller, Laboratory of Computer Science, MIT