Visual Motion of Curves and Surfaces [Paperback]

This book describes how to reconstruct 3D surfaces from images, using geometry, with applications to computer vision.Computer vision aims to detect and reconstruct features of surfaces from images. This book describes how the 3D shape of surfaces can be recovered from image sequences of 'outlines'. It provides all the necessary background in differential geometry (assuming knowledge of elementary algebra and calculus) and in the analysis of visual motion, emphasising intuitive visual understanding of the geometric techniques with computer-generated illustrations. It also gives a thorough introduction to the mathematical techniques and the details of the implementations, and applies the methods to data from real images.Computer vision aims to detect and reconstruct features of surfaces from images. This book describes how the 3D shape of surfaces can be recovered from image sequences of 'outlines'. It provides all the necessary background in differential geometry (assuming knowledge of elementary algebra and calculus) and in the analysis of visual motion, emphasising intuitive visual understanding of the geometric techniques with computer-generated illustrations. It also gives a thorough introduction to the mathematical techniques and the details of the implementations, and applies the methods to data from real images.The world is full of objects, many of which are visible to us as surfaces. Examples are people, cars, machines, computers and bananas. Exceptions are such things as clouds and trees, which have a more detailed, fuzzy structure. Computer vision aims to detect and reconstruct features of surfaces from the images produced by cameras, in some ways mimicking the way in which humans reconstruct features of the world around them by using their eyes. This book describes how the 3D shape of surfaces can be recovered from image sequences of outlines. Cipolla and Giblin provide all the necessary background in differential geometry (assuming knowledge of elementarl3+