Computer vision is a rapidly growing field which aims to make computers 'see' as effectively as humans. In this book, Shapiro presents a new framework of computer vision for interpreting time-varying imagery. This is an important task, since movement reveals valuable information about the environment. The author's fully-automated system operates on long, monocular image sequences containing multiple, independently-moving objects, and demonstrates the practical feasibility of recovering scene structure and motion in a bottom-up fashion. The author gives real and synthetic examples throughout, with particular emphasis on image coding applications. He derives novel theory in the context of the affine camera, a generalization of the familiar scaled orthographic model. Graduate students and researchers in robotics and computer science will benefit from this book.