The European Conference on Computer Vision (ECCV) has established itself as a major event in this exciting and very active field of research and development. These refereed two-volume proceedings include the 123 papers accepted for presentation at the 4th ECCV, held in Cambridge, UK, in April 1996; these papers were selected from a total of 328 submissions and together give a well-balanced reflection of the state of the art in computer vision.
The papers in volume II are grouped in sections on color vision and shading; image features; motion; medical applications; tracking; applications and recognition; calibration, focus, and optics; applications; and structure from motion.

The European Conference on Computer Vision (ECCV) has established itself as a major event in this exciting and very active field of research and development. These refereed two-volume proceedings include the 123 papers accepted for presentation at the 4th ECCV, held in Cambridge, UK, in April 1996; these papers were selected from a total of 328 submissions and together give a well-balanced reflection of the state of the art in computer vision.
The papers in volume I are grouped in sections on structure from motion; recognition; geometry and stereo; texture and features; tracking; grouping and segmentation; stereo; and recognition, matching, and segmentation.

This book describes experimental advances made in the interpretation of visual motion over the last few years that have moved researchers closer to emulating the way in which we recover information about the surrounding world. If robots are to act intelligently in everyday environments, they must have a perception of motion and its consequences. This book describes experimental advances made in the interpretation of visual motion over the last few years that have moved researchers closer to emulating the way in which we recover information about the surrounding world. It describes algorithms that form a complete, implemented, and tested system developed by the authors to measure two-dimensional motion in an image sequence, then to compute three-dimensional structure and motion, and finally to recognize the moving objects. The authors develop algorithms to interpret visual motion around four principal constraints. The first and simplest allows the scene structure to be recovered on a pointwise basis. The second constrains the scene to a set of connected straight edges. The third makes the transition between edge and surface representations by demanding that the wireframe recovered is strictly polyhedral. And the final constraint assumes that the scene is comprised of planar surfaces, and recovers them directly. Contents Image, Scene, and Motion * Computing Image Motion * Structure from Motion of Points * The Structure and Motion of Edges * From Edges to Surfaces * Structure and Motion of Planes * Visual Motion Segmentation * Matching to Edge Models * Matching to Planar Surfaces