Computer Vision - ECCV '96: Fourth European Conference on Computer Vision, Cambridge, UK April 14-18, 1996. Proceedings, Volume II [Paperback]

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.Colour constancy for scenes with varying illumination.- Color angular indexing.- Bidirectional reflection distribution function expressed in terms of surface scattering modes.- Generalizing Lambert's Law for smooth surfaces.- Local scale control for edge detection and blur estimation.- Regularization, scale-space, and edge detection filters.- Direct differential range estimation using optical masks.- Generalised epipolar constraints.- Object models from contour sequences.- Directions of motion fields are hardly ever ambiguous.- Euclidean reconstruction: From paraperspective to perspective.- Optical flow and phase portrait methods for environmental satellite image sequences.- Refinement of optical flow estimation and detection of motion edges.- Reliable extraction of the camera motion using constraints on the epipole.- Accuracy vs. efficiency trade-offs in optical flow algorithms.- Rigorous bounds for two-frame structure from motion.- The rank 4 constraint in multiple (?3) view geometry.- Using singular displacements for uncalibrated monocular visual systems.- Duality of multi-point and multi-frame geometry: Fundamental shape matrices and tensors.- On the appropriateness of camera models.- Ground plane motion camera models.- Snakes and splines for tracking non-rigid heal³x