This book presents fast and reliable algorithms for dense stereo matching - for every point on the image - and optical-flow estimations using a general language, such as C, optimize computations in an existing processor.

An ongoing effort is being made in the field of computer vision to refine algorithms for optimal/better performance, which can mean reliability and increased computational speed. Such fast algorithms are becoming increasingly important for tele-reality, interactive media and visual serving applications. This book presents some fast and reliable algorithms for dense stereo matching and optical-flow estimations. Techniques described include: fast algorithms for similarity measure, use of subregioning technique to expedite similarity calculation, multiresolution scheme, fast 3-D surface technique for stereo matching, and stereo matching using warping.

Author hosts Fast Stereo Matching Demo website Author is widely-published leader in the field

Inhalt

Introduction.- Stereo vision.- Fast calculation of similarity measures.- Rectangular subregioning.- Multi-resolution Scheme.- Fast stereo matching.- Stereo matching using 3-D surface.- Stereo matching using warping.- Panoramic stereo matching.- Fast optical flow.- Discussions on reliability and speed.- Applications.