Experiments in the Machine Interpretation of Visual MotioneBook - 1990
This book describes experimental advances made in the interpretation of visualmotion over the last few years that have moved researchers closer to emulating the way in which werecover information about the surrounding world.
If robots are to act intelligently in everyday environments, they must have aperception of motion and its consequences. This book describes experimental advances made in theinterpretation of visual motion over the last few years that have moved researchers closer toemulating the way in which we recover information about the surrounding world. It describesalgorithms that form a complete, implemented, and tested system developed by the authors to measuretwo-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 visualmotion around four principal constraints. The first and simplest allows the scene structure to berecovered on a pointwise basis. The second constrains the scene to a set of connected straightedges. The third makes the transition between edge and surface representations by demanding that thewireframe recovered is strictly polyhedral. And the final constraint assumes that the scene iscomprised of planar surfaces, and recovers them directly.David W. Murray is University Lecturer inEngineering Science at the University of Oxford and Draper's Fellow in Robotics at St Anne'sCollege, Oxford. Bernard F. Buxton is Senior Research Fellow at the General Electric Company's HirstResearch Centre, Wembley, UK, where he leads the Computer Vision Group in the Long Range ResearchLaboratory.Contents: Image, Scene, and Motion. Computing Image Motion. Structure from Motion ofPoints. 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.
Describes experimental advances made in the interpretation of visual motion over the last few years and presents original algorithms that form a complete, implemented, and tested system to measure two-dimensional motion in an image sequence, compute three-dimensional structure and motion, and recognize the moving objects. Annotation copyright Book News, Inc. Portland, Or.