Finding structurally consistent motion correspondences

TitleFinding structurally consistent motion correspondences
Publication TypeConference Papers
Year of Publication1994
AuthorsJacobs DW, Chennubhotla C
Conference NamePattern Recognition, 1994. Vol. 1 - Conference A: Computer Vision Image Processing., Proceedings of the 12th IAPR International Conference on
Date Published1994/10//
Keywords3D, boundaries;, common, consistent, correspondences;, estimation;, features;, image, independent, linear, MOTION, motion;, occlusion, programming;, scene, segmentation;, specularities;, structurally, structure;, tracked

Much work on deriving scene structure and motion from features assumes as input a set of tracked image features that share a common 3D motion. Producing this input requires segmenting independent motions, and detecting image features that do not correspond to 3D features, originating instead, for example in occlusion boundaries or specularities. We derive a linear program that tells when a set of tracked points might have come from 3D points that share a single motion, assuming affine motion and bounded error. We can also use linear programming to place conservative bounds on the structure of the scene that corresponds to tracked points. We implement and test this algorithm on real images