Motion segmentation using occlusions

TitleMotion segmentation using occlusions
Publication TypeJournal Articles
Year of Publication2005
AuthorsOgale AS, Fermüller C, Aloimonos Y
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Pagination988 - 992
Date Published2005/06//
ISBN Number0162-8828
Keywords3D motion estimation, algorithms, Artificial intelligence, CAMERAS, Computer vision, Filling, hidden feature removal, Image Enhancement, Image Interpretation, Computer-Assisted, image motion, Image motion analysis, Image segmentation, Layout, MOTION, Motion detection, Motion estimation, motion segmentation, Movement, Object detection, occlusion, occlusions, optical flow, ordinal depth, Pattern Recognition, Automated, Photography, Reproducibility of results, segmentation, Semiconductor device modeling, Sensitivity and Specificity, video analysis., Video Recording

We examine the key role of occlusions in finding independently moving objects instantaneously in a video obtained by a moving camera with a restricted field of view. In this problem, the image motion is caused by the combined effect of camera motion (egomotion), structure (depth), and the independent motion of scene entities. For a camera with a restricted field of view undergoing a small motion between frames, there exists, in general, a set of 3D camera motions compatible with the observed flow field even if only a small amount of noise is present, leading to ambiguous 3D motion estimates. If separable sets of solutions exist, motion-based clustering can detect one category of moving objects. Even if a single inseparable set of solutions is found, we show that occlusion information can be used to find ordinal depth, which is critical in identifying a new class of moving objects. In order to find ordinal depth, occlusions must not only be known, but they must also be filled (grouped) with optical flow from neighboring regions. We present a novel algorithm for filling occlusions and deducing ordinal depth under general circumstances. Finally, we describe another category of moving objects which is detected using cardinal comparisons between structure from motion and structure estimates from another source (e.g., stereo).