TY - JOUR T1 - Motion segmentation using occlusions JF - IEEE Transactions on Pattern Analysis and Machine Intelligence Y1 - 2005 A1 - Ogale, A. S A1 - Fermüller, Cornelia A1 - Aloimonos, J. KW - 3D motion estimation KW - algorithms KW - Artificial intelligence KW - CAMERAS KW - Computer vision KW - Filling KW - hidden feature removal KW - Image Enhancement KW - Image Interpretation, Computer-Assisted KW - image motion KW - Image motion analysis KW - Image segmentation KW - Layout KW - MOTION KW - Motion detection KW - Motion estimation KW - motion segmentation KW - Movement KW - Object detection KW - occlusion KW - occlusions KW - optical flow KW - ordinal depth KW - Pattern Recognition, Automated KW - Photography KW - Reproducibility of results KW - segmentation KW - Semiconductor device modeling KW - Sensitivity and Specificity KW - video analysis. KW - Video Recording AB - 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). VL - 27 SN - 0162-8828 CP - 6 M3 - 10.1109/TPAMI.2005.123 ER -