Motion Segmentation and Tracking Using Normalized Cuts Export

@inproceedings{citeulike:6057273, abstract = {We propose a motion segmentation algorithm that aims to break a scene into its most prominent moving groups. A weighted graph is constructed on the image sequence by connecting pixels that are in the spatiotemporal neighborhood of each other. At each pixel, we define motion profile vectors which capture the probability distrobution of the image velocity. The distance between motion profiles is used to assign a weight on the graph edges. Using normalized cuts we find the most salient partitions of the spaciotemporal graph formed by the image sequence. For segmenting long image sequences, we have developed a recursive update procedure that incorporates knowledge of segmentation in previous frames for efficiently finding the group correspondence in the new frame.}, address = {Washington, DC, USA}, author = {Shi, Jianbo and Malik, Jitendra}, booktitle = {ICCV '98: Proceedings of the Sixth International Conference on Computer Vision}, citeulike-article-id = {6057273}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=939083}, comment = {Segmentation of layers of motions}, isbn = {81-7319-221-9}, keywords = {motion, segmentation}, pages = {1154+}, posted-at = {2009-11-02 19:15:59}, priority = {2}, publisher = {IEEE Computer Society}, title = {Motion Segmentation and Tracking Using Normalized Cuts}, url = {http://portal.acm.org/citation.cfm?id=939083}, year = {1998} }

TY - CONF ID - citeulike:6057273 L3 - citeulike-article-id:6057273 N2 - We propose a motion segmentation algorithm that aims to break a scene into its most prominent moving groups. A weighted graph is constructed on the image sequence by connecting pixels that are in the spatiotemporal neighborhood of each other. At each pixel, we define motion profile vectors which capture the probability distrobution of the image velocity. The distance between motion profiles is used to assign a weight on the graph edges. Using normalized cuts we find the most salient partitions of the spaciotemporal graph formed by the image sequence. For segmenting long image sequences, we have developed a recursive update procedure that incorporates knowledge of segmentation in previous frames for efficiently finding the group correspondence in the new frame. SN - 81-7319-221-9 AD - Washington, DC, USA TI - Motion Segmentation and Tracking Using Normalized Cuts PB - IEEE Computer Society T2 - ICCV '98: Proceedings of the Sixth International Conference on Computer Vision SP - 1154 KW - motion KW - segmentation N1 - Segmentation of layers of motions AU - Shi, Jianbo AU - Malik, Jitendra PY - 1998/// UR - http://portal.acm.org/citation.cfm?id=939083 ER -