Plan-view trajectory estimation with dense stereo background models Export

@inproceedings{citeulike:1219357, abstract = {In a known environment, objects may be tracked in multiple views using a set of background models. Stereo-based models can be illumination-invariant, but often have undefined values which inevitably lead to foreground classification errors. We derive dense stereo models for object tracking using long-term, extended dynamic-range imagery, and by detecting and interpolating uniform but unoccluded planar regions. Foreground points are detected quickly in new images using pruned disparity search. We adopt a \“late-segmentation\” strategy, using an integrated plan-view density representation. Foreground points are segmented into object regions only when a trajectory is finally estimated, using a dynamic programming-based method. Object entry and exit are optimally determined and are not restricted to special spatial zones}, author = {Darrell, T. and Demirdjian, D. and Checka, N. and Felzenszwalb, P.}, citeulike-article-id = {1219357}, citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=937685}, journal = {Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on}, keywords = {stereo-vision, tracking}, pages = {628--635 vol.2}, posted-at = {2007-04-10 18:39:31}, priority = {2}, title = {Plan-view trajectory estimation with dense stereo background models}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=937685}, volume = {2}, year = {2001} }

TY - CONF ID - citeulike:1219357 L3 - citeulike-article-id:1219357 N2 - In a known environment, objects may be tracked in multiple views using a set of background models. Stereo-based models can be illumination-invariant, but often have undefined values which inevitably lead to foreground classification errors. We derive dense stereo models for object tracking using long-term, extended dynamic-range imagery, and by detecting and interpolating uniform but unoccluded planar regions. Foreground points are detected quickly in new images using pruned disparity search. We adopt a “late-segmentation” strategy, using an integrated plan-view density representation. Foreground points are segmented into object regions only when a trajectory is finally estimated, using a dynamic programming-based method. Object entry and exit are optimally determined and are not restricted to special spatial zones JF - Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on EP - 635 vol.2 TI - Plan-view trajectory estimation with dense stereo background models VL - 2 SP - 628 KW - stereo-vision KW - tracking AU - Darrell, T AU - Demirdjian, D AU - Checka, N AU - Felzenszwalb, P PY - 2001/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=937685 ER -