On-the-fly Object Modeling while Tracking

@inproceedings{citeulike:2987316, abstract = {To implement a persistent tracker, we build a set of view-dependent object appearance models adoptively and automatically while tracking an object under different viewing angles. This collection of acquired models is indexed with respect to the view sphere. The acquired models aid recovery from tracking failure due to occlusion and changing view angle. In this paper, view-dependent object appearance is represented by intensity patches around detected Harris corners. The intensity patches from a model are matched to the current frame by solving a bipartite linear assignment problem with outlier exclusion and missed inlier recovery. Based on these reliable matches, the change in object rotation, translation and scale is estimated between consecutive frames using Procrustes analysis. The experimental results show good performance using a collection of view-specific patch-based models for detection and tracking of vehicles in low-resolution airborne video.}, author = {Yin, Zhaozheng and Collins, R. }, booktitle = {Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on}, citeulike-article-id = {2987316}, doi = {10.1109/CVPR.2007.383237}, journal = {Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on}, keywords = {imaging}, pages = {1--8}, posted-at = {2008-07-11 09:45:26}, priority = {1}, title = {On-the-fly Object Modeling while Tracking}, url = {http://dx.doi.org/10.1109/CVPR.2007.383237}, year = {2007} }

TY - CONF ID - citeulike:2987316 L3 - citeulike-article-id:2987316 TI - On-the-fly Object Modeling while Tracking T2 - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on JF - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on SP - 1 EP - 8 N2 - To implement a persistent tracker, we build a set of view-dependent object appearance models adoptively and automatically while tracking an object under different viewing angles. This collection of acquired models is indexed with respect to the view sphere. The acquired models aid recovery from tracking failure due to occlusion and changing view angle. In this paper, view-dependent object appearance is represented by intensity patches around detected Harris corners. The intensity patches from a model are matched to the current frame by solving a bipartite linear assignment problem with outlier exclusion and missed inlier recovery. Based on these reliable matches, the change in object rotation, translation and scale is estimated between consecutive frames using Procrustes analysis. The experimental results show good performance using a collection of view-specific patch-based models for detection and tracking of vehicles in low-resolution airborne video. KW - imaging AU - Yin, Zhaozheng AU - Collins, R PY - 2007/// UR - http://dx.doi.org/10.1109/CVPR.2007.383237 ER -