A Geodesic Framework for Fast Interactive Image and Video Segmentation and Matting Export

@inproceedings{citeulike:2362311, abstract = {An interactive framework for soft segmentation and matting of natural images and videos is presented in this paper The proposed technique is based on the optimal, linear time, computation of weighted geodesic distances to the user-provided scribbles, from which the whole data is automatically segmented. The weights are based on spatial and/or temporal gradients, without explicit optical flow or any advanced and often computationally expensive feature detectors. These could be naturally added to the proposed framework as well if desired, in the form of weights in the geodesic distances. A localized refinement step follows this fast segmentation in order to accurately compute the corresponding matte function. Additional constraints into the distance definition permit to efficiently handle occlusions such as people or objects crossing each other in a video sequence. The presentation of the framework is complemented with numerous and diverse examples, including extraction of moving foreground from dynamic background, and comparisons with the recent literature.}, author = {Bai, Xue and Sapiro, Guillermo}, booktitle = {Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on}, citeulike-article-id = {2362311}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/ICCV.2007.4408931}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4408931}, doi = {10.1109/ICCV.2007.4408931}, journal = {Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on}, keywords = {distance, geodesic, interactive, matting, segmentation, statistical}, pages = {1--8}, posted-at = {2008-02-11 11:20:22}, priority = {5}, title = {A Geodesic Framework for Fast Interactive Image and Video Segmentation and Matting}, url = {http://dx.doi.org/10.1109/ICCV.2007.4408931}, year = {2007} }

TY - CONF ID - citeulike:2362311 L3 - citeulike-article-id:2362311 N2 - An interactive framework for soft segmentation and matting of natural images and videos is presented in this paper The proposed technique is based on the optimal, linear time, computation of weighted geodesic distances to the user-provided scribbles, from which the whole data is automatically segmented. The weights are based on spatial and/or temporal gradients, without explicit optical flow or any advanced and often computationally expensive feature detectors. These could be naturally added to the proposed framework as well if desired, in the form of weights in the geodesic distances. A localized refinement step follows this fast segmentation in order to accurately compute the corresponding matte function. Additional constraints into the distance definition permit to efficiently handle occlusions such as people or objects crossing each other in a video sequence. The presentation of the framework is complemented with numerous and diverse examples, including extraction of moving foreground from dynamic background, and comparisons with the recent literature. JF - Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on EP - 8 TI - A Geodesic Framework for Fast Interactive Image and Video Segmentation and Matting T2 - Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on SP - 1 KW - distance KW - geodesic KW - interactive KW - matting KW - segmentation KW - statistical AU - Bai, Xue AU - Sapiro, Guillermo PY - 2007/// UR - http://dx.doi.org/10.1109/ICCV.2007.4408931 ER -