Effective Gaussian Mixture Learning for Video Background Subtraction Export

@article{citeulike:2798963, abstract = {Adaptive Gaussian mixtures have been used for modeling nonstationary temporal distributions of pixels in video surveillance applications. However, a common problem for this approach is balancing between model convergence speed and stability. This paper proposes an effective scheme to improve the convergence rate without compromising model stability. This is achieved by replacing the global, static retention factor with an adaptive learning rate calculated for each Gaussian at every frame. Significant improvements are shown on both synthetic and real video data. Incorporating this algorithm into a statistical framework for background subtraction leads to an improved segmentation performance compared to a standard method.}, address = {Los Alamitos, CA, USA}, author = {Lee, Dar S.}, booktitle = {Pattern Analysis and Machine Intelligence, IEEE Transactions on}, citeulike-article-id = {2798963}, citeulike-linkout-0 = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2005.102}, citeulike-linkout-1 = {http://dx.doi.org/10.1109/TPAMI.2005.102}, citeulike-linkout-2 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1407887}, doi = {10.1109/TPAMI.2005.102}, issn = {0162-8828}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, keywords = {background, gaussian, gmm, mixture, segmentation, subtraction}, number = {5}, pages = {827--832}, posted-at = {2008-05-14 15:19:36}, priority = {2}, publisher = {IEEE Computer Society}, title = {Effective Gaussian Mixture Learning for Video Background Subtraction}, url = {http://dx.doi.org/10.1109/TPAMI.2005.102}, volume = {27}, year = {2005} }

TY - JOUR ID - citeulike:2798963 L3 - citeulike-article-id:2798963 N2 - Adaptive Gaussian mixtures have been used for modeling nonstationary temporal distributions of pixels in video surveillance applications. However, a common problem for this approach is balancing between model convergence speed and stability. This paper proposes an effective scheme to improve the convergence rate without compromising model stability. This is achieved by replacing the global, static retention factor with an adaptive learning rate calculated for each Gaussian at every frame. Significant improvements are shown on both synthetic and real video data. Incorporating this algorithm into a statistical framework for background subtraction leads to an improved segmentation performance compared to a standard method. IS - 5 JF - IEEE Transactions on Pattern Analysis and Machine Intelligence SN - 0162-8828 AD - Los Alamitos, CA, USA EP - 832 TI - Effective Gaussian Mixture Learning for Video Background Subtraction PB - IEEE Computer Society VL - 27 T2 - Pattern Analysis and Machine Intelligence, IEEE Transactions on SP - 827 KW - background KW - gaussian KW - gmm KW - mixture KW - segmentation KW - subtraction AU - Lee, Dar PY - 2005/// UR - http://dx.doi.org/10.1109/TPAMI.2005.102 ER -