Change detection by probabilistic segmentation from monocular view
作者： Francisco J. Hernandez-Lopez , Mariano Rivera
DOI: 10.1007/S00138-013-0564-3
关键词: General-purpose computing on graphics processing units 、 Pattern recognition (psychology) 、 Pixel 、 Segmentation 、 Computer vision 、 Change detection 、 Artificial intelligence 、 CUDA 、 Pattern recognition 、 Graphics processing unit 、 Computer science 、 Background subtraction
摘要: We present a method for foreground/background video segmentation (change detection) in real-time that can be used, applications such as background subtraction or analysis of surveillance cameras. Our approach implements probabilistic based on the Quadratic Markov Measure Field models. This framework regularizes likelihood each pixel belonging to one classes (background foreground). propose new takes into account two cases: first is when static and foreground might moving (Static Background Subtraction), second unstable (Unstable Subtraction). Moreover, our robust illumination changes, cast shadows camouflage situations. implement parallel version algorithm CUDA using NVIDIA Graphics Processing Unit order fulfill execution requirements.
springer.com
acm.org
sci-hub.se 参考文章(51)
V. Kolmogorov, A. Criminisi, A. Blake, G. Cross, C. Pother, Probabilistic fusion of stereo with color and contrast for bilayer segmentation IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 28, pp. 1480- 1492 ,(2006) , 10.1109/TPAMI.2006.193
Simone Calderara, Andrea Prati, Rita Cucchiara, HECOL: Homography and epipolar-based consistent labeling for outdoor park surveillance Computer Vision and Image Understanding. ,vol. 111, pp. 21- 42 ,(2008) , 10.1016/J.CVIU.2007.07.006
C. Stauffer, W.E.L. Grimson, Learning patterns of activity using real-time tracking IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 22, pp. 747- 757 ,(2000) , 10.1109/34.868677
Shinji Fukui, Yuji Iwahori, Robert J. Woodham, GPU based extraction of moving objects without shadows under intensity changes world congress on computational intelligence. pp. 4165- 4172 ,(2008) , 10.1109/CEC.2008.4631366
A. Elgammal, R. Duraiswami, D. Harwood, L.S. Davis, Background and foreground modeling using nonparametric kernel density estimation for visual surveillance Proceedings of the IEEE. ,vol. 90, pp. 1151- 1163 ,(2002) , 10.1109/JPROC.2002.801448
Carsten Rother, Vladimir Kolmogorov, Andrew Blake, "GrabCut" ACM Transactions on Graphics. ,vol. 23, pp. 309- 314 ,(2004) , 10.1145/1015706.1015720
Mariano Rivera, Pedro P. Mayorga, Quadratic Markovian Probability Fields for Image Binary Segmentation international conference on computer vision. pp. 1- 8 ,(2007) , 10.1109/ICCV.2007.4409119
O Barnich, M Van Droogenbroeck, ViBe: A Universal Background Subtraction Algorithm for Video Sequences IEEE Transactions on Image Processing. ,vol. 20, pp. 1709- 1724 ,(2011) , 10.1109/TIP.2010.2101613
V. Kolmogorov, A. Criminisi, A. Blake, G. Cross, C. Rother, Bi-layer segmentation of binocular stereo video computer vision and pattern recognition. ,vol. 2, pp. 407- 414 ,(2005) , 10.1109/CVPR.2005.91
Minglun Gong, Li Cheng, Real-time foreground segmentation on GPUs using local online learning and global graph cut optimization international conference on pattern recognition. pp. 1- 4 ,(2008) , 10.1109/ICPR.2008.4761488