Automatic and Real-Time Extraction Algorithm for Video Object Based on a Graph Cut Frame

Abstract

Abstract:

Abstract： In order to extract foreground object accurately and efficiently in natural scenes, a segmentation algorithm based on the graph cut frame was proposed. First, GMMs background models with the adaptability to the scene change were combined with shadows removal methods using color and local appearance cues to set the data cost in the energy function. Then, the difference based on local binary pattern operator was used to set the smoothness term in the energy function. After that, all pixels were assigned to binary labels by minimizing the energy function by dynamic graph cut algorithm. Finally, the proposed algorithm was verified on different videos. Experimental results prove that the proposed method can cut the foreground object accurately with realtime ability.

Key words: object extraction, background modeling, graph cut, foreground segmentation

CLC Number:

TP 391.4

WU XiaoYu1,YANG Lei1,ZHANG YiChun2. Automatic and Real-Time Extraction Algorithm for Video Object Based on a Graph Cut Frame[J]. Journal of Shanghai Jiaotong University, 2014, 48(12): 1732-1738.

References

［1］Zivkovic Z. Improved adaptive Gaussian mixture model for background subtraction［C］//IEEE Proceedings of the 17th International Conference on Pattern Recognition. Cambridge, England, UK: IEEE Press, 2004: 2831.

［2］Wang H Z, Suter D. A consensusbased method for tracking: Modeling background scenario and foreground appearance ［J］. Pattern Recognition, 2007, 40(3):10911105.

［3］Barnich O, Van Droogenbroeck M. ViBe: A universal background subtraction algorithm for video sequences ［J］. IEEE Transactions on Image Processing, 2011, 20(6):17091724.

［4］SUN Jian, ZHANG Weiwei, TANG Xiaoou, et al. Background cut［C］//European Conference on Computer Vision. Graz, Austria: Springer, 2006: 628641.

［5］Yin P, Criminisi A, Winn J, et al. Bilayer segmentation of webcam videos using treebased classifiers ［J］. IEEE Transcation on Pattern Analysis and Machine Intelligence, 2011, 33(1): 3042.

［6］Price B L, Morse B, Cohen S. Livecut: Learningbased interactive video segmentation by evaluation of multiple propagated cues［C］//International Conference on Computer Vision. Kyoto, Japan: IEEE Press, 2009:779789.

［7］Boykov Y, Kolmogorov V. An experimental comparison of mincut/maxflow algorithms for energy minimization in vision［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 11241137

［8］WU Xiaoyu, WANG Yangsheng, ZHENG Xiaolong. Monocular video foreground segmentation system［C］//International Conference on Pattern Recognition. Tampa, Florida, USA: IEEE Press, 2008, 14.

［9］Ojala T, Pietikinen M, Menp T. Multiresolution grayscale and rotation invariant texture classification with local binary patterns［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971987.

［10］刘松涛,殷福亮. 基于图割的图像分割方法及其新进展［J］.自动化学报,2012, 38(6):911922.

LIU Songtao,YIN Fuliang. The basic principle and its new advances of image segmentation methods based on graph cuts ［J］. Acta Automatica Sinica, 2012, 38(6):911922.

［11］Kohli P, Torr P H S. Dynamic graph cuts for efficient inference in markov random fields［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(12): 20792088.

［12］Prah A, Wic I, Trivedi M M, et al. Detecting moving shadows: Algorithms and evaluation ［J］. IEEE Trans Pattern Analysis and Machine Intelligence, 2003, 25(7): 918923.