语义对象分割的若干方法研究
|
摘要
语义对象分割的应用领域相当宽泛,包括视频编码、视频监控、图象和视频编辑、图象和视频检索、人机交互、图象理解以及对象识别等,这些应用系统性能的优劣在很大程度上取决于语义对象分割结果的好坏,因此语义对象分割具有非常重要的研究意义和应用价值。在经典的视频对象分割研究基础上,近几年来对于图象和视频中对象分割的研究已逐步聚焦在对显著对象的自动分割和基于视觉关注度的感兴趣语义对象的提取,并取得了不少成果,但仍有值得改善之处。本文的研究主要属于这一领域,对其中的方法或算法作了改进。此外,对运动对象可能存在的运动阴影也作了较深入的研究,取得了较好的结果。本文的主要工作包括:
第一,为了准确地从彩色图象中提取出视觉上显著的对象,提出了一种基于区域显著性比值的显著对象自动提取方法。首先用核密度估计方法把输入图象分割成不同的区域,并通过高斯图象金字塔计算输入图象的多分辨率对比度特征,生成一个具有尺度不变性的显著性图;然后计算每个区域组合与其补集的区域显著性及其比值;最后通过找出这个比值的最大值从而提取出显著对象。该方法能够有效地从彩色图象中提取出符合人类视觉关注的多个显著对象。
第二,对于视频序列中感兴趣运动对象的分割问题,提出了一种结合有选择的视觉关注度和马尔可夫随机场(Markov Random Field)的分割方法。首先把灰度级为256的输入图象转换成8个灰度级波段的图象,进而根据象素在相邻两帧的灰度级波段是否发生变化提取出运动特征;接着利用连通成分标记算法并结合运动特征以获得运动区域;然后提取出这些运动区域的形状特征并且和预先定义的感兴趣对象的形状特征进行比较,从而得到初始的运动对象分割结果;最后把每个象素的状态沿着时间的记录作为MRF的能量函数,通过能量最小化获得最终更为精确的运动对象分割结果。本方法能够有效地把场景中的运动象素和背景象素区别开,提高了对象分割的准确性。
第三,对于视频对象分割中运动阴影消除的问题,提出了一种结合色度、亮度和边缘信息的方法。首先使用结合核密度估计和边缘信息的分割方法获得初始对象分割结果及其中运动对象的边缘,然后提取输入视频帧的色度和亮度信息以得到可能的运动阴影区域,最后利用阴影区域生长方法将运动阴影区域和运动对象区分开。对室内外视频序列的实验结果表明,该方法具有良好的消除运动阴影的性能。
The application domain of semantic object segmentation is quite broad. It includes video coding, video surveillance, image and video editing, image and video retrieval, human computer interaction, image understanding and object recognition, etc. The performance of these application systems depends largely on the results of semantic object segmentation. Therefore, the research on semantic object segmentation is very important for a variety of applications. On the basis of traditional video object segmentation, the research on semantic object segmentation has gradually been focused on automatic extraction of salient objects and visual attention based interesting semantic object segmentation in the recent years. Although many progresses have been achieved in this research field, there is still room for improvement. The research in this dissertation mainly belongs to this research field and has improved some related approaches. In addition, moving cast shadow has also been studied in this dissertation, and good results have been obtained. The main work of this dissertation is as follows:
(1) An efficient salient object extraction approach based on region saliency ratio is proposed to automatically segment visually salient objects from color images. The input image is first segmented into homogenous regions using nonparametric kernel density estimation, meanwhile a scale-invariant saliency map is constructed based on multi-resolution feature contrast calculation. Then the region saliency ratio of each region combination to its complement is calculated in turn. Finally, salient objects are extracted by maximizing the region saliency ratio. The proposed approach can efficiently extract multiple salient objects complying with human vision attention from color images.
(2) An segmentation approach that combines selective visual attention with the Markov random field (MRF) framework is proposed to segment interested moving objects from video sequences. The input images with 256 gray-levels are first transformed into the images with 8 gray-level bands, and motion feature is extracted based on variation of gray-level band between two consecutive frames. Then moving regions are obtained by combining motion features with connected component labeling. The shape features of moving regions are extracted and compared with the predefined shape features of interesting objects, and initial object mask is generated by a set of selected moving regions. Finally, the memorization along time for each pixel is used as the energy function of MRF and more accurate moving object segmentation results are obtained by energy minimization. The proposed approach can efficiently distinguish moving object pixels from background pixels, and improve the accuracy of object segmentation.
(3) A moving cast shadow removal approach based on chromaticity, intensity and the edge information is proposed for accurate video object segmentation. Based on kernel density estimation and edge information of the input frame, an initial moving object mask and corresponding edges of moving objects are obtained. Then candidate shadow regions are obtained by extracting chromaticity and intensity information from the input frame. Finally, the moving cast shadow region is detected and removed using region growing method. Experimental results of indoor and outdoor video sequences demonstrate the good performance of moving cast shadow removal of the proposed approach.
第一,为了准确地从彩色图象中提取出视觉上显著的对象,提出了一种基于区域显著性比值的显著对象自动提取方法。首先用核密度估计方法把输入图象分割成不同的区域,并通过高斯图象金字塔计算输入图象的多分辨率对比度特征,生成一个具有尺度不变性的显著性图;然后计算每个区域组合与其补集的区域显著性及其比值;最后通过找出这个比值的最大值从而提取出显著对象。该方法能够有效地从彩色图象中提取出符合人类视觉关注的多个显著对象。
第二,对于视频序列中感兴趣运动对象的分割问题,提出了一种结合有选择的视觉关注度和马尔可夫随机场(Markov Random Field)的分割方法。首先把灰度级为256的输入图象转换成8个灰度级波段的图象,进而根据象素在相邻两帧的灰度级波段是否发生变化提取出运动特征;接着利用连通成分标记算法并结合运动特征以获得运动区域;然后提取出这些运动区域的形状特征并且和预先定义的感兴趣对象的形状特征进行比较,从而得到初始的运动对象分割结果;最后把每个象素的状态沿着时间的记录作为MRF的能量函数,通过能量最小化获得最终更为精确的运动对象分割结果。本方法能够有效地把场景中的运动象素和背景象素区别开,提高了对象分割的准确性。
第三,对于视频对象分割中运动阴影消除的问题,提出了一种结合色度、亮度和边缘信息的方法。首先使用结合核密度估计和边缘信息的分割方法获得初始对象分割结果及其中运动对象的边缘,然后提取输入视频帧的色度和亮度信息以得到可能的运动阴影区域,最后利用阴影区域生长方法将运动阴影区域和运动对象区分开。对室内外视频序列的实验结果表明,该方法具有良好的消除运动阴影的性能。
The application domain of semantic object segmentation is quite broad. It includes video coding, video surveillance, image and video editing, image and video retrieval, human computer interaction, image understanding and object recognition, etc. The performance of these application systems depends largely on the results of semantic object segmentation. Therefore, the research on semantic object segmentation is very important for a variety of applications. On the basis of traditional video object segmentation, the research on semantic object segmentation has gradually been focused on automatic extraction of salient objects and visual attention based interesting semantic object segmentation in the recent years. Although many progresses have been achieved in this research field, there is still room for improvement. The research in this dissertation mainly belongs to this research field and has improved some related approaches. In addition, moving cast shadow has also been studied in this dissertation, and good results have been obtained. The main work of this dissertation is as follows:
(1) An efficient salient object extraction approach based on region saliency ratio is proposed to automatically segment visually salient objects from color images. The input image is first segmented into homogenous regions using nonparametric kernel density estimation, meanwhile a scale-invariant saliency map is constructed based on multi-resolution feature contrast calculation. Then the region saliency ratio of each region combination to its complement is calculated in turn. Finally, salient objects are extracted by maximizing the region saliency ratio. The proposed approach can efficiently extract multiple salient objects complying with human vision attention from color images.
(2) An segmentation approach that combines selective visual attention with the Markov random field (MRF) framework is proposed to segment interested moving objects from video sequences. The input images with 256 gray-levels are first transformed into the images with 8 gray-level bands, and motion feature is extracted based on variation of gray-level band between two consecutive frames. Then moving regions are obtained by combining motion features with connected component labeling. The shape features of moving regions are extracted and compared with the predefined shape features of interesting objects, and initial object mask is generated by a set of selected moving regions. Finally, the memorization along time for each pixel is used as the energy function of MRF and more accurate moving object segmentation results are obtained by energy minimization. The proposed approach can efficiently distinguish moving object pixels from background pixels, and improve the accuracy of object segmentation.
(3) A moving cast shadow removal approach based on chromaticity, intensity and the edge information is proposed for accurate video object segmentation. Based on kernel density estimation and edge information of the input frame, an initial moving object mask and corresponding edges of moving objects are obtained. Then candidate shadow regions are obtained by extracting chromaticity and intensity information from the input frame. Finally, the moving cast shadow region is detected and removed using region growing method. Experimental results of indoor and outdoor video sequences demonstrate the good performance of moving cast shadow removal of the proposed approach.
引文
[1]张兆杨,杨高波,刘志等.视频对象分割提取的原理与应用[M].北京:科学出版社,2009.
[2] B KP Horn, B G Schunck.. Determining optical Flow[J]. Artificial Intelligence, 1981, 17: 185-203.
[3] H H Nagel. Displacement vectors derived from second order intensity variations in image sequence[J]. Computer Graphics and Image Processing, 1983, 21: 299-324.
[4] Liu Haiying, Rama C, Azriel R. Accurate dense optical flow estimation using adaptive structure tensors and a parametric model[J]. IEEE transactions on image processing, 2003, 12: 1170-1180.
[5] Weickert J, Schnorr C. Variational optic flow computation with a spatio-temporal smoothness constraint[J]. Journal of Mathematical Imaging and Vision, 2001, 14(3): 245-255.
[6] Choi J G, Kim S D. Multi-stage segmentation of optical flow field[J]. Signal Processing, 1996, 54(2): 109-118.
[7] Tuncel E, Onural L. Utilization of the recursive shortest spanning tree algorithm for video-object segmentation by 2-D affine motion modeling[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2000, 10(5): 776-781.
[8] Ma Kaikuang, Wang Haiyun. Unsupervised semantic video objects segmentation over optical-flow field[C]. Seventh International Conference on Control, Automation, Robotics and Vision, Singapore, 2002, 1: 1216-1221.
[9] Y Zinbi, Y Chahir, A Elmoataz. Moving object segmentation using optical flow with active contour model[C]. 2008 3rd International Conference on Informationand Communication Technologies: From Theory to Applications, Damascus, Syria, 2008: 1-5.
[10] Jain R. Difference and accumulative difference pictures in dynamic scene analysis [J] . Image and Vision Computing, 1984, 2(2) : 98-108.
[11]印勇,张影.基于变化检测的视频对象分割算法研究[J].计算机工程与应用,2008,44(13): 161-163.
[12] Salvador E, Cavallaro A, Ebrahimi T. Cast shadow segmentation using invariant color features[J]. Computer Vision and Image Understanding, 2004, 95(2): 238-259.
[13] Xu Dong, Liu Jianzhuang, Li Xuelong, et al. Insignificant shadow detection for video segmentation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2005, 15(8): 1058-1064.
[14] Chien S Y, Ma S Y, Chen L G. Efficient moving object segmentation algorithm using background registration technique [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2002, 12(7): 577-586.
[15] Elgammal A, Duraiswami R, Harwood D, et al. Background and foreground modeling using non-parametric kernel density estimation for visual surveillance[J]. Proceedings of the IEEE, 2002 , 90 (7):1151-1162.
[16] Stauffer C, Grimson W E L. Learning patterns of activity using real-time tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 747-757.
[17] Neri A, Colonnese S, Russo G, et al. Automatic moving object and background separation[J]. Signal Processing, 1998, 66(2): 219-232.
[18] Aach T, Kaup A, Mester R. Statistical model2based change detection in moving video[J]. Signal Processing, 1993, 31(2): 165-180.
[19] Ziliani F, Cavallaro A. Image analysis for video surveillance based on spatial regularization of a statistical model-based change detection[J]. Real-Time Imaging, 2001, 7(5): 389-399.
[20] Sifakis E, Tziritas G. Moving object localisation using a multi-label fast marching algorithm[J]. Signal Processing: Image Communication, 2001, 16 (10): 963-976.
[21] Cavallaro A , Ebrahimi T. Accurate video object segmentation through change etection[C]. IEEE International Conference on Multimedia and Expo. 2002, 1: 445-448.
[22] Fan J, Ji Y, Wu L. Automatic moving object extraction toward content-based video representation and indexing[J]. Visual Communication and Image Representation, 2001, 12 (3): 306-347.
[23] Fan J P, Zhu X Q, Wu L D. Automatic model-based semantic object extraction algorithm. IEEE Transactions on Circuits and Systems for Video Technology, 2001, 11(10): 1073-1084.
[24] Luo Huitao, Eleftheriadis Alexandros. Model-based segmentation and tracking of head-and-shoulder video objects for real time multimedia services[J]. IEEE Transactions on Multimedia, 2003, 5(3): 379-389.
[25] Su Yih-Ming, Hsieh Chaur-Heh. A novel model-based segmentation approach to extract caption contents on sports videos[C]. IEEE International Conference on Multimedia and Expo. Toronto, 2006: 1829-1832.
[26] Zhang Dengsheng, Lu Guojun. Segmentation of moving objects in image sequences: A review. Circuits, Systems, and Signal Processing, 2001, 20(2): 143-183.
[27] Mech R, Wollborn M. A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera. Signal Processing, 1998, 66(2): 203-217.
[28] Choi G, Lee S W, Kim S D. Spatio-temporal video seg-mentation using a joint similarity measure[J]. IEEE Transactions Circuits Systems for Video Technology, 1997, 7 (2): 279-286.
[29] Greenspan H, Goldberger J, Mayer A. Probabilistic Space-Time Video Modelingvia Piecewise GMM. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(3): 384-396.
[30] Ahmed R, Karmakar G C, Dooley L S. Efficient probabilistic spatio-temporal video object segmentation[C]. 6th IEEE/ACIS International Conference on Computer and Information Science, Melbourne, 2007: 807-811.
[31] Boykov Y Y, Jolly M P. Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images[C]. Eighth IEEE International Conference on Computer Vision, Vancouver, 2001, 1: 105-112.
[32] Rother C, Kolmogorov V, Blake A.“Grabcut”—interactive foreground extraction using iterated graph cuts[J]. ACM Transactions on Graphics, 2004, 23(3): 309-314.
[33] Criminisi A, Cross G, Blake A, et al. Bilayer segmentation of live video[C]. In Proceedings of IEEE Computer Vision and Pattern Recognition, 2006, 1: 53-60.
[34] Sun J, Jia J, Tang C K, et al. Poisson matting[C]. ACM Transactions on Graphics, 2004, 23: 315-321.
[35] Chuang Y Y, Curless B, Salesin D H, et al. A Bayesian approach to digital matting[C]. In Proceedings of IEEE Computer Vision and Pattern Recognition, 2001, 2: 264-271.
[36] Chuang Y Y, Agarwala A, Curless B, et al. Video matting of complex scenes[C]. ACM Transactions on Graphics, United states, 2002, 21(3): 243-248.
[37] Levin A, Rav-Acha A, Lischinski D. Spectral matting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(10): 1699-1712.
[38] Levin A, Lischinski D, Weiss Y. A closed form solution to natural image matting[C]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, 2006, 1: 61-68.
[39] Wang Jue, Agrawala M, Cohen M F. Soft scissors: an interactive tool for realtime high quality matting[C]. 34th Annual Meeting of the Association for Computing Machinery's Special Interest Group on Graphics, San Diego, 2007, 26 (3): 1-6.
[40] Bai Xue, Sapiro G. Geodesic matting: a framework for fast interactiv image and video segmentation and matting[J]. International Journal on Computer Vision, 2009, 82(2): 113-132.
[41] L Itti, C Koch, E Niebur. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259.
[42] Cheng Wenhuang, Chu Weita, Wu Jaling. A visual attention based region-of-interest determination framework for video sequences[J]. IEICE Transactions on Information and Systems, 2005, E88-D: 1578-1586.
[43] Ma Yufei, Hua Xiansheng, Lu Lie, et al. A generic framework of user attention model and its application in video summarization[J]. IEEE Transactions Multimedia, 2005, 7(5): 907-919.
[44] Hu Yiqun, Xie Xing, Ma Weiying, et al. Salient region detection using weighted feature maps based on the human visual attention model[C]. Advances in Multimedia Information Processing-PCM, 2004, LNCS 3332: 993-1000.
[45] Han Junwei, Ngan K N, Li Mingjing, et al. Towards unsupervised attention object extraction by integrating visual attention and object growing[C]. International Conference on Image Processing, 2004, 5: 941-944.
[46] Han Junwei, Ngan K N, Li Mingjing, et al. Unsupervised extraction of visual attention objects in color images[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2006, 16(1): 141-145.
[47] Park K T, Moon Y S. Automatic extraction of salient objects using feature maps[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Honolulu, 2007, 1: 1617-1620.
[48] Lu Yinghua, Zhang Xiaohua, Kong Jun, et al. A novel objects of interest extraction approach using attention-driven model for content-based image retrieval[C]. 1st International Congress on Image and Signal Processing, Hainan, 2008, 1: 339-343.
[49] Atsumi M. Attention-based segmentation on an image pyramid sequence[C]. 10th International Conference on Advanced Concepts for Intelligent Vision Systems, France, 2008, 5259 LNCS: 625-636.
[50] Pirnog I, Oprea C, Paleoloqu C. Image content extraction using a bottom-up visual attention model[C]. 3rd International Conference on Digital Society, Cancun, 2009: 300-303.
[51] Borba G B, Gamba H R, Marques O, et al. Extraction of salient regions of interest using visual attention models[J]. Proceedings of SPIE-The International Society for Optical Engineering, 2009, 7255: 725508-1-12.
[52] Crevier D. Extracting Salient Objects from Operator-Framed Images[C]. Proceedings-Fourth Canadian Conference on Computer and Robot Vision, Montreal, 2007: 36-43.
[53] Lu Huihai, Woods J C, Ghanbari M. Binary partition tree for semantic object extraction and image segmentation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2007, 17 (3): 378-383.
[54] Maria T Lopez, Miguel A Fernandez, Antonio Fernandez-Caballero, et al. Dynamic visual attention model in image sequences[J]. Image and Vision Computing, 2007, 25 (5): 597–613.
[55] Bastan M, Gudukbay U, Ulusoy O. Segmentation-based extraction of important objects from video for object-based indexing[C]. IEEE International Conference on Multimedia and Expo, Hannover, 2008: 1357-1360.
[56] J Serra, L Vincent. An overview of morphological filtering[J]. Circuits, Systems and Signal Processing, 1992, 11(1): 47-108.
[57] Arun N Netravali, Barry G Haskell. Digital pictures: representation, compression and standards (2nd edition) [M]. Spring street: Plenum Press, 1995.
[58] Duda Richard O, Hart Peter E, Stork David G. Pattern classication (2nd edition) [M]. New York: Wiley, 2000.
[59] Ziou D, Tabbone S. Edge detection techniques an overview[J]. InternationalJournal of Pattern Recognition and Image Analysis, 1998, 8(4): 537-559.
[60] John Canny. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
[61] R Deriche, Using Canny's criteria to derive an optimal edge detectorecursively implemented[J]. International Journal of Computer Vision, 1987,1: 167-187.
[62] P L Rosin. Edges: saliency measures and automatic thresholding[J]. Machine Vision and Applications, 1997, 9(4): 139-159.
[63] P L Rosin. Comments on ground from figure discrimination[J]. Pattern Recognition Letters, 2003, 24(15): 2761-2766.
[64] D R Martin, C C Fowlkes, J Malik. Learning to detect natural image boundaries using local brightness, color, and texture cues[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26 (5): 530–549.
[65] A. Sha’ashua and S Ullman. Structural saliency: the detection of globally salient structures using a locally connected network[J]. Second International Conference on Computer Vision, 1988: 321–327.
[66] G Guy, G Medioni. Inferring global perceptual contours from local features[J]. International Journal of Computer Vision, 1996, 20(1-2): 113-133.
[67] J S Huang, D H Tseng. Statistical theory of edge detection[J]. Computer vision, graphics, and image processing, 1988, 43(3): 337-346.
[68] D Marr, E Hidreth. Theory of edge detection. Proceedings of the Royal Society of London. Series B, Biological Sciences, 1980, 207 (1167) : 187-217.
[69] V Nalwa, T O Binford. On detecting edges[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6) : 699-714.
[70] K N Le, K P Dabke, G K Egan. Hyperbolic wavelet power spectra of nonstationary signals[J]. Optical Engineering, 2003, 42 (10): 3017-3037.
[71] R C Gonzales, R E Woods. Digital Image Processing[M]. New Jersey: Prentice Hall, Inc., 2002.
[72] R M Haralick, L G Shapiro. Survey-image segmentation techniques[J], ComputerVision Graphics and Image Processing, 1985, 29: 100-132.
[73] Cui Weihong, Guan Zequn, Zhang Zhiyi. An improved region growing algorithm for image segmentation[C], International Conference on Computer Science and Software Engineering. Wuhan, 2008, 6: 93-96.
[74] A Bleau, L J Leon. Watershed-based segmentation and region merging[J]. Computer Vision and Image Understanding, 2000, 77(3): 317–370.
[75] Ilya Levner, Zhang Hong. Classification-Driven Watershed Segmentation[J]. IEEE Transactions On Image Processing, 2007, 16(5): 1437–1445.
[76] A K Jain, R C Dubes. Algorithms for clustering data[M]. New Jersey: Prentice Hall, 1988.
[77] T Kurita. An efficient agglomerative clustering algorithm using a heap[J]. Pattern Recognition, 1991, 24(3): 205-209.
[78] H Frigui, R Krishnapuram. A robust competitive clustering algorithm with applications in computer vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(5): 450-465.
[79] E J Pauwels, G Frederix. Finding salient regions in images: nonparametric clustering for image segmentation and grouping[J]. Computer Vision and Image Understanding, 1999, 75(1): 73-85.
[80] J R Ohm, P Ma. Feature-based cluster segmentation of image sequences[C]. Proceedings International Conference on Image Processing. 1997, 3: 178-181.
[81] M K Ng. A note on constrained k-means algorithm[J]. Pattern Recognition, 2000, 33: 515-519.
[82] Y H Kuan, S T Chen, C M Kuo, et al. A novel unsupervised salient region segmentation for color images[C], International Conference on Innovative Computing, Information and Control, 2006, 2: 96-99.
[83] Stan Z Li. Markov Random Field Modeling in Image Analysis (3rd Edition). Series: Advances in Pattern Recognition. Springer. 2009.
[84] S Geman, D Geman. Stochastic relaxation, gibbs distributions, and the Bayesianrestoration of images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984, 6: 721-741.
[85] J Besag. On the statistical analysis of dirty pictures[J]. Journal of the Royal Statistical Society. Series B, 1986, 48(3): 259-302.
[86] P Chou, C Brown. The theory and practice of Bayesian image labeling[J]. International Journal of Computer Vision, 1990, 4: 185-210.
[87] Moscato P. On evolution, search, optimization, genetic algorithms and martial arts: Towards memetic algorithms. C3P Report 826, Caltech Concurrent Computation Program. 1989.
[88] Radcliffe N J, Surry P D. Formal memetic algorithms. Proceedings of the AISB Workshop on Evolutionary Computing, Leeds, 1994, 865: 1-14.
[89] D Greig, B Porteous, A Seheult. Exact maximum a posteriori estimation for binary images[J]. Jounal of the Royal Statistical Society, Series B, 1989, 51(2): 271-279.
[90] Yuri B, Gareth F. Graph cuts and efficient N-D image segmentation[J]. International Journal of Computer Vision, 2006, 70(2): 109-131.
[91] L Ford, D Fulkerson. Flows in networks[M]. Princeton University Press, 1962.
[92] R K Ahuja, T L Magnanti, J B Orlin. Network flows: theory, algorithms, and applications[M]. Prentice Hall, 1993.
[93] Y Boykov, V Kolmogorov. 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.
[94] A Goldberg, R Tarjan. A new approach to the maximum-flow problem[J]. Journal of the ACM, 1988, 35(4): 921-940.
[95] Kolmogorov V, Zabih R. What energy functions can be minimized via graph cuts?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(2): 147-156.
[96] S F Chang, W Chen, H J Meng, et al. A fully automated content-based videosearch engine supporting spatiotemporal queries[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1998, 8(5): 602-615.
[97] C M Privitera, L W Stark. Algorithms for defining visual regions-of-interest: comparison with eye fixations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(9): 970-982.
[98] Ma Yufei, Zhang Hongjiang. Contrast-based image attention analysis by using fuzzy growing[C]. Proceedings of the ACM International Multimedia Conference and Exhibition, 2003: 374-381.
[99] V Setlur, S Takagi, R Raskar, et al. Automatic image retargeting[C]. In Proceedings of the 4th International Conference on Mobile and Ubiquitous Multimedia, 2005: 59-68.
[100] S Avidan, A Shamir. Seam carving for content-aware image resizing[J]. ACM Transactions on Graphics, 2007, 26(3):10.
[101] B C Ko, J Y Nam. Object-of-interest image segmentation based on human attention and semantic region clustering[J]. Journal of Optical Society of America A, 2006, 23(10): 2462-2470.
[102] K D Zhang, H Q Lu. Automatic salient regions of interest extraction based on edge and region integration[C]. IEEE International Symposium on Industrial Electronics, 2006, 1: 620-623.
[103] Z Yu, H S Wong. A rule based technique for extraction of visual attention regions based on real-time clustering[J]. IEEE Transactions on Multimedia, 2007, 9 (4): 766-784.
[104] H Fu, Z Chi, D Feng. Attention-driven image interpretation with application to image retrieval[J]. Pattern Recognition, 2006, 39(9): 1604-1621.
[105] Weiwei Li, Zhi Liu, Zhongmin Han, et al. Salient object extraction based on nonparametric kernel density estimation[C]. IET Communications Conference on Wireless, Mobile and Sensor Networks, Shanghai, 2007: 402-405.
[106] E P Ong, B J Tye, W S Lin, et al. An efficient video object segmentationscheme[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, 2002, 4: 3361-3364.
[107] Ziliani F, Cavallaro A. Image analysis for video surveillance based on spatial regularization of a statistical model-based change detection[J]. Real-Time Imaging, 2001, 7: 389-399.
[108] Y Yacob, M J Black. Parameterized modeling and recognition of activities[J]. Computer Vision and Image Understanding, 1999, 73(2): 232-247.
[109] S Jabri, Z Duric, H Wechsler, et al. Detection and location of people in video images using adaptive fusion of colour and edge information[C]. International Conference on Pattern Recognition, 2000, 4: 627-630.
[110] S S Huang, L C Fu, P Y Hsiao. Region-level motion-based background modeling and subtraction using MRFs[J]. IEEE Transaction on Image Processing, 2007, 16: 1446-1456.
[111] M T Lopez, A Fernandez-Caballero, M A Fernandez, et al. Motion features to enhance scene segmentation in active visual attention[J]. Pattern Recognition Letters, 2006, 27(5): 469-478.
[112] M A Fernandez, J Mira, M T Lopez, et al. Local accumulation of persistent activity at synaptic level: application to motion analysis[M]. Lecture Notes in Computer Science, 1995, 930: 137-143.
[113] F C Jeng, J W Woods. Compound Gauss-Markov random fields for image estimation[J]. IEEE Transactions on Signal Processing, 1991, 39(3): 683-697.
[114] Cucchiara R, Granan C, Piccardi M, et al. Detecting moving objects, ghosts, and shadows in video streams[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(10): 1337-1342.
[115] Hsieh Junwei, Hu Wenfong, Chang Chiajung, et al. Shadow elimination for effective moving object detection by Gaussian shadow modeling[J]. Image and Vision Computing, 2003, 21(6): 505-516.
[116] Rosin P, Ellis T. Image difference threshold strategies and shadow detection[A]. In: Proceedings of the 1995 British Conference on Machine Vision[C],Birmingham, United Kingdom, 1995: 347-356.
[117]顾建栋,刘志,张兆杨.结合核密度估计和边缘信息的运动对象分割算法[J].计算机辅助设计与图形学学报, 2009, 21(2): 223-228.
[118]邓宇,李振波,李华.图切割支持的融合颜色和梯度特征的实时背景减除方法[J].计算机辅助设计与图形学学报, 2006, 18(11): 1741-1747.
[2] B KP Horn, B G Schunck.. Determining optical Flow[J]. Artificial Intelligence, 1981, 17: 185-203.
[3] H H Nagel. Displacement vectors derived from second order intensity variations in image sequence[J]. Computer Graphics and Image Processing, 1983, 21: 299-324.
[4] Liu Haiying, Rama C, Azriel R. Accurate dense optical flow estimation using adaptive structure tensors and a parametric model[J]. IEEE transactions on image processing, 2003, 12: 1170-1180.
[5] Weickert J, Schnorr C. Variational optic flow computation with a spatio-temporal smoothness constraint[J]. Journal of Mathematical Imaging and Vision, 2001, 14(3): 245-255.
[6] Choi J G, Kim S D. Multi-stage segmentation of optical flow field[J]. Signal Processing, 1996, 54(2): 109-118.
[7] Tuncel E, Onural L. Utilization of the recursive shortest spanning tree algorithm for video-object segmentation by 2-D affine motion modeling[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2000, 10(5): 776-781.
[8] Ma Kaikuang, Wang Haiyun. Unsupervised semantic video objects segmentation over optical-flow field[C]. Seventh International Conference on Control, Automation, Robotics and Vision, Singapore, 2002, 1: 1216-1221.
[9] Y Zinbi, Y Chahir, A Elmoataz. Moving object segmentation using optical flow with active contour model[C]. 2008 3rd International Conference on Informationand Communication Technologies: From Theory to Applications, Damascus, Syria, 2008: 1-5.
[10] Jain R. Difference and accumulative difference pictures in dynamic scene analysis [J] . Image and Vision Computing, 1984, 2(2) : 98-108.
[11]印勇,张影.基于变化检测的视频对象分割算法研究[J].计算机工程与应用,2008,44(13): 161-163.
[12] Salvador E, Cavallaro A, Ebrahimi T. Cast shadow segmentation using invariant color features[J]. Computer Vision and Image Understanding, 2004, 95(2): 238-259.
[13] Xu Dong, Liu Jianzhuang, Li Xuelong, et al. Insignificant shadow detection for video segmentation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2005, 15(8): 1058-1064.
[14] Chien S Y, Ma S Y, Chen L G. Efficient moving object segmentation algorithm using background registration technique [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2002, 12(7): 577-586.
[15] Elgammal A, Duraiswami R, Harwood D, et al. Background and foreground modeling using non-parametric kernel density estimation for visual surveillance[J]. Proceedings of the IEEE, 2002 , 90 (7):1151-1162.
[16] Stauffer C, Grimson W E L. Learning patterns of activity using real-time tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 747-757.
[17] Neri A, Colonnese S, Russo G, et al. Automatic moving object and background separation[J]. Signal Processing, 1998, 66(2): 219-232.
[18] Aach T, Kaup A, Mester R. Statistical model2based change detection in moving video[J]. Signal Processing, 1993, 31(2): 165-180.
[19] Ziliani F, Cavallaro A. Image analysis for video surveillance based on spatial regularization of a statistical model-based change detection[J]. Real-Time Imaging, 2001, 7(5): 389-399.
[20] Sifakis E, Tziritas G. Moving object localisation using a multi-label fast marching algorithm[J]. Signal Processing: Image Communication, 2001, 16 (10): 963-976.
[21] Cavallaro A , Ebrahimi T. Accurate video object segmentation through change etection[C]. IEEE International Conference on Multimedia and Expo. 2002, 1: 445-448.
[22] Fan J, Ji Y, Wu L. Automatic moving object extraction toward content-based video representation and indexing[J]. Visual Communication and Image Representation, 2001, 12 (3): 306-347.
[23] Fan J P, Zhu X Q, Wu L D. Automatic model-based semantic object extraction algorithm. IEEE Transactions on Circuits and Systems for Video Technology, 2001, 11(10): 1073-1084.
[24] Luo Huitao, Eleftheriadis Alexandros. Model-based segmentation and tracking of head-and-shoulder video objects for real time multimedia services[J]. IEEE Transactions on Multimedia, 2003, 5(3): 379-389.
[25] Su Yih-Ming, Hsieh Chaur-Heh. A novel model-based segmentation approach to extract caption contents on sports videos[C]. IEEE International Conference on Multimedia and Expo. Toronto, 2006: 1829-1832.
[26] Zhang Dengsheng, Lu Guojun. Segmentation of moving objects in image sequences: A review. Circuits, Systems, and Signal Processing, 2001, 20(2): 143-183.
[27] Mech R, Wollborn M. A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving camera. Signal Processing, 1998, 66(2): 203-217.
[28] Choi G, Lee S W, Kim S D. Spatio-temporal video seg-mentation using a joint similarity measure[J]. IEEE Transactions Circuits Systems for Video Technology, 1997, 7 (2): 279-286.
[29] Greenspan H, Goldberger J, Mayer A. Probabilistic Space-Time Video Modelingvia Piecewise GMM. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(3): 384-396.
[30] Ahmed R, Karmakar G C, Dooley L S. Efficient probabilistic spatio-temporal video object segmentation[C]. 6th IEEE/ACIS International Conference on Computer and Information Science, Melbourne, 2007: 807-811.
[31] Boykov Y Y, Jolly M P. Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images[C]. Eighth IEEE International Conference on Computer Vision, Vancouver, 2001, 1: 105-112.
[32] Rother C, Kolmogorov V, Blake A.“Grabcut”—interactive foreground extraction using iterated graph cuts[J]. ACM Transactions on Graphics, 2004, 23(3): 309-314.
[33] Criminisi A, Cross G, Blake A, et al. Bilayer segmentation of live video[C]. In Proceedings of IEEE Computer Vision and Pattern Recognition, 2006, 1: 53-60.
[34] Sun J, Jia J, Tang C K, et al. Poisson matting[C]. ACM Transactions on Graphics, 2004, 23: 315-321.
[35] Chuang Y Y, Curless B, Salesin D H, et al. A Bayesian approach to digital matting[C]. In Proceedings of IEEE Computer Vision and Pattern Recognition, 2001, 2: 264-271.
[36] Chuang Y Y, Agarwala A, Curless B, et al. Video matting of complex scenes[C]. ACM Transactions on Graphics, United states, 2002, 21(3): 243-248.
[37] Levin A, Rav-Acha A, Lischinski D. Spectral matting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(10): 1699-1712.
[38] Levin A, Lischinski D, Weiss Y. A closed form solution to natural image matting[C]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, 2006, 1: 61-68.
[39] Wang Jue, Agrawala M, Cohen M F. Soft scissors: an interactive tool for realtime high quality matting[C]. 34th Annual Meeting of the Association for Computing Machinery's Special Interest Group on Graphics, San Diego, 2007, 26 (3): 1-6.
[40] Bai Xue, Sapiro G. Geodesic matting: a framework for fast interactiv image and video segmentation and matting[J]. International Journal on Computer Vision, 2009, 82(2): 113-132.
[41] L Itti, C Koch, E Niebur. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259.
[42] Cheng Wenhuang, Chu Weita, Wu Jaling. A visual attention based region-of-interest determination framework for video sequences[J]. IEICE Transactions on Information and Systems, 2005, E88-D: 1578-1586.
[43] Ma Yufei, Hua Xiansheng, Lu Lie, et al. A generic framework of user attention model and its application in video summarization[J]. IEEE Transactions Multimedia, 2005, 7(5): 907-919.
[44] Hu Yiqun, Xie Xing, Ma Weiying, et al. Salient region detection using weighted feature maps based on the human visual attention model[C]. Advances in Multimedia Information Processing-PCM, 2004, LNCS 3332: 993-1000.
[45] Han Junwei, Ngan K N, Li Mingjing, et al. Towards unsupervised attention object extraction by integrating visual attention and object growing[C]. International Conference on Image Processing, 2004, 5: 941-944.
[46] Han Junwei, Ngan K N, Li Mingjing, et al. Unsupervised extraction of visual attention objects in color images[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2006, 16(1): 141-145.
[47] Park K T, Moon Y S. Automatic extraction of salient objects using feature maps[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Honolulu, 2007, 1: 1617-1620.
[48] Lu Yinghua, Zhang Xiaohua, Kong Jun, et al. A novel objects of interest extraction approach using attention-driven model for content-based image retrieval[C]. 1st International Congress on Image and Signal Processing, Hainan, 2008, 1: 339-343.
[49] Atsumi M. Attention-based segmentation on an image pyramid sequence[C]. 10th International Conference on Advanced Concepts for Intelligent Vision Systems, France, 2008, 5259 LNCS: 625-636.
[50] Pirnog I, Oprea C, Paleoloqu C. Image content extraction using a bottom-up visual attention model[C]. 3rd International Conference on Digital Society, Cancun, 2009: 300-303.
[51] Borba G B, Gamba H R, Marques O, et al. Extraction of salient regions of interest using visual attention models[J]. Proceedings of SPIE-The International Society for Optical Engineering, 2009, 7255: 725508-1-12.
[52] Crevier D. Extracting Salient Objects from Operator-Framed Images[C]. Proceedings-Fourth Canadian Conference on Computer and Robot Vision, Montreal, 2007: 36-43.
[53] Lu Huihai, Woods J C, Ghanbari M. Binary partition tree for semantic object extraction and image segmentation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2007, 17 (3): 378-383.
[54] Maria T Lopez, Miguel A Fernandez, Antonio Fernandez-Caballero, et al. Dynamic visual attention model in image sequences[J]. Image and Vision Computing, 2007, 25 (5): 597–613.
[55] Bastan M, Gudukbay U, Ulusoy O. Segmentation-based extraction of important objects from video for object-based indexing[C]. IEEE International Conference on Multimedia and Expo, Hannover, 2008: 1357-1360.
[56] J Serra, L Vincent. An overview of morphological filtering[J]. Circuits, Systems and Signal Processing, 1992, 11(1): 47-108.
[57] Arun N Netravali, Barry G Haskell. Digital pictures: representation, compression and standards (2nd edition) [M]. Spring street: Plenum Press, 1995.
[58] Duda Richard O, Hart Peter E, Stork David G. Pattern classication (2nd edition) [M]. New York: Wiley, 2000.
[59] Ziou D, Tabbone S. Edge detection techniques an overview[J]. InternationalJournal of Pattern Recognition and Image Analysis, 1998, 8(4): 537-559.
[60] John Canny. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.
[61] R Deriche, Using Canny's criteria to derive an optimal edge detectorecursively implemented[J]. International Journal of Computer Vision, 1987,1: 167-187.
[62] P L Rosin. Edges: saliency measures and automatic thresholding[J]. Machine Vision and Applications, 1997, 9(4): 139-159.
[63] P L Rosin. Comments on ground from figure discrimination[J]. Pattern Recognition Letters, 2003, 24(15): 2761-2766.
[64] D R Martin, C C Fowlkes, J Malik. Learning to detect natural image boundaries using local brightness, color, and texture cues[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26 (5): 530–549.
[65] A. Sha’ashua and S Ullman. Structural saliency: the detection of globally salient structures using a locally connected network[J]. Second International Conference on Computer Vision, 1988: 321–327.
[66] G Guy, G Medioni. Inferring global perceptual contours from local features[J]. International Journal of Computer Vision, 1996, 20(1-2): 113-133.
[67] J S Huang, D H Tseng. Statistical theory of edge detection[J]. Computer vision, graphics, and image processing, 1988, 43(3): 337-346.
[68] D Marr, E Hidreth. Theory of edge detection. Proceedings of the Royal Society of London. Series B, Biological Sciences, 1980, 207 (1167) : 187-217.
[69] V Nalwa, T O Binford. On detecting edges[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6) : 699-714.
[70] K N Le, K P Dabke, G K Egan. Hyperbolic wavelet power spectra of nonstationary signals[J]. Optical Engineering, 2003, 42 (10): 3017-3037.
[71] R C Gonzales, R E Woods. Digital Image Processing[M]. New Jersey: Prentice Hall, Inc., 2002.
[72] R M Haralick, L G Shapiro. Survey-image segmentation techniques[J], ComputerVision Graphics and Image Processing, 1985, 29: 100-132.
[73] Cui Weihong, Guan Zequn, Zhang Zhiyi. An improved region growing algorithm for image segmentation[C], International Conference on Computer Science and Software Engineering. Wuhan, 2008, 6: 93-96.
[74] A Bleau, L J Leon. Watershed-based segmentation and region merging[J]. Computer Vision and Image Understanding, 2000, 77(3): 317–370.
[75] Ilya Levner, Zhang Hong. Classification-Driven Watershed Segmentation[J]. IEEE Transactions On Image Processing, 2007, 16(5): 1437–1445.
[76] A K Jain, R C Dubes. Algorithms for clustering data[M]. New Jersey: Prentice Hall, 1988.
[77] T Kurita. An efficient agglomerative clustering algorithm using a heap[J]. Pattern Recognition, 1991, 24(3): 205-209.
[78] H Frigui, R Krishnapuram. A robust competitive clustering algorithm with applications in computer vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(5): 450-465.
[79] E J Pauwels, G Frederix. Finding salient regions in images: nonparametric clustering for image segmentation and grouping[J]. Computer Vision and Image Understanding, 1999, 75(1): 73-85.
[80] J R Ohm, P Ma. Feature-based cluster segmentation of image sequences[C]. Proceedings International Conference on Image Processing. 1997, 3: 178-181.
[81] M K Ng. A note on constrained k-means algorithm[J]. Pattern Recognition, 2000, 33: 515-519.
[82] Y H Kuan, S T Chen, C M Kuo, et al. A novel unsupervised salient region segmentation for color images[C], International Conference on Innovative Computing, Information and Control, 2006, 2: 96-99.
[83] Stan Z Li. Markov Random Field Modeling in Image Analysis (3rd Edition). Series: Advances in Pattern Recognition. Springer. 2009.
[84] S Geman, D Geman. Stochastic relaxation, gibbs distributions, and the Bayesianrestoration of images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984, 6: 721-741.
[85] J Besag. On the statistical analysis of dirty pictures[J]. Journal of the Royal Statistical Society. Series B, 1986, 48(3): 259-302.
[86] P Chou, C Brown. The theory and practice of Bayesian image labeling[J]. International Journal of Computer Vision, 1990, 4: 185-210.
[87] Moscato P. On evolution, search, optimization, genetic algorithms and martial arts: Towards memetic algorithms. C3P Report 826, Caltech Concurrent Computation Program. 1989.
[88] Radcliffe N J, Surry P D. Formal memetic algorithms. Proceedings of the AISB Workshop on Evolutionary Computing, Leeds, 1994, 865: 1-14.
[89] D Greig, B Porteous, A Seheult. Exact maximum a posteriori estimation for binary images[J]. Jounal of the Royal Statistical Society, Series B, 1989, 51(2): 271-279.
[90] Yuri B, Gareth F. Graph cuts and efficient N-D image segmentation[J]. International Journal of Computer Vision, 2006, 70(2): 109-131.
[91] L Ford, D Fulkerson. Flows in networks[M]. Princeton University Press, 1962.
[92] R K Ahuja, T L Magnanti, J B Orlin. Network flows: theory, algorithms, and applications[M]. Prentice Hall, 1993.
[93] Y Boykov, V Kolmogorov. 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.
[94] A Goldberg, R Tarjan. A new approach to the maximum-flow problem[J]. Journal of the ACM, 1988, 35(4): 921-940.
[95] Kolmogorov V, Zabih R. What energy functions can be minimized via graph cuts?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(2): 147-156.
[96] S F Chang, W Chen, H J Meng, et al. A fully automated content-based videosearch engine supporting spatiotemporal queries[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1998, 8(5): 602-615.
[97] C M Privitera, L W Stark. Algorithms for defining visual regions-of-interest: comparison with eye fixations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(9): 970-982.
[98] Ma Yufei, Zhang Hongjiang. Contrast-based image attention analysis by using fuzzy growing[C]. Proceedings of the ACM International Multimedia Conference and Exhibition, 2003: 374-381.
[99] V Setlur, S Takagi, R Raskar, et al. Automatic image retargeting[C]. In Proceedings of the 4th International Conference on Mobile and Ubiquitous Multimedia, 2005: 59-68.
[100] S Avidan, A Shamir. Seam carving for content-aware image resizing[J]. ACM Transactions on Graphics, 2007, 26(3):10.
[101] B C Ko, J Y Nam. Object-of-interest image segmentation based on human attention and semantic region clustering[J]. Journal of Optical Society of America A, 2006, 23(10): 2462-2470.
[102] K D Zhang, H Q Lu. Automatic salient regions of interest extraction based on edge and region integration[C]. IEEE International Symposium on Industrial Electronics, 2006, 1: 620-623.
[103] Z Yu, H S Wong. A rule based technique for extraction of visual attention regions based on real-time clustering[J]. IEEE Transactions on Multimedia, 2007, 9 (4): 766-784.
[104] H Fu, Z Chi, D Feng. Attention-driven image interpretation with application to image retrieval[J]. Pattern Recognition, 2006, 39(9): 1604-1621.
[105] Weiwei Li, Zhi Liu, Zhongmin Han, et al. Salient object extraction based on nonparametric kernel density estimation[C]. IET Communications Conference on Wireless, Mobile and Sensor Networks, Shanghai, 2007: 402-405.
[106] E P Ong, B J Tye, W S Lin, et al. An efficient video object segmentationscheme[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, 2002, 4: 3361-3364.
[107] Ziliani F, Cavallaro A. Image analysis for video surveillance based on spatial regularization of a statistical model-based change detection[J]. Real-Time Imaging, 2001, 7: 389-399.
[108] Y Yacob, M J Black. Parameterized modeling and recognition of activities[J]. Computer Vision and Image Understanding, 1999, 73(2): 232-247.
[109] S Jabri, Z Duric, H Wechsler, et al. Detection and location of people in video images using adaptive fusion of colour and edge information[C]. International Conference on Pattern Recognition, 2000, 4: 627-630.
[110] S S Huang, L C Fu, P Y Hsiao. Region-level motion-based background modeling and subtraction using MRFs[J]. IEEE Transaction on Image Processing, 2007, 16: 1446-1456.
[111] M T Lopez, A Fernandez-Caballero, M A Fernandez, et al. Motion features to enhance scene segmentation in active visual attention[J]. Pattern Recognition Letters, 2006, 27(5): 469-478.
[112] M A Fernandez, J Mira, M T Lopez, et al. Local accumulation of persistent activity at synaptic level: application to motion analysis[M]. Lecture Notes in Computer Science, 1995, 930: 137-143.
[113] F C Jeng, J W Woods. Compound Gauss-Markov random fields for image estimation[J]. IEEE Transactions on Signal Processing, 1991, 39(3): 683-697.
[114] Cucchiara R, Granan C, Piccardi M, et al. Detecting moving objects, ghosts, and shadows in video streams[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(10): 1337-1342.
[115] Hsieh Junwei, Hu Wenfong, Chang Chiajung, et al. Shadow elimination for effective moving object detection by Gaussian shadow modeling[J]. Image and Vision Computing, 2003, 21(6): 505-516.
[116] Rosin P, Ellis T. Image difference threshold strategies and shadow detection[A]. In: Proceedings of the 1995 British Conference on Machine Vision[C],Birmingham, United Kingdom, 1995: 347-356.
[117]顾建栋,刘志,张兆杨.结合核密度估计和边缘信息的运动对象分割算法[J].计算机辅助设计与图形学学报, 2009, 21(2): 223-228.
[118]邓宇,李振波,李华.图切割支持的融合颜色和梯度特征的实时背景减除方法[J].计算机辅助设计与图形学学报, 2006, 18(11): 1741-1747.