智能视频监控系统中目标检测与跟踪关键技术研究
|
摘要
近年来,智能视频监控技术在各个领域得到了广泛的应用。运动目标检测和跟踪技术是智能视频监控系统的关键技术,一直是学术界研究的热点和难点问题。由于背景变化、光照条件、遮挡、阴影和目标物建模等的复杂性,目标检测和跟踪在理论研究和实践应用上都还面临着许多难题。
本文在综合分析现有目标检测和跟踪算法的基础上,重点对动态背景下的目标检测和跟踪,以及多目标跟踪问题进行了研究,主要内容如下:
(1)本文对智能视频监控中的相关关键技术进行了概述。比较和分析了常用目标检测算法:光流法、二帧差法、三帧差法、背景减除法和高斯建模法的原理和优缺点;研究了目标跟踪方法的分类、原理和典型算法:粒子滤波、Meanshift、Kalman Filter,并探讨了目标跟踪领域中的难点问题。
(2)针对动态背景下的目标检测问题,本文提出了一种适用于动态背景下的基于背景运动参数估计的目标检测算法,并通过实验验证了算法的有效性。
(3)本文重点研究了Camshift算法,在此基础上,针对Camshift在复杂动态背景下跟踪鲁棒性不高的缺点,提出了一种适用于动态背景下的改进Camshift目标跟踪算法。
(4)为了克服传统Camshift只能跟踪单目标这一局限性,以及实现多目标跟踪中对运动、静止、再进入场景、恢复运动和退出场景目标的持续跟踪,论文提出了基于Camshift与目标轨迹跟踪相结合的多目标跟踪算法。
In recent years, intelligent video surveillance technology has been widely used in various fields. Moving target detection and tracking is the key technology of intelligent video surveillance system, and has been the hot and difficult problems of academic research. Because of background changing, lighting conditions, occlusion, shadow, and the complexity of objects modeling in real scenes, target detection and tracking are still facing many problems both in theoretical study and practical applications.
Based on the comprehensive analysis of existing target detection and tracking algorithm, this thesis extends the research mainly on two aspects:Target detection and tracking in dynamic background, and multi-target tracking problem. The main work of this thesis includes the following four aspects:
(1) In this thesis, key technologies of intelligent video surveillance are summarized. The principle, advantages and disadvantages of currently used target detection algorithm (optical flow method, two-frame subtraction method, third-frame subtraction method, simple background subtraction method and the Gaussian Modeling method) are compared and analyzed; The classification and principles of currently used tracking methods are studied, the typical tracking algorithms: Particle Filter, Meanshift and Kalman Filter are explored, and current difficult problems of target tracking are summarized.
(2) Aiming at the objects detecting problem in dynamic background, a detection algorithm based on the estimation of background motion parameters is presented to detect motion objects in dynamic background in this paper, and the validity of the algorithm is verified by experiment.
(3) Aiming at the unsatisfied tracking robustness of Camshift in complex and dynamic background, an improved Camshift algorithm, which can be apply to dynamic background, is proposed.
(4) In order to improve the demerit of Camshift that it only can be used in single object scenes, and to track the static object, out-scene objects, re-moving objects and re-enter objects in real applications, an improved algorithm based on the combination of motion trajectory and Camshift, is presented.
本文在综合分析现有目标检测和跟踪算法的基础上,重点对动态背景下的目标检测和跟踪,以及多目标跟踪问题进行了研究,主要内容如下:
(1)本文对智能视频监控中的相关关键技术进行了概述。比较和分析了常用目标检测算法:光流法、二帧差法、三帧差法、背景减除法和高斯建模法的原理和优缺点;研究了目标跟踪方法的分类、原理和典型算法:粒子滤波、Meanshift、Kalman Filter,并探讨了目标跟踪领域中的难点问题。
(2)针对动态背景下的目标检测问题,本文提出了一种适用于动态背景下的基于背景运动参数估计的目标检测算法,并通过实验验证了算法的有效性。
(3)本文重点研究了Camshift算法,在此基础上,针对Camshift在复杂动态背景下跟踪鲁棒性不高的缺点,提出了一种适用于动态背景下的改进Camshift目标跟踪算法。
(4)为了克服传统Camshift只能跟踪单目标这一局限性,以及实现多目标跟踪中对运动、静止、再进入场景、恢复运动和退出场景目标的持续跟踪,论文提出了基于Camshift与目标轨迹跟踪相结合的多目标跟踪算法。
In recent years, intelligent video surveillance technology has been widely used in various fields. Moving target detection and tracking is the key technology of intelligent video surveillance system, and has been the hot and difficult problems of academic research. Because of background changing, lighting conditions, occlusion, shadow, and the complexity of objects modeling in real scenes, target detection and tracking are still facing many problems both in theoretical study and practical applications.
Based on the comprehensive analysis of existing target detection and tracking algorithm, this thesis extends the research mainly on two aspects:Target detection and tracking in dynamic background, and multi-target tracking problem. The main work of this thesis includes the following four aspects:
(1) In this thesis, key technologies of intelligent video surveillance are summarized. The principle, advantages and disadvantages of currently used target detection algorithm (optical flow method, two-frame subtraction method, third-frame subtraction method, simple background subtraction method and the Gaussian Modeling method) are compared and analyzed; The classification and principles of currently used tracking methods are studied, the typical tracking algorithms: Particle Filter, Meanshift and Kalman Filter are explored, and current difficult problems of target tracking are summarized.
(2) Aiming at the objects detecting problem in dynamic background, a detection algorithm based on the estimation of background motion parameters is presented to detect motion objects in dynamic background in this paper, and the validity of the algorithm is verified by experiment.
(3) Aiming at the unsatisfied tracking robustness of Camshift in complex and dynamic background, an improved Camshift algorithm, which can be apply to dynamic background, is proposed.
(4) In order to improve the demerit of Camshift that it only can be used in single object scenes, and to track the static object, out-scene objects, re-moving objects and re-enter objects in real applications, an improved algorithm based on the combination of motion trajectory and Camshift, is presented.
引文
[1]张海清.计算机智能视频监控系统的目标运动检测和跟踪研究[D].中国科学技术大学,2007.
[2]刘一山.智能监控系统中运动目标检测与跟踪技术的研究[D].西安科技大学,2007.
[3]赵俊.智能视频监控系统关键技术研究[D].西安电子科技大学,2007.
[4]李爽.运动目标识别和跟踪的智能化视频监控系统研究[D].辽宁工学院,2007.
[5]孟凤.视频监控系统中运动目标检测与跟踪算法的研究[D].燕山大学,2007.
[6]刘雪.研究运动目标检测与跟踪技术[D].山东大学,2007.
[7] Paragios N, Deriche R. Geodesic active contours and level sets for the detection and tracking of moving objects .IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22 (3) :266-280 .
[8] Jong Bae Kim, Hang Joon Kim. Efficient region-based motion segmentation for a video monitoring system .Pattern Recognition Letters, 2003, 24 (1-3):113-128.
[9] LI Guang-lun, SHU Wei-qun. Real-time Detection for Moving Object in Video Monitor System [ J ]. Computer Engineering, 2009, 35(17):217-222.
[10] Fejes S, Davis L S. Detection of Independent Motion Using Directional Motion Estimation[R]. University of Maryland, Technical Report: CAR-TR-866, CS3815, 1997.
[11] Xu L Q,Landabaso J L,Lei B. Segmentation and track-ing of multiple moving objects for intelligent video analysis[J] .BT Technology Journal, 2004, 22 (3) :140-150 .
[12] Mitiche A, Wang Y F, Aggarwal. Experiments in computing optical flow with gradient-based, multi-constraint method .Pattern Recognition, 1987, 20 (2):173-179.
[13] TENG Chin-Hung,LAI Shang-Hong. Accurate optical flow computation under non-uniform brightness variations [J] .Computer Vision and ImageUnderstanding, 2005, (11):315-346.
[14] GHOSAL Sugata. A moment-based unified approach to image feature detection[C] .Image Processing, IEEE, 1997, 6 (6):781-793.
[15] GHOSAL Sugata. Robust optical flow estimation [J] .Image Processing, IEEE, 1994, 2 (12):780-784.
[16] Barron J L, Fleet D J, Beauchemin S. Performance of optical flow techniques .International Journal of Computer Vision, 1994, 12 (1):42-77.
[17] ZHANG Juan, MAO Xiao-bo, CHEN Tie-jun. Survey of moving object tracking algorithm [J]. Application Research of Computers, 2006, 26(12):4407-4410.
[18] WANG Liang, HU Wei-ming, TAN Tie-niu. A Survey of Visual Analysis of Human Motion [J]. Chinese Journal of Computers, 2002, 25(3):225-237.
[19] Anderson C, Bert P, Vander W al G. Change detection and tracking using pyramids transformation techniques. In: Proc SPIE Conference on Intelligent Robots and Computer Vision, Cambridge, MAR, 1985, 579: 72-78.
[20] HOU Zhi-Qiang, HAN Chong-Zhao. A Survey of Visual Tracking [J]. ACTA Automatica Sinica, 2006, 32(4):603-617.
[21] HUANG Xin-juan,ZHOU Jie-min,LIU Bo-yang. Moving objects detection approach based on adaptive mixture Gaussian background model [J]. Journal of Computer Applications, 2010, 30(1):71-74.
[22] Power PW, Schoonees JA. Understanding background mixture models for foregrounds segmentation[C] .Proceedings of Image and Vision Computing. New Zealand Auckland. 2002:267-271.
[23] LIU Guang-yu, LIU Guo-dong. Method for moving objection detection based on mixture Guassian models [J]. Computer Engineering and Applications, 2009, 45(24):180-182.
[24] ZHANG Hai-qing, LI Hou-qiang. Object Tracking Through Multiple Cues [J]. Journal of Image and Graphics, 2008, 13(11):2187-2196.
[25] WANG Huan, Wang Jiang-tao,REN Ming-wu,YANG Jing-yu. A New Robust Objects Tracking Algorithm by Fusing Multi-features [J]. Journal of Image and Graphics, 2009, 14(3):489-498.
[26] Ristic B, Arulampalam S, and Gordon N. Beyond the Kalman Filter: Particle Filters for Tracking Applications [M]. Boston, London: Artech House, 2004.
[27] ZHANG Hong-zhi, ZHANG Jin-huan, YUE Hui, HUANG Shi-lin. Object tracking algorithm based on CamShift [J]. Computer Engineering and Design, 2006, 27(11):108-110.
[28] Nummiaro Katja, Koller-meier Esther, Van Gool Luc. Object Tracking with an Adaptive Color-Based Particle Filter [C]. Proceedings of the 24th DAGM Symposium on Pattern Recognition. London, UK : Springer-Verlag, 2003:591-599.
[29] Comaniciu Dorin,Ramesh Visvanathan,Meer Peter. Kernel-based object tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003, 25(5):564-577.
[30] SUN Kai, LIU Shi-rong. Combined algorithm with modified Camshift and Kalman Filter for multi-object tracking [J]. Information and Control, 2009, 38(1):11-16.
[31] LIU Xue, CHANG Fa-liang, WANG Hua-jie. An Object Tracking Method Based on Improved Camshift Algorithm [J]. Microcomputer Information, 2007, 23(21):304-306.
[32] Nouar O D, Ali G, Raphael C. Improved object tracking with Camshift algorithm. Proceedings of the IEEE International Conference on Acoustics, Speech,and Signal Processing[C]. Piscataway,NJ,USA: IEEE, 2006,:657-660.
[33] ZHANG Liu-yang, ZHANG Gui-lin. Background motion model parameters estimation based on extended Kanade-Lucas tracker [J]. Computer Applications, 2005, 25(8):1946～1947.
[34] YAN Xiao-ling, LIANG Bo, ZENG Gui-hua. Object tracking method based on block motion estimation [J]. Journal of Image and Graphics, 2008, 13(10):1869～1872.
[35] Aherne F, Thacker N, Rockett P. The Bhattacharyya metric as an absolute similarity measure for frequency coded data[J]. Statistical Techniquts in Pattern Recognition, 1998, 34(4):363-368.
[36] YUE Ying-ying, GAO Yun, ZHANG Xue-jie. An Improved Camshift Algorithm Based on Dynamic Background. 1st International Conference on Information Science and Engineering, 2009.
[37] Ristic B, Arulampalam S, and Gordon N. Beyond the Kalman Filter: ParticleFilters for Tracking Applications [M]. Boston, London: Artech House, 2004.
[38] ZHANG Hong-zhi, ZHANG Jin-huan, YUE Hui, HUANG Shi-lin. Object Tracking Algorithm Based on CamShift [J]. Computer Engineering and Design, 2006, 27(11):108-110.
[39] Nummiaro Katja, Koller-meier Esther,Van Gool Luc. Object Tracking with an Adaptive Color-Based Particle Filter [C]. Proceedings of the 24th DAGM Symposium on Pattern Recognition. London, UK Springer-Verlag, 2003,:591-599.
[40] Sun Kai, LIU Shi-rong. Combined algorithm with modified Camshift and Kalman Filter for multi-object tracking [J]. Information and Control, 2009, 38(1):11-16.
[41] Huang lv-e, Li ping-kang, Du xiu-xia. Automatic Tracking Method for Indoor People Motion Object [J]. Computing Engineering, 2009, 35(9):201-204.
[42] Su Xin-jun, Chen Jin-bo, Xu Fa-wei. Multiple Targets Tracking in Traffic Image Sequence [J]. Journal of Changshu Institute Technology (Nature Sciences), 2009, 23(4):82-86.
[43] LIU Xue, CHANG Fa-liang, WANG Hua-jie. An Object Tracking Method Based on Improved Camshift Algorithm [J]. Microcomputer Information, 2007, 23(21):304-306.
[44] Nouar O D, Ali G, Raphael C. Improved object tracking with Camshift algorithm. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing[C]. Piscataway,NJ,USA:IEEE, 2006,:657-660.
[45]刘瑞祯,于仕琪. OpenCV教程.基础篇[M].北京:北京航空航天大学出版社,2007.6.
[46]冈萨雷斯.数字图像处理[M].电子工业出版社,2004.
[47]徐慧. VisualC++数字图像实用工程案例精选[M].北京:人民邮电出版社,2004.
[48]雷雨权.多媒体电视监控与报警系统[M].北京:国防工业出版社2004.1.
[49]王耀南,李树涛,毛建旭.计算机图像处理与识别技术[M].北京:高等教育出版社,2003.
[50]章毓晋.图像理解与计算机视觉[M].北京:清华大学出版社,2000.
[51] Cheng Yan, Liu Kai-hua. The way to check and track moving object indynamic background [J]. Communications Technology, 2003, 12:104-106.
[52] Wang Xin-hong, Wang Jing, Tian Min, Yang Yu, Li Zhi-peng. Mean Shift Tracking Algorithm based on Spatial Edge Orientation Histograms [J]. Journal of Image and Graphics, 2008, 13(3):586-592.
[53]谭铁牛.智能视觉监控研究进展第二届全国智能视觉监控学术会议论文集[M].北京:科学出版社,2003.
[54]第一届信息科学与技术国际学术会议(The International Conference on Information Science and Engineering,ICISE2009)论文集[C]. IEEE计算机协会出版,2009.
[55]第一届因特网多媒体计算和服务国际学术会议(The First International Conference on Internet Multimedia Computing and Service )论文集[C].ACM出版,2009.
[2]刘一山.智能监控系统中运动目标检测与跟踪技术的研究[D].西安科技大学,2007.
[3]赵俊.智能视频监控系统关键技术研究[D].西安电子科技大学,2007.
[4]李爽.运动目标识别和跟踪的智能化视频监控系统研究[D].辽宁工学院,2007.
[5]孟凤.视频监控系统中运动目标检测与跟踪算法的研究[D].燕山大学,2007.
[6]刘雪.研究运动目标检测与跟踪技术[D].山东大学,2007.
[7] Paragios N, Deriche R. Geodesic active contours and level sets for the detection and tracking of moving objects .IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22 (3) :266-280 .
[8] Jong Bae Kim, Hang Joon Kim. Efficient region-based motion segmentation for a video monitoring system .Pattern Recognition Letters, 2003, 24 (1-3):113-128.
[9] LI Guang-lun, SHU Wei-qun. Real-time Detection for Moving Object in Video Monitor System [ J ]. Computer Engineering, 2009, 35(17):217-222.
[10] Fejes S, Davis L S. Detection of Independent Motion Using Directional Motion Estimation[R]. University of Maryland, Technical Report: CAR-TR-866, CS3815, 1997.
[11] Xu L Q,Landabaso J L,Lei B. Segmentation and track-ing of multiple moving objects for intelligent video analysis[J] .BT Technology Journal, 2004, 22 (3) :140-150 .
[12] Mitiche A, Wang Y F, Aggarwal. Experiments in computing optical flow with gradient-based, multi-constraint method .Pattern Recognition, 1987, 20 (2):173-179.
[13] TENG Chin-Hung,LAI Shang-Hong. Accurate optical flow computation under non-uniform brightness variations [J] .Computer Vision and ImageUnderstanding, 2005, (11):315-346.
[14] GHOSAL Sugata. A moment-based unified approach to image feature detection[C] .Image Processing, IEEE, 1997, 6 (6):781-793.
[15] GHOSAL Sugata. Robust optical flow estimation [J] .Image Processing, IEEE, 1994, 2 (12):780-784.
[16] Barron J L, Fleet D J, Beauchemin S. Performance of optical flow techniques .International Journal of Computer Vision, 1994, 12 (1):42-77.
[17] ZHANG Juan, MAO Xiao-bo, CHEN Tie-jun. Survey of moving object tracking algorithm [J]. Application Research of Computers, 2006, 26(12):4407-4410.
[18] WANG Liang, HU Wei-ming, TAN Tie-niu. A Survey of Visual Analysis of Human Motion [J]. Chinese Journal of Computers, 2002, 25(3):225-237.
[19] Anderson C, Bert P, Vander W al G. Change detection and tracking using pyramids transformation techniques. In: Proc SPIE Conference on Intelligent Robots and Computer Vision, Cambridge, MAR, 1985, 579: 72-78.
[20] HOU Zhi-Qiang, HAN Chong-Zhao. A Survey of Visual Tracking [J]. ACTA Automatica Sinica, 2006, 32(4):603-617.
[21] HUANG Xin-juan,ZHOU Jie-min,LIU Bo-yang. Moving objects detection approach based on adaptive mixture Gaussian background model [J]. Journal of Computer Applications, 2010, 30(1):71-74.
[22] Power PW, Schoonees JA. Understanding background mixture models for foregrounds segmentation[C] .Proceedings of Image and Vision Computing. New Zealand Auckland. 2002:267-271.
[23] LIU Guang-yu, LIU Guo-dong. Method for moving objection detection based on mixture Guassian models [J]. Computer Engineering and Applications, 2009, 45(24):180-182.
[24] ZHANG Hai-qing, LI Hou-qiang. Object Tracking Through Multiple Cues [J]. Journal of Image and Graphics, 2008, 13(11):2187-2196.
[25] WANG Huan, Wang Jiang-tao,REN Ming-wu,YANG Jing-yu. A New Robust Objects Tracking Algorithm by Fusing Multi-features [J]. Journal of Image and Graphics, 2009, 14(3):489-498.
[26] Ristic B, Arulampalam S, and Gordon N. Beyond the Kalman Filter: Particle Filters for Tracking Applications [M]. Boston, London: Artech House, 2004.
[27] ZHANG Hong-zhi, ZHANG Jin-huan, YUE Hui, HUANG Shi-lin. Object tracking algorithm based on CamShift [J]. Computer Engineering and Design, 2006, 27(11):108-110.
[28] Nummiaro Katja, Koller-meier Esther, Van Gool Luc. Object Tracking with an Adaptive Color-Based Particle Filter [C]. Proceedings of the 24th DAGM Symposium on Pattern Recognition. London, UK : Springer-Verlag, 2003:591-599.
[29] Comaniciu Dorin,Ramesh Visvanathan,Meer Peter. Kernel-based object tracking [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003, 25(5):564-577.
[30] SUN Kai, LIU Shi-rong. Combined algorithm with modified Camshift and Kalman Filter for multi-object tracking [J]. Information and Control, 2009, 38(1):11-16.
[31] LIU Xue, CHANG Fa-liang, WANG Hua-jie. An Object Tracking Method Based on Improved Camshift Algorithm [J]. Microcomputer Information, 2007, 23(21):304-306.
[32] Nouar O D, Ali G, Raphael C. Improved object tracking with Camshift algorithm. Proceedings of the IEEE International Conference on Acoustics, Speech,and Signal Processing[C]. Piscataway,NJ,USA: IEEE, 2006,:657-660.
[33] ZHANG Liu-yang, ZHANG Gui-lin. Background motion model parameters estimation based on extended Kanade-Lucas tracker [J]. Computer Applications, 2005, 25(8):1946～1947.
[34] YAN Xiao-ling, LIANG Bo, ZENG Gui-hua. Object tracking method based on block motion estimation [J]. Journal of Image and Graphics, 2008, 13(10):1869～1872.
[35] Aherne F, Thacker N, Rockett P. The Bhattacharyya metric as an absolute similarity measure for frequency coded data[J]. Statistical Techniquts in Pattern Recognition, 1998, 34(4):363-368.
[36] YUE Ying-ying, GAO Yun, ZHANG Xue-jie. An Improved Camshift Algorithm Based on Dynamic Background. 1st International Conference on Information Science and Engineering, 2009.
[37] Ristic B, Arulampalam S, and Gordon N. Beyond the Kalman Filter: ParticleFilters for Tracking Applications [M]. Boston, London: Artech House, 2004.
[38] ZHANG Hong-zhi, ZHANG Jin-huan, YUE Hui, HUANG Shi-lin. Object Tracking Algorithm Based on CamShift [J]. Computer Engineering and Design, 2006, 27(11):108-110.
[39] Nummiaro Katja, Koller-meier Esther,Van Gool Luc. Object Tracking with an Adaptive Color-Based Particle Filter [C]. Proceedings of the 24th DAGM Symposium on Pattern Recognition. London, UK Springer-Verlag, 2003,:591-599.
[40] Sun Kai, LIU Shi-rong. Combined algorithm with modified Camshift and Kalman Filter for multi-object tracking [J]. Information and Control, 2009, 38(1):11-16.
[41] Huang lv-e, Li ping-kang, Du xiu-xia. Automatic Tracking Method for Indoor People Motion Object [J]. Computing Engineering, 2009, 35(9):201-204.
[42] Su Xin-jun, Chen Jin-bo, Xu Fa-wei. Multiple Targets Tracking in Traffic Image Sequence [J]. Journal of Changshu Institute Technology (Nature Sciences), 2009, 23(4):82-86.
[43] LIU Xue, CHANG Fa-liang, WANG Hua-jie. An Object Tracking Method Based on Improved Camshift Algorithm [J]. Microcomputer Information, 2007, 23(21):304-306.
[44] Nouar O D, Ali G, Raphael C. Improved object tracking with Camshift algorithm. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing[C]. Piscataway,NJ,USA:IEEE, 2006,:657-660.
[45]刘瑞祯,于仕琪. OpenCV教程.基础篇[M].北京:北京航空航天大学出版社,2007.6.
[46]冈萨雷斯.数字图像处理[M].电子工业出版社,2004.
[47]徐慧. VisualC++数字图像实用工程案例精选[M].北京:人民邮电出版社,2004.
[48]雷雨权.多媒体电视监控与报警系统[M].北京:国防工业出版社2004.1.
[49]王耀南,李树涛,毛建旭.计算机图像处理与识别技术[M].北京:高等教育出版社,2003.
[50]章毓晋.图像理解与计算机视觉[M].北京:清华大学出版社,2000.
[51] Cheng Yan, Liu Kai-hua. The way to check and track moving object indynamic background [J]. Communications Technology, 2003, 12:104-106.
[52] Wang Xin-hong, Wang Jing, Tian Min, Yang Yu, Li Zhi-peng. Mean Shift Tracking Algorithm based on Spatial Edge Orientation Histograms [J]. Journal of Image and Graphics, 2008, 13(3):586-592.
[53]谭铁牛.智能视觉监控研究进展第二届全国智能视觉监控学术会议论文集[M].北京:科学出版社,2003.
[54]第一届信息科学与技术国际学术会议(The International Conference on Information Science and Engineering,ICISE2009)论文集[C]. IEEE计算机协会出版,2009.
[55]第一届因特网多媒体计算和服务国际学术会议(The First International Conference on Internet Multimedia Computing and Service )论文集[C].ACM出版,2009.