行人交通的视频检测方法综述

摘要/Abstract

摘要： 行人交通是我国城市居民出行的主要交通方式，而行人交通的视频检测技术对于智能交通系统的发展与应用具有重要意义，通过对行人检测和分析确定行人的运动轨迹，提取行人交通参数，为交通规划、管理与控制提供科学的数据。首先回顾行人交通视频检测技术的发展历程，综述研究的方法、技术和主要成果；其次，从行人交通系统的一般处理框架—行人检测、识别、跟踪和交通参数的提取,分层次回顾低级、中级和高级各处理阶段的发展水平；重点阐述各处理阶段的现有技术和方法,并将每阶段相应地划分为不同方法子类加以讨论；最后，分析行人检测研究的技术难点及未来的发展趋势。

关键词: 交通工程, 行人交通, 交通数据, 视频检测, 交通参数

Abstract: Pedestrian traffic is the major trip mode of Chinese urban residents. Being the important part of intelligent transportation system, pedestrian traffic data collection method based on video image processing is the basis of traffic planning, traffic management and traffic control by detecting pedestrian, analyzing motion trajectory and extracting traffic parameter. This paper reviews the development of pedestrian traffic collection method technique and describes four steps studied intensively in the past work including pedestrian detection, recognition, tracking, and traffic parameter extraction. Finally, the recent problems and prospect in this area are also provided.

Key words: traffic engineering, pedestrian traffic, traffic data, video detection: traffic parameter

中图分类号:

U491

邵春福,李娟,赵熠,董春娇. 行人交通的视频检测方法综述[J]. 交通运输系统工程与信息, 2008, 8(4): 23-29 .

SHAO Chun-fu, LI Juan,ZHAO Yi,DONG Chun-jiao. Review of Pedestrian Traffic Data Collection Method Based on Video Image Processing[J]. Journal of Transportation Systems Engineering and Information Technology, 2008, 8(4): 23-29 .

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract17682.shtml

http://www.tseit.org.cn/CN/Y2008/V8/I4/23

参考文献

[1] WANG L, NING H Z, HU W M, TAN T N. Gait Recognition Based on Procrustes Shape Analysis[C]. IEEE Int. Conf. on Image Processing, 2002: 433-436.

[2] Haritaoglu I, Harwood D, Davis L.S. Hydra: multiple people detection and tracking using silhouettes[C]. Second IEEE Workshop on Visual Surveillance, 1999: 210-217.

[3]王亮, 胡卫明, 谭铁牛. 人运动的视觉分析综述[J]. 计算机学报, 2002, 25(3): 225-237. [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.]

[4] WANG L , NING H, TAN T, HU W. Fusion of static and dynamic body biometrics for gait recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(2):149–158.

[5] Yilmaz A, Javed O, Shah M.. Object tracking: a survey[J]. ACM Computing Surveys, 2006, 38(4): 11-45.

[6] 王亮. 步态分析与识别[D]. 北京：中国科学院，2004. [WANG Liang. Analysis and recognition of gait[D]. Beijing: Chinese Academy of Sciences, 2004. ]

[7] 赵明. 二维视觉对象分割[D]. 杭州：浙江大学，2004. [ZHAO Ming. 2D visual object segmentation[D]. Hangzhou: Zhejiang University, 2004. ]

[8] ZHAO M, LI S Z, BU J J. Shape evaluation for weighted active shape models[C]. Proceedings of the Asian Conference on Computer Vision, 2004(2): 1074-1079.

[9] 常好丽. 运动行人检测与跟踪方法研究[D]. 西安：西北工业大学，2006. [CHANG Hao-li. Research on the method of moving pedestrian detection and tracking[D]. Xi’an: Northwestern Polytechnical University, 2006.]

[10] 陆朝霞. 基于Adaboost算法的行人检测方法研究[D]. 西安: 西北工业大学, 2006. [LU Chao-xia Research on the method of pedestrian detection based on adaboost algorithm [D]. Xi’an: Northwestern Polytechnical University, 2006.]

[11] 邓士弟. 基于交通视频的运动目标检测和跟踪[D]. 西安：西北工业大学，2007. [DENG Shi-di. Moving objects detection and tracking based on traffic video[D]. Xi’an: Northwestern Polytechnical University, 2007. ]

[12] 田广. 基于视觉的行人检测和跟踪技术的研究[D]. 上海:上海交通大学，2007. [TIAN Guang.. Study of visual based pedestrian detection and tracking algorithm[D]. Shanghai: Shanghai Jiaotong University, 2007. ]

[13] 李曦, 曹广益, 付晓薇, 朱新坚. 基于实时图像序列的行人跟踪计数方法[J]. 计算机仿真, 2005, 22 (2): 79-85. [LI Xi, CAO Guang-yi, FU Xiao-wei, ZHU Xin-jian. A method of passing people tracking and counting based on real-time image sequence[J]. Computer Simulation, 2005, 22 (2): 79-85. ]

[14] 邵春福, 赵熠, 吴戈. 道路交通数据采集技术研究展望[J]. 现代交通技术, 2006, 6: 66-70. [SHAO Chun-fu, ZHAO Yi, WU G.e. Review of road traffic data collection technology[J]. Modern Transportation Technology, 2006, 6: 66-70. ]

[15] Shao C F， Zhao Y， Yue H， Zhang X. Study on a vision based system for real-time collection of mixed traffic data[C]. Proceedings of ICTTS’ 2006, Science Press, 2006: 606-614.

[16]岳昊, 邵春福, 赵熠, 陈小明. 基于视频序列的行人多目标跟踪方法研究[J]. 交通运输系统工程与信息, 2007, 7(4): 47-51. [YUE Hao, SHAO Chun-fu, ZHAO Yi, CHEN Xiao-ming. A study on moving pedestrian tracking based on video sequences[J]. Journal of Transportation Systems Engineering and Information Technology, 2007, 7(4): 47-51. ]

[17] Haritaoglu I, Harwood D, Davis L S. A human body part labeling system using silhouettes [J]. Fourteenth International Conference on Pattern Recognition, 1998(1): 77-82.

[18] McKenna S, et al. Tracking groups of people [J]. Computer Vision and Image Understanding, 2000, 80(1): 42-56.

[19] Nixon M S, et al. Automatic gait recognition in BIOMETRICS-personal identification in networked society [J]. Kluwer Academic, 1999: 231-249.

[20] Winter D A. The Biomechanics and Motor Control of Human Movement[M]. 2nd Eds. John Wiley & Sons, 1990.

[21] Bedenas J, Boder M, Pla F. Segmenting traffic scenes from grey level and motion information[J]. Pattern Analysis & Applications, 2001, 4(1): 28-38.

[22] Kim J B, Park H S, Park M H, et al. A real-time region-based motion segmentation using adaptive thresholding and k-means clustering[J]. Lecture Notes in Computer Science- AI 2001: Advances in Artificial Intelligence, 2001, 2256: 213-224.

[23] Michael Girard, Anthony A Maciejewski. Computational modeling for the computer animation of legged figures[J]. ACM SIGGRAPH’85, Proceedings, 1985,7: 263-270.

[24] 洪炳熔, 贺怀清. 虚拟人的步行和跑步运动控制方法的研究[J]. 高技术通讯, 2001, 3: 91－95.[HONG Bing-rong, HE Huai-qing. Research of waling and running locomotion control methods for virtual humans[J]. Chinese High Technology Letters, 2001, 3: 91-95. ]

[25]Meyer D, Denzler J, Niemann H. Model based extraction of articulated objects in image sequences for gait analysis[C]. Proc IEEE International Conference on Image Processing,Santa Barbara, California, 1997, 78-81.

[26] Viola P, Jones M J, Snow D. Detecting pedestrians using patterns of motion and appearance[J]. Int. J. Comp. Vision, 2005, 63(2):153–161.

[27] Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]. IEEE International Conference on Computer Vision and Pattern Recognition, 2005, I: 886–893.

[28] Wu Y, Hua T. u, G. . A statistical field model for pedestrian detection [C]. IEEE International Conference on Computer Vision, 2005, I: 1023–1030.

[29] 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.

[30] Hutenlocker P, Rucklidge W. Tracking nonrigid objects in complex scenes[C]. Proc. Int. Conf. Computer Vision (ICCV), 1992:155-163.

[31] Chapelle O, Haffner P, Vapnik V N. Support vector machines for histogram-based image classification[C]. IEEE Trans. On Neural networks, 1999, 10(5): 1055–1064.

[32] Jang D S, Choi H I. Active models for tracking moving objects[C]. Pattern Recognition, 2000, 33(7): 1135-1146.

[33] Isard M, Blake A. CONDENSATION-conditional density propagation for visual tracking[J]. Intl. Journal of Computer Vision, 1998, 29(1): 5-28.

[34] Gilbert W J. Modern Algebra with Application[M]. New York: John Wiley & Sons, 1976.

[35] Niyogi S A, Adelson E H. Analyzing and recognizing walking figures in XYT[C]. Proc Of IEEE Computer Society Conf on Computer Vision and Pattern Recognition, 1994: 469-474.

[36] Rohr K. Towards model-based recognition of human movements in sequences[J]. Computer Vision, Graphics and Image Processing, 1994: 94-115.

[37] Bertalmio M, Sapiroo G., Randll G. Morphing active contours[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(7): 733-737.

[38] Paragios N, Deriche R. Geodesic active contours and level sets for the detection and tracking of moving objects[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(3): 266-280.

[39] Peterfreund N. Robust tracking of position and velocity with Kalman snakes[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(6): 564-569.

[40]Wren C R, Azarbayejani A, Darrell T, Pentland A P. Pfinder: Real-time tracking of the human body[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1997,19(7):780-785

[41]Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 2003, 25 (5): 564-577.

[42] Jepson A D,Fleet D J,El-Maraghi T F.Robust online appearance models for visual tracking[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2003,25(10):1296-1311.

[43] Segen J, Pingali S. A camera-based system for tracking people in real time[C]. Proc International Conference on Patern Recognition, Vienna, 1996:63-67.

[44] Shafique K, Shah M. A noniterative greedy algorithm for multiframe point correspondence[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27(1): 51-65.

[45] 王建军，严宝杰编著. 交通调查与分析[M]. 北京：人民交通出版社，2004. [WANG Jian-jun, YAN Bao-jie. Traffic Survey and Analysis[M]. Beijing: China Communications Press, 2004. ]