基于Kalman滤波的行人跟踪方法研究

交通运输系统工程与信息 ›› 2009, Vol. 9 ›› Issue (6): 148-153 .

基于Kalman滤波的行人跟踪方法研究

李娟;邵春福*;杨励雅;李琦

北京交通大学城市交通复杂系统理论与技术教育部重点实验室，北京 100044

收稿日期:2009-01-22 修回日期:2009-03-24 出版日期:2009-12-25 发布日期:2009-12-25
通讯作者: 邵春福
作者简介:李娟(1980-），女，山东德州人，博士生.
基金资助:
国家重点基础研究发展计划(973计划)(2006CB705500)；国家自然科学基金(50778015)；中国人民大学科学研究基金(07XND012).

LI Juan; SHAO Chun-fu; YANG Li-ya; LI Qi

MOE Key Laboratory for Transportation Complex Systems Theory and Technology, Beijing Jiaotong University, Beijing 100044, China

Received:2009-01-22 Revised:2009-03-24 Online:2009-12-25 Published:2009-12-25
Contact: SHAO Chun-fu

摘要/Abstract

摘要： 应用视频处理技术对行人交通进行研究和分析受到广泛的重视和发展，已成为智能交通领域的研究热点之一，而行人跟踪是行人交通采集系统的基础，是后续交通参数提取，行为分析的前提.本文提出一种基于Kalman滤波的行人跟踪方法.首先，利用改进的混合高斯模型提取背景，并采用HSV颜色空间模型和目标重构方法得到消除阴影后的前景图像.其次，进行行人的特征提取，得到融合行人位置特征和形状特征的运动模板.最后，采用Kalman滤波对行人的运动轨迹进行预测，将检测到的目标与预测结果匹配，得到行人的跟踪匹配矩阵,根据匹配矩阵判断合并和分离的发生.试验结果表明，该方法不仅可以准确跟踪多目标，而且可以有效解决遮挡问题，具有很好的适应性和鲁棒性.

关键词: 智能交通系统, 行人跟踪, 混合高斯模型, Kalman滤波

Abstract: Pedestrian tracking is an important part of Intelligent Transportation Systems (ITS) application. A new robust system for pedestrian tracking based on computer vision is proposed in this paper. First, improved Gaussian mixture model is used to detect pedestrian. To get better segmentation result, morphological reconstruction is utilized to remove shadows. Then, pedestrian tracking is achieved by feature fusion and prediction methodology. The trajectories are incorporated by the Kalman filter to determine the search windows, which are used to establish the matching matrix at two successive frames by comparing with detected pedestrians. Finally, an object association strategy is incorporated to deal with object tracking in case of merging and splitting by the template integrated spatial position and shape information. The tracking method is tested under real scenarios. Elaborate experiment results show good robustness and high efficiency of this method.

Key words: intelligent transportation systems (ITS), pedestrian tracking, Gaussian mixture model, Kalman filter

中图分类号:

U491

李娟,邵春福,杨励雅,李琦. 基于Kalman滤波的行人跟踪方法研究[J]. 交通运输系统工程与信息, 2009, 9(6): 148-153 .

LI Juan, SHAO Chun-fu, YANG Li-ya, LI Qi. [J]. Journal of Transportation Systems Engineering and Information Technology, 2009, 9(6): 148-153 .

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract17907.shtml

http://www.tseit.org.cn/CN/Y2009/V9/I6/148

参考文献

［1］G H Zhang, R P Avery, Y H Wang. A video-based vehicle detection and classification system for real-time traffic data collection using uncalibrated video cameras［J］. Transportation Research Record, No. 1993, 2007: 138-147. ［2］H Cheng, N N Zheng, X T Zhang, J J Qin, H van de Wetering. interactive road situation analysis for driver assistance and safety warning systems: framework and algorithms［J］. IEEE Transactions on Intelligent Transportation Systems, 2007, 8(1): 157-167. ［3］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 C F, ZHAO Y, WU G. Review of road traffic data collection technology［J］. Modern Transportation Technology, 2006, 6: 66-70. ］ ［4］C F Shao, Y Zhao, H Yue, X Zhang. Study on a vision based system for real-time collection of mixed traffic data［C］. Proceedings of ICTTS’ 2006: 606-614. ［5］邵春福, 李娟, 赵熠, 等. 行人交通的视频检测方法综述［J］. 交通运输系统与信息, 2008, 8(4): 23-29. ［SHAO C F, LI J, ZHAO Y, et al. A survey 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.］ ［6］岳昊, 邵春福, 赵熠, 等. 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 H, SHAO C F, ZHAO Y, et al. A study on moving pedestrian tracking based on video sequences［J］. Journal of Transportation Systems Engineering and Information Technology, 2007, 7(4): 47-51.］ ［7］B Liu, O Jesorsky, R Kompe. Robust real-time multiple object tracking in traffic scenes using an optical matrix range sensor［C］. IEEE International Conference on Intelligent Transportation Systems, 2007: 742-747. ［8］Jepson A D, Fleet D J, El-Maraghi T F. Robust online appearance models for visual tracking［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(10): 1296-1311. ［9］Paragios N, Deriche R. Geodesic active contours and level sets for the detection and tracking of moving objects［C］. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2000, 22(3): 266-280. ［10］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. ［11］Rohr K. Towards model-based recognition of human movements in sequences［C］. Computer Vision, Graphics and Image Processing, 1994: 94-115. ［12］Stauffer C, Grimson W E L. Learning patterns of activity using real-time tracking［C］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000: 747-757. ［13］王勇, 谭毅华, 田金文. 基于阴影消除和混合高斯模型的视频分割算法［J］. 光电工程, 2008, 35(3): 21-25. ［WANG Y, TAN Y H, TIAN J W. Videio segmentation algorithm with Gaussian Mixture Model and shadow removal［J］. Opto-Electronic Enginerring, 2008, 35(3): 21-25.］ ［14］Cucchiara R, Grana C, Piccardi M, Prati A, Sirotti S. Improving shadow suppression in moving object detection with hsv color information［C］. IEEE International Conference on Intelligent Transportation Systems, 2001: 334-339. ［15］Gonzalez R C, Woods R E. Digital Image Processing［M］. 2nd ed. Prentice-Hall, Inc., 2002. ［16］Meuter M, Iurgel U, Park S, Kummert A. The unscented kalman filter for pedestrian tracking from a moving host［C］. IEEE Intelligent Vehicles Symposium, 2008: 37-42.

[1]	陆化普，孙智源，屈闻聪. 大数据及其在城市智能交通系统中的应用综述[J]. 交通运输系统工程与信息, 2015, 15(5): 45-52.
[2]	张荣辉，李福樑，周喜，蒋同海，游峰，徐建闽，杨三强. 一种基于激光与视频信息时空数据融合的行人检测方法[J]. 交通运输系统工程与信息, 2015, 15(3): 49-55.
[3]	YOUSEFI Saleh,ABBASI Tofigh, ANVARI Zahra. 基于车载通信实时交通信息的城市道路路径选择方法[J]. 交通运输系统工程与信息, 2014, 14(5): 23-36.
[4]	翁剑成，荣建，王梦佳，刘力力. ETC 系统的环境效益评价测算模型[J]. 交通运输系统工程与信息, 2014, 14(5): 55-60.
[5]	张国伍. 动态交通仿真理论应用与发展——“交通7+1论坛”第三十四次会议纪实[J]. 交通运输系统工程与信息, 2014, 14(2): 1-6.
[6]	李强, 葛乾, 缪立新, 戚铭尧. 基于探测车数据的路段交通特性研究[J]. 交通运输系统工程与信息, 2012, 12(2): 41-46.
[7]	高万宝, 吴坚, 邹娇. 基于实时密度的入口匝道控制算法研究[J]. 交通运输系统工程与信息, 2012, 12(2): 150-155.
[8]	郭敏, 彭德品, 吴建平, 王天骄. 中英典型交叉口通行能力对比分析及应用[J]. 交通运输系统工程与信息, 2011, 11(6): 193-199.
[9]	宁滨,王飞跃,董海荣,李润梅,文丁,李莉. 基于ACP方法的城市轨道交通平行系统体系研究[J]. 交通运输系统工程与信息, 2010, 10(6): 22-28 .
[10]	马文佳,曲仕茹. 基于非下采样Contourlet变换的交通图像融合方法研究[J]. 交通运输系统工程与信息, 2010, 10(6): 48-52 .
[11]	邓小勇,扈中伟,张彭,郭继孚. 基于车流特征分区算法的地磁传感器单节点车速估计[J]. 交通运输系统工程与信息, 2010, 10(5): 35-39 .
[12]	林森, 刘静, 关积珍, 侯晓宇, 孙建平, 刘雪杰. 基于相关性分析的浮动车速度建库方法研究[J]. 交通运输系统工程与信息, 2010, 10(5): 40-44 .
[13]	熊娟,刘静,关积珍,孙建平,刘雪杰,温慧敏. 北京市快速路浮动车最小样本量研究[J]. 交通运输系统工程与信息, 2010, 10(4): 38-43 .
[14]	姚智胜,熊志华,邵春福. 交通流短时预测的相关性研究[J]. 交通运输系统工程与信息, 2010, 10(2): 117-121 .
[15]	邓中伟,季民河,陈雯,施宝宏,徐超,张治华,张波,邬毅敏. 耦合被动式GPS与网络调查的居民出行调查[J]. 交通运输系统工程与信息, 2010, 10(2): 178-183 .