基于HMM的车辆行驶状态实时判别方法研究

王相海; 丛志环; 方玲玲; 秦钜鳌

doi:10.3724/SP.J.1004.2013.02131

基于HMM的车辆行驶状态实时判别方法研究

doi: 10.3724/SP.J.1004.2013.02131

1.
辽宁师范大学计算机与信息技术学院大连 116029;
2.
苏州大学江苏省计算机信息处理技术重点实验室苏州 215006

基金项目:

国家自然科学基金（41271422），高等学校博士学科点专项科研基金（20132136110002），辽宁省自然科学基金（20102123），计算机软件新技术国家重点实验室开放基金（KFKT2011B09，KFKT2011B11），南京邮电大学图像处理与图像通信江苏省重点实验室开放基金（LBEK2010003），智能计算与信息处理教育部重点实验室（湘潭大学）开放课题（2011ICIP06）资助

详细信息

作者简介:
王相海博士，教授. 主要研究方向为多媒体信息处理和计算机图形学. 本文通信作者. E-mail：xhwang@lnnu.edu.cn

计量
- 文章访问数: 1584
- HTML全文浏览量: 102
- PDF下载量: 1576
- 被引次数: 0
出版历程
- 收稿日期: 2011-06-22
- 修回日期: 2013-06-21
- 刊出日期: 2013-12-20

Determination of Real-time Vehicle Driving Status Using HMM

1.
College of Computer and Information Technology, Liaoning Normal University, Dalian 116029;
2.
Computer Information Processing Technology Key Laboratory in Jiangsu Province, Soochow University, Suzhou 215006

Funds:

Supported by National Natural Science Foundation of China (41271422), Specialized Research Fund for the Doctoral Program of Higher Education (20132136110002), Natural Science Foundation of Liaoning Province (20102123), Open Foundation of Novel Software Technology of State Key Laboratory (Nanjing University) (KFKT2011B09, KFKT2011B11), Open Foundation of Image Processing and Image Communication Laboratory (Nanjing University of Posts and Telecommunications) of Jiangsu Province (LBEK2010003), and Intelligent Computing and Information Processing, Open Topics of Education Ministry (Xiangtan University) (2011ICIP06)

摘要

摘要: 对交通视频车辆轨迹时序特征下的车辆行驶状态进行研究，提出了一种基于隐马尔科夫模型（Hidden Markov model，HMM）的车辆行驶状态实时判别方法.首先对轨迹序列进行了基于轨迹长度的去不完整轨迹序列、对车辆轨迹点序列的线性平滑滤波和最小二乘线性拟合的预处理操作，保证了所获得轨迹序列的有效性；其次，提出一种基于车辆运行轨迹点序列方向角的车辆轨迹特征值表示方法和基于方向角区间划分的HMM观察值序列生成方法，该方法以方向角的区间变化来区分不同轨迹模式的特征；最后，采用多观察值序列下的Baum-Welch 算法训练得到相关交通场景轨迹模式类的最优HMM 参数，并通过实时获取车辆行驶轨迹段与相应模型的匹配，实现对车辆行驶状态的实时判别. 仿真实验验证了本文方法的有效性和稳定性.
- 视频车辆轨迹 /
- 隐马尔科夫模型 /
- 方向角 /
- 行驶状态 /
- 实时判别
Abstract: In this paper, we propose a method for determination of vehicle driving status from its time-ordered trajectory data using the hidden Markov model (HMM). Firstly, we take some preprocessing including linear smooth filtering and least square fitting to abandon the trajectory sequences whose lengths are not enough, so as to guarantee the usability of acquired trajectory sequences. Secondly, we extract trajectory direction angle features from the trajectory sequences, and on this basis we propose a direction angle region partition algorithm to generate the observation sequences, which will determine the different trajectory patterns acquired by vehicle real-time various driving status. Finally, we get the optimal HMM model parameters of each trajectory pattern in specific traffic scene by multiple observations based Baum-Welch algorithm, then through matching with the above trained HMM models, we can determine the real-time vehicle driving status. Experiment results demonstrate the effectiveness and stability of this method.
- Video vehicle trajectories /
- hidden Markov models (HMM) /
- direction angles /
- driving status /
- realtime determination

HTML全文

参考文献(18)

[1]	Cuntoor N P, Yegnanarayana B, Chellappa R. Activity modeling using event probability sequences. IEEE Transactions on Image Processing, 2008, 17(4): 594-607
[2]	Feng B L, Gao J, Lin S X, Zhang Y D, Tao K. Motion region-based trajectory analysis and re-ranking for video retrieval. In: Proceedings of the 2009 IEEE International Conference on Multimedia and Expo. New York, NY: IEEE, 2009. 378-381
[3]	Wang Xiang-Hai, Fang Ling-Ling, Cong Zhi-Huan. Research on real-time multi-target tracking algorithm based on MSPF. Acta Automatica Sinica, 2012, 38(1): 139-144(王相海, 方玲玲, 丛志环. 基于MSPF的实时监控多目标跟踪算法研究. 自动化学报, 2012, 38(1): 139-144)
[4]	Wang Kun-Feng, Li Zhen-Jiang, Tang Shu-Ming. Visual traffic data collection approach based on multi-features fusion. Acta Automatica Sinica, 2011, 37(3): 322-330(王坤峰, 李镇江, 汤淑明. 基于多特征融合的视频交通数据采集方法. 自动化学报, 2011, 37(3): 322-330)
[5]	Wu Cong, Li Bo, Dong Rong, Chen Qi-Mei. Detecting traffic parameters based on vehicle clustering from video. Acta Automatica Sinica, 2011, 37(5): 569-576(吴聪, 李勃, 董蓉, 陈启美. 基于车型聚类的交通流参数视频检测. 自动化学报, 2011, 37(5): 569-576)
[6]	Morris B T, Trovedi M M. A survey of vision-based trajectory learning and analysis for surveillance. IEEE Transactions on Circuits and Systems for Video Technology, 2008, 18(8): 1114-1127
[7]	Buccolieri F, Distante C, Leone A. Human posture recognition using active contours and radial basis function neural network. In: Proceedings of the 2005 IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS. Como: IEEE, 2005. 213-218
[8]	Dilruba R A, Chowdhury N, Liza F F, Karmakar C K. Data pattern recognition using neural network with back-propagation training. In: Proceedings of the 2006 IEEE International Conference on Electrical and Computer Engineering, ICECE. Dhaka: IEEE, 2006. 451-455
[9]	Meyer D D, Sturm J, Burgard W. Regression-based online situation recognition for vehicular traffic scenarios. In: Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. PiSCAtaway, NJ, USA: IEEE Press, 2009. 1711-1716
[10]	Jiu Y H, Sheng H, Chao L, Zhang X. Vehicle behavior understanding based on movement string. In: Proceedings of the 12th International IEEE Conference on Intelligent Transportation Systems, ITSC. St. Louis, MO: IEEE, 2009: 1-6
[11]	Rabiner L R. A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 1989, 77(2): 257-286
[12]	Mitchell T M[Author], Zeng Hua-Jun, Zhang Yin-Kui et al.[Translator]. Machine Learning. Beijing: Mechanical Industry Press, 2008(米歇尔[著], 曾华军, 张银奎等[译]. 机器学习. 北京: 机械工业出版社, 2008)
[13]	Duda R O et al.[Author], Li Hong-Dong et al.[Translator]. Pattern Classification (2nd edition). Beijing: Mechanical Industry Press, 2003(迪达等[著], 李宏东等[译]. 模式分类 (第2版). 北京: 机械工业出版社, 2003)
[14]	Li X L, Parizeau M, Plamondon R. Training hidden Markov models with multiple observations ——a combinatorial method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(4): 371-377
[15]	Jia Bin, Zhu Xiao-Yan, Luo Yu-Pin, Hu Dong-Cheng. Accurate Baum-Welch algorithm free from overflow. Journal of Software, 2000, 11(5): 707-710(贾宾, 朱小燕, 罗予频, 胡东成. 消除溢出问题的精确Baum-Welch算法. 软件学报, 2000, 11(5): 707-710)
[16]	Chenshomi S, Rahati Q S, Akbarzadeh T. HMM training by a hybrid of chaos optimization and Baum-Welch algorithms for discrete speech recognition. In: Proceedings of the 6th International Conference on Digital Content, Multimedia Technology and Its Applications, IDC. Seoul: IEEE, 2010. 337-341
[17]	Chen M, Madden M G, Liu Y. Refined learning of hidden Markov models with a modified Baum-Welch algorithm and informative components. In: Proceedings of the 2010 IEEE International Conference on Progress in Informatics and Computing, PIC. Shanghai, China: IEEE, 2010: 165-169
[18]	Wang Xiang-Hai, Fang Ling-Ling, Cong Zhi-Huan. Research on video vehicle tracking algorithm based on Kalman and particle filter. Journal of Image and Graphics, 2010, 15(11): 1616-1622(王相海, 方玲玲, 丛志环. 卡尔曼粒子滤波的视频车辆跟踪算法研究. 中国图象图形学报, 2010, 15(11): 1616-1622)