Multimedia Tools and Applications

, Volume 52, Issue 1, pp 133–145 | Cite as

Traffic incident classification at intersections based on image sequences by HMM/SVM classifiers

  • Yuexian Zou
  • Guangyi Shi
  • Hang Shi
  • He Zhao


With the development of modern intelligent transportation systems (ITS), automatic traffic incident detection with quick response and high accuracy becomes one of the most important issues, especially for metropolitan streets that are full of signaled intersections. In this paper, we present our up-to-date research outcomes of the traffic incident detection system, which makes use of the image sequences gathered from a typical urban intersection. Basic image signal processing was used to extract image difference information for traffic image database construction. Feature extraction algorithms were then discussed and compared including PCA, FFT, and hybrid analysis of DCT-FFT. Finally, multi-classification of traffic signal logics (East–West, West–East, South–North, North–South) and accidents were realized by HMM (Hidden Markov Model) and SVM (Support Vector Machine) respectively. Experimental results showed that the hybrid DCT-FFT method gives the best features, and classification performance of SVM is superior to HMM with limited training samples, where the correction rate is 100% for SVM and 91% for HMM.


ITS Traffic incident detection HMM SVM Intersection 



This project is partially supported by the Chinese National 863 Program (2007AA11Z224) and Shenzhen Science and Technology Program (SZKJ-200716)


  1. 1.
    Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, CambridgeGoogle Scholar
  2. 2.
    Dia H, Rose G (1996) Development and evaluation of neural network freeway incident detection models using field data. Transp Res C Emerg Technol 5:313–331CrossRefGoogle Scholar
  3. 3.
    Dougherty M (1995) A review of neural networks applied to transport. Transp Res C Emerg Technol 3:247–260CrossRefGoogle Scholar
  4. 4.
  5. 5.
    Ikeda H, Matsuo T, Kaneko Y, Tsuji K (1999) Abnormal incident detection system employing image processing technology. In Proc IEEE Int Conf Intell Transp Syst, Tokyo, Japan, Oct. 1999, pp. 748–752Google Scholar
  6. 6.
    Kamijo S, Matsushita Y, Ikeuchi K, Sakauchi M (2000) Traffic monitoring and accident detection at intersections. IEEE Trans Intell Transp Syst 1(2), June 2000Google Scholar
  7. 7.
    Ki Y-K, Lee D-Y (2007) A traffic accident recording and reporting model at intersections. IEEE Trans Intell Transp Syst 9(2), June 2007Google Scholar
  8. 8.
    Lee S-H, Choi J-W, Hong N-K. Development of incident detection model using neuro-fuzzy algorithm. Proceedings of the Fouth Annual ACIS, International Conference on Computer and Infromation Science (ICIS’05)Google Scholar
  9. 9.
    Lin C-P, Tai J-C, Song K-T (2003) Traffic monitoring based on real-time image tracking. Proceedings of the 2003 IEEE International Conference on Robotics and Automation, Taipei, Taiwan, September 14–19Google Scholar
  10. 10.
    Owens J, Hunter A (2000) Application of the self-organizing map to trajectory classification. in Proc. IEEE Workshop Visual Surveillance, Dublin, Ireland, pp. 77–83Google Scholar
  11. 11.
    The Ministry of Public Security of China:
  12. 12.
    Vapnik V (1995) The nature of statistical learning theory. Springer-Verlag, 1995Google Scholar
  13. 13.
    Veeraraghavan H, Masoud O, Papanikolopoulos NP (2003) Computer vision algorithms for intersection monitoring. IEEE Trans Intell Transp Syst 4(2):78–89CrossRefGoogle Scholar
  14. 14.
  15. 15.
    Zou Y, Shi G, Shi H, Wang Y (2009) Image sequences based traffic incident detection for signaled intersections using HMM. IEEE International Conference on Hybrid Intelligent Systems 2009, HIS 2009, August 12–14th 2009, Shenyang, ChinaGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  1. 1.Advanced Digital Signal Processing LabShenzhen Graduate School of Peking UniversityShenzhenPeople’s Republic of China

Personalised recommendations