A Robust On-Road Vehicle Detection and Tracking Method Based on Monocular Vision

  • Ling Xiao
  • Yongjun ZhangEmail author
  • Jun Liu
  • Yong Zhao
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 834)


In this paper, we propose a new framework for vehicle detection and tracking. Multi-features are used in the vehicle detection algorithm, which can be divided into two main steps: generation of candidates using features such as the shadow and vertical edge, and verification of the candidates using HOG and SVM. In the vehicle tracking algorithm, the RGB model and orientation histogram are used to represent the object feature, and the mean shift is employed to search the mode of the potential object rapidly in a neighborhood frame, which obtains the preliminary tracking results. Then, we use ORB feature matching and correction methods to adjust the preliminary tracking results. The improved Mean-Shift tracking results and the ORB correction results are then fused by linear weighted, which obtains the final results of the tracking. Experimental results demonstrate that the proposed approach is robust and validate in complicated real scenes.


Vehicle detection Vehicle tracking Vertical edge Mean shift ORB 



This work was supported by the Joint Fund of Department of Science and Technology of Guizhou Province and Guizhou University under grant: LH [2014]7635, Research Foundation for Advanced Talents of Guizhou University under grant: (2016) No. 49, Key Supported Disciplines of Guizhou Province—Computer Application Technology (No. QianXueWeiHeZi ZDXX[2016]20), Specialized Fund for Science and Technology Platform and Talent Team Project of Guizhou Province(No. QianKeHePingTaiRenCai [2016]5609), and the work was also supported by National Natural Science Foundation of China (61462013, 61661010).


  1. 1.
    Chen, Z., Wang, C., Luo, H., et al.: Vehicle detection in high-resolution aerial images based on fast sparse representation classification and multiorder feature. IEEE Trans. Intell. Transp. Syst. 17(8), 2296–2309 (2016)CrossRefGoogle Scholar
  2. 2.
    Hsieh, C.H., Hung, M.H., Weng, S.K.: Visual object tracking based on color and implicit shape features. J. Inf. Hiding Multimed. Signal Process. 9(1), 198–210 (2018)Google Scholar
  3. 3.
    Zhao, D.N., Guo, D.J., Lu, Z.M., Luo, H.: Tracking multiple moving objects in video based on multi-channel adaptive mixture background model. J. Inf. Hiding Multimed. Signal Process. 8(5), 987–995 (2017)Google Scholar
  4. 4.
    Bebis, G., Sun, Z., Miller, R.: On-road vehicle detection review. IEEE Trans. Pattern Anal. Mach. Intell. 694–711 (2006)Google Scholar
  5. 5.
    Han, S., Han, Y., Hahn, H.: Vehicle detection method using Haar-like feature on real time system. In: Proceedings of World Academy of Science, Engineering and Technology, pp. 455–459 (2009)Google Scholar
  6. 6.
    Chan, Y.M., Huang, S.S., Fu, L.C., Hsiao, P.Y., Lo, M.F.: Vehicle detection and tracking under various lighting conditions using a particle filter. IET Intel. Transp. Syst. 6(1), 1–8 (2012)CrossRefGoogle Scholar
  7. 7.
    Lin, B., Lin, Y., Fu, L., et al.: Integrating appearance and edge features for sedan vehicle detection in the blind-spot area. IEEE Trans. Intell. Transp. Syst. 13(2), 737–747 (2012)CrossRefGoogle Scholar
  8. 8.
    Vojir, T., Noskova, J., Matas, J.: Robust scale-adaptive mean-shift for tracking. Pattern Recogn. Lett. 49(3), 250–258 (2014)CrossRefGoogle Scholar
  9. 9.
    Chen, L., Bian, M., Luo, Y., et al.: Real-time identification of the tyre–road friction coefficient using an unscented Kalman filter and mean-square-error-weighted fusion. Proc. Inst. Mech. Eng. Part D J. Automob. Eng. 230(6) (2016)Google Scholar
  10. 10.
    Dong, F., Liu, Z., Kong, D., et al.: Adapting the sample size in particle filters through KLD-sampling. Int. J. Robot. Res. 22(12), 985–1003 (2016)Google Scholar
  11. 11.
    Liu, T., Zheng, N., Zhao, L., Cheng, H.: Learning based symmetric features selection for vehicle detection. IEEE Intelligent Vehicles Symposium, Las Vegas, Nevada, USA, pp. 124–129 (2005)Google Scholar
  12. 12.
    Ramesh, V., Comaniciu, D., Meer, P.: Kernel-based object tracking. IEEE Trans. Pattern Anal. Mach. Intell. 564–577 (2003)Google Scholar
  13. 13.
    O’malley, R., Glavin, M., Jones, E.: Vision-based detection and tracking of vehicles to the rear with perspective correction in low-light conditions. IET Intell. Trans. Syst. Scholar
  14. 14.
    Takeuchi, A., Mita, S., McAllester, D.: On-road vehicle tracking using deformable object model and particle filter with integrated likelyhoods. In: Intelligent Vehicles Symposium, pp. 1014–1021. IEEE, Piscataway (2010)Google Scholar
  15. 15.
    Huan, S., Shun-ming, L., Jian-guo, M., et al.: A robust vehicle tracking approach using mean shift procedure. In: 5th International Conference on Information Assurance and Security, pp. 741–744. IEEE, Piscataway (2009)Google Scholar
  16. 16.
    Zhou, H., Yuan, Y., Shi, C.: Object tracking using SIFT features and mean shift. Comput. Vis. Image Underst. 113(3), 345–352 (2009)CrossRefGoogle Scholar
  17. 17.
  18. 18.
    Rublee, E., Rabaud, V., Konolige, K., et al.: ORB: an efficient alternative to SIFT or SURF. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 2564–2571. IEEE (2011)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou ProvinceCollege of Computer Science and Technology, Guizhou UniversityGuiyangChina
  2. 2.School of Electronic and Computer EngineeringShenzhen Graduate School of Peking UniversityShenzhenChina

Personalised recommendations