Multiple Objects Tracking Based Vehicle Speed Analysis with Gaussian Filter from Drone Video

  • Yue Liu
  • Zhichao LianEmail author
  • Junjie Ding
  • Tangyi Guo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11935)


Vehicle speed analysis based on the video is a challenging task in the field of traffic safety, which has high requirements for accuracy and computational burden. The drone’s video is taken from a top-down perspective, providing more complete view comparing to the common surveillance cameras in poles. In this paper, we introduce a Gaussian Filter to deal with the estimated speed data which are extracted by a multiple objects tracking method composed of You Only Look Once (YOLOv3) and Kalman Filter. We exploit the capability of Gaussian Filter to suppress data noise appearing in the process of tracking vehicles from drone videos, and thus use the filter to solve the case where the estimated vehicle speed is fluctuated along the ongoing direction. On the other hand, we built a vehicle dataset from the drone’s videos we mentioned above which additionally contains vehicle’s real speed information. Experimental results showed that our method is effective to improve the accuracy of vehicle speed estimated by our tracking module. It can improve Mean Squared error (MSE) accuracy 80.5% on experimental data.


Gaussian Filter Data analysis Multiple object tracking Traffic safety 


  1. 1.
    Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement (2018)Google Scholar
  2. 2.
    Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: IEEE Conference on Computer Vision & Pattern Recognition (2017)Google Scholar
  3. 3.
    Kalman, R.E.: A new approach to linear filtering and prediction problems. J. Basic Eng. Trans. 82, 35–45 (1960)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Wu, Y., Lim, J., Yang, M.H.: Online object tracking: a benchmark. In: Computer Vision & Pattern Recognition (2013)Google Scholar
  5. 5.
    Ito, K.: Gaussian filter for nonlinear filtering problems. In: IEEE Conference on Decision & Control (2002)Google Scholar
  6. 6.
    Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015)
  7. 7.
    Perret-Gentil, C.: Gaussian distribution of short sums of trace functions over finite fields. Math. Proc. Camb. Philos. Soc. 163(3), 38 (2017)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Eaves, J.L., Reedy, E.K.: Principles of Modern Radar. SciTech Publishing, Chennai (2013)Google Scholar
  9. 9.
    Yun, D.S., et al.: The system integration of unmanned vehicle and driving simulator with sensor fusion system. In: International Conference on Multisensor Fusion & Integration for Intelligent Systems (2002)Google Scholar
  10. 10.
    Im, D.Y., et al.: Development of magnetic position sensor for unmanned driving of robotic vehicle. In: Sensors (2009)Google Scholar
  11. 11.
    Zhang, X., Gao, H., Mu, G., et al.: A study on key technologies of unmanned driving. CAAI Trans. Intell. Technol. 1(1), 4–13 (2016)CrossRefGoogle Scholar
  12. 12.
    Setchell, C., Dagless, E.L.: Vision-based road-traffic monitoring sensor. IEE Proc. – Vis. Image Signal Process. 148(1), 78–84 (2002)CrossRefGoogle Scholar
  13. 13.
    Li, C., Dai, B., Wang, R., et al.: Multi-lane detection based on omnidirectional camera using anisotropic steerable filters. IET Intell. Transp. Syst. 10(5), 298–307 (2016)CrossRefGoogle Scholar
  14. 14.
    Zhe, Y., et al.: Filter design for linear frequency modulation signal based on fractional Fourier transform. In: IEEE International Conference on Signal Processing (2010)Google Scholar
  15. 15.
    Soo, J.S., Pang, K.K.: Multidelay block frequency domain adaptive filter. IEEE Trans. Acoust. Speech Signal Process. 38(2), 373–376 (1990)CrossRefGoogle Scholar
  16. 16.
    Alt, N., Claus, C., Stechele, W.: Hardware/software architecture of an algorithm for vision-based real-time vehicle detection in dark environments. In: Design, Automation & Test in Europe (2008)Google Scholar
  17. 17.
    Zhao, Z., Ping, F., Guo, J., et al.: A hybrid tracking framework based on kernel correlation filtering and particle filtering. Neurocomputing 297, 40–49 (2018)CrossRefGoogle Scholar
  18. 18.
    Wei, C., Zhang, K., Liu, Q.: Robust visual tracking via patch based kernel correlation filters with adaptive multiple feature ensemble. Neurocomputing 214, 607–617 (2016)CrossRefGoogle Scholar
  19. 19.
    Strait, J.C., Jenkins, W.: Filter architectures and adaptive algorithms for 2-D adaptive digital signal processing. In: International Conference on Acoustics (1989)Google Scholar
  20. 20.
    Reid, D.B., Bryson, R.G.: A non-Gaussian filter for tracking targets moving over terrain. In: Asilomar Conference on Circuits (1979)Google Scholar
  21. 21.
    Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S.E.: SSD: single shot multibox detector. CoRR, abs/1512.02325 (2015)Google Scholar
  22. 22.
    Szegedy, C., et al.: Going deeper with convolutions. CoRR, abs/1409.4842 (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Yue Liu
    • 1
  • Zhichao Lian
    • 1
    Email author
  • Junjie Ding
    • 1
  • Tangyi Guo
    • 1
  1. 1.Nanjing University of Science and TechnologyNanjingChina

Personalised recommendations