Small Object Tracking in High Density Crowd Scenes

  • Yujie LiEmail author
  • Shinya Takahashi
Part of the Studies in Computational Intelligence book series (SCI, volume 810)


In recent years, computer vision for automatically identification and tracking of animals has evolved into a popular tool for quantifying behavior. Honeybees are a popular model for learning and memory, so tracking of honeybees within a colony is a particularly task due to dense populations, similar target appearance and a significant portion of the colony frequently leaving the hive. In this paper we present a detection method based on improved three-frame difference method and VIBE algorithm and one tracking method based on Kalman filtering for honeybees tracking. We evaluate the performance of the proposed methods on datasets which contains videos with crowd honeybee colony. The experimental results show that the proposed method performs good performance in detection and tracking.


Target detection Object tracking Kalman filter 



This work was supported by Research Fund of SKL of Ocean Engineering in Shanghai Jiaotong University (1315; 1510), Research Fund of SKL of Marine Geology in Tongji University (MGK1608).


  1. 1.
    Li, G., Zeng, R., Lin, L.: Moving target detection in video monitoring system. In: Proceeding of the 6th World Congress on Intelligent Control and Automation, pp. 9778–9781 (2006)Google Scholar
  2. 2.
    Elgammal, A., Duraiswami, R.: Background and foreground modelling using nonparametric kernel density estimation for visual surveillance. In: Proceedings of IEEE, pp. 1151–1163 (2002)Google Scholar
  3. 3.
    Ohta, N., Kanatani, K.: Moving object detection from optical flow without empirical thresholds. IEICE Trans. Inf. Syst. E81-D(2), 243–245 (1998)Google Scholar
  4. 4.
    Shi, J., Tomasi, C.: Good features to track. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (1994)Google Scholar
  5. 5.
    Lowe, D.: Object recognition from local scale-invariant features. In: Proceedings of the International Conference on Computer Vision ICCV, Corfu, pp. 1150–1157 (1999)Google Scholar
  6. 6.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of non-rigid objects using mean shift. In: Proceedings of CVPR, pp. 142–151 (2000)Google Scholar
  7. 7.
    Allen, J.G., Xu, R.Y.D.: Object tracking using Camshift algorithm and multiple quantized feature spaces. In: Proceedings of Pan-Sydney Area Workshop on Visual Information Processing VIP 2003, pp. 1–5 (2003)Google Scholar
  8. 8.
    Barnich, O., Van Droogenbroeck, M.: VIBE: a universal background subtraction algorithm for video sequences. IEEE Trans. Image Process. 20(6), 1709–1724 (2011)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Van Droogenbroeck, M., Paquot, O.: Background subtraction: experiments and improvements for VIBE. In: Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 32–37 (2012)Google Scholar
  10. 10.
    Kalman, R.E.: A new approach to linear filtering nonlinear systems. J. Basic Eng. 35–45 (1960)Google Scholar
  11. 11.
    Welch, G., Bishop, G.: An introduction to the Kalman filter. In: Proceedings of SIGGRAPH, pp. 19–24 (2001)Google Scholar
  12. 12.
    Poiesi, F., Cavallaro, A.: Tracking multiple high-density homogeneous targets. IEEE Trans. Circuits Syst. Video Technol. 25(4), 623–637 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Electronics Engineering and Computer ScienceFukuoka UniversityFukuokaJapan

Personalised recommendations