Regression Based Trajectory Learning and Prediction for Human Motion

  • Alparslan Yildiz
  • Noriko Takemura
  • Yoshio Iwai
  • Kosuke Sato
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8334)


This paper presents a method for learning and predicting human motion in closed environments.

Many surveillance, security, entertainment and smart-home systems require the localization of human subjects and the prediction of their future locations in the environment. Traditional tracking methods employ a linear motion model for human motion. However, for complex scenarios, where motion trajectory is dependent on the structure of the environment, linear motion model is insufficient.

In this paper, we present a behavior-aware method for learning and predicting human motion in closed environments. Our method adaptively combines traditional linear motion model, where there is not much behavioral data, with the learned motion model, where there is sufficient data available.

We present the mathematical and implementation details along with the experimental results to show the effectiveness of our method.


human tracking surveillance trajectory learning 


  1. 1.
    Mittal, A., Larry, S.: M2tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene. Intl. J. Computer Vision (2002)Google Scholar
  2. 2.
    Khan, S.M., Shah, M.: Tracking Multiple Occluding People by Localizing on Multiple Scene Planes. IEEE Transactions on Pattern Analysis and Machine Intelligence (2008)Google Scholar
  3. 3.
    Yilmaz, A., Javed, O., Shah, M.: Object Tracking: A Survey. ACM J. Computing Surveys (2006)Google Scholar
  4. 4.
    Takemura, N., Miura, J.: View Planning of Multiple Active Cameras for Wide Area Surveillance. In: IEEE International Conference on Robotics and Automation (2007)Google Scholar
  5. 5.
    Hu, W., Hu, M., Zhou, X., Tan, T., Lou, J., Maybank, S.: Principal Axis-Based Correspondence between Multiple Cameras for People Tracking. IEEE Trans. Pattern Analysis and Machine Intelligence 29 (2006)Google Scholar
  6. 6.
    Zhao, T., Nevatia, R.: Tracking Multiple Humans in Crowded Environment. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (2004)Google Scholar
  7. 7.
    Bennewitz, M., Burgard, W., Cielniak, G., Thrun, S.: Learning Motion Patterns of People for Compliant Robot Motion. International Journal of Robotics Research 24 (2005)Google Scholar
  8. 8.
    Berclaz, J., Fleuret, F., Fua, P.: Robust People Tracking with Global Trajectory Optimization. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (2006)Google Scholar
  9. 9.
    Berclaz, J., Fleuret, F., Fua, P.: Multi-Camera Tracking and Atypical Motion Detection with Behavioral Maps. In: European Conference on Computer Vision (2008)Google Scholar
  10. 10.
    Haering, N., Venetianer, P.L., Lipton, A.: The evolution of video surveillance: an overview. Machine Vision and Applications (2008)Google Scholar
  11. 11.
    Xie, Y., Lin, L., Jia, Y.: Tracking Objects with Adaptive Feature Patches for PTZ Camera Visual Surveillance. In: International Conference on Pattern Recognition (2010)Google Scholar
  12. 12.
    Madrigal, F., Rivera, M., Hayet, J.-B.: Learning and Regularizing Motion Models for Enhancing Particle Filter-Based Target Tracking. In: Ho, Y.-S. (ed.) PSIVT 2011, Part II. LNCS, vol. 7088, pp. 287–298. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  13. 13.
    Yildiz, A., Akgul, Y.: A Fast Method for Tracking People with Multiple Cameras. In: Third Workshop on HUMAN MOTION Understanding, Modeling, Capture and Animation, Greece (2010)Google Scholar
  14. 14.

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Alparslan Yildiz
    • 1
  • Noriko Takemura
    • 1
  • Yoshio Iwai
    • 2
  • Kosuke Sato
    • 1
  1. 1.Osaka UniversityJapan
  2. 2.Tottori UniversityJapan

Personalised recommendations