Skip to main content
SpringerLink
Log in

Multimodal MSEPF for visual tracking

  • Original Article
  • Published:
Artificial Life and Robotics Aims and scope Submit manuscript

Abstract

Recently, particle filter has been applied to many visual tracking problems and it has been modified in order to reduce the computation time or memory usage. One of them is the Mean-Shift embedded particle filter (MSEPF, for short) and it is further modified as Randomized MSEPF. These methods can decrease the number of the particles without the loss of tracking accuracy. However, the accuracy may depend on the definition of the likelihood function (observation model) and of the prediction model. In this paper, the authors propose an extension of these models in order to increase the tracking accuracy. Furthermore, the expansion resetting method, which was proposed for mobile robot localization, and the changing the size of the window in Mean-Shift search are also selectively applied in order to treat the occlusion or rapid change of the movement.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Kitagawa G (1996) Monte–Carlo filter and smoother for non-Gaussian nonlinear state space models. J Comput Graphical Stat 5(1):1–25

    MathSciNet  Google Scholar 

  2. Gordon NJ, Salmond D, Smith AFM (1993) Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEEE Proc F 140(2):107–113

    Article  Google Scholar 

  3. Isard M, Blake A (1998) CONDENSATION: conditional density propagation for visual tracking. Int J Comput Vis 29(1):5–28

    Article  Google Scholar 

  4. Shan C, Wei Y, Tan T, Ojardias F (2004) Real time hand tracking by combining particle filter and mean shift. In: Proceedings of 6th IEEE international conference of automatic face and gesture recognition, pp 669–674

  5. Nakagama Y, Yokomichi M (2011) An improvement of MSEPF for visual tracking. Int J Artif Life Robot 15(4):534–538

    Article  Google Scholar 

  6. Boers Y, Driessen JN (2003) Interacting multiple model particle filter. IEEE Proc Radar Sonar Navig 150(5):344–349

    Article  Google Scholar 

  7. Wang J, Zhao D, Gao W, Shan S (2004) Interacting multiple model particle filter to adaptive visual tracking. In: Proceedings of international conference on image and graphics, pp 568–571

  8. Ueda R, Arai T, Sakamoto K, Kikuchi T, Kamiya S (2004) Expansion resetting for recovery from fatal error in Monte Carlo localization—comparison with sensor resetting methods. In: Proceedings of International Conference on Intelligent Robots and Systems (IROS) 2004, vol 3, pp 2481–2486

  9. Yang C et al (2005) Efficient Mean-Shift tracking via a new similarity measure. In: Proceedings of IEEE computer society conference on computer vision and pattern recognition (CVPR’05), vol 1, pp 176–183

Download references

Author information

Authors and Affiliations

  1. Faculty of Engineering, University of Miyazaki, 1-1, Gakuenkibanadainishi, Miyazaki, 889-2155, Japan

    Masahiro Yokomichi

  2. The Graduate School of Computer Science and Systems Engineering, University of Miyazaki, 1-1, Gakuenkibanadainishi, Miyazaki, 889-2155, Japan

    Yuki Nakagama

Authors
  1. Masahiro Yokomichi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuki Nakagama
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Masahiro Yokomichi.

About this article

Cite this article

Yokomichi, M., Nakagama, Y. Multimodal MSEPF for visual tracking. Artif Life Robotics 17, 257–262 (2012). https://doi.org/10.1007/s10015-012-0050-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10015-012-0050-4

Keywords

Search

Navigation