Skip to main content

Advertisement

SpringerLink
Log in

Particle filtering strategies for data fusion dedicated to visual tracking from a mobile robot

  • Original Paper
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

This paper introduces data fusion strategies within particle filtering in order to track people from a single camera mounted on a mobile robot in a human environment. Various visual cues are described, relying on color, shape or motion, together with several filtering strategies taking into account all or parts of these measurements in their importance and/or measurement functions. A preliminary evaluation enables the selection of the most meaningful visual cues associations in terms of discriminative power, robustness to artifacts and time consumption. The depicted filtering strategies are then evaluated in order to check which people trackers regarding visual cues and algorithms associations best fulfill the requirements of the considered scenarios. The performances are compared through some quantitative and qualitative evaluations. Some associations of filtering strategies and visual cues show a significant increase in the tracking robustness and precision. Future works are finally discussed.

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

Similar content being viewed by others

References

  1. Alami R., Chatila R., Fleury S., Ingrand F.: An architecture for autonomy. Int. J. Robot. Res. 17(4), 315–337 (1998)

    Article  Google Scholar 

  2. Andrieu, C., Davy, M., Doucet, A.: Improved auxiliary particle filtering: Application to timevarying spectral analysis. In: IEEE Wk. on Statistical Signal Processing, pp. 309–312. Singapore (2001)

  3. Arulampalam S., Maskell S., Gordon N., Clapp T.: A tutorial on particle filters for on-line non-linear/non-gaussian bayesian tracking. IEEE Trans. Signal Process. 50(2), 174–188 (2002)

    Article  Google Scholar 

  4. Avidan, S.: Support vector tracking. In: IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR’01), pp. 184–191. Kauai, HI (2001)

  5. Bailly, G., Brèthes, L., Chatila, R., Clodic, A., Crowley, J., Danès, P., Elisei, F., Fleury, S., Herrb, M., Lerasle, F., Menezes, P., Alami, R.: HR+ : towards an interactive autonomous robot. In: Journées ROBEA, pp. 39–45. Montpellier, France (2005)

  6. Bichot E., Mascarilla L., Courtellemont P.: Particle filtering based on motion and color information. IEEE Trans. Information Sci. Appl. 2, 220–227 (2005)

    Google Scholar 

  7. Brèthes, L., Menezes, P., Lerasle, F., Briot, M.: Face tracking and hand gesture recognition for human-robot interaction. In: IEEE Int. Conf. on Robotics and Automation (ICRA’04), pp. 1901–1906. New Orleans, LA (2004)

  8. Bretzner, L., Laptev, I., Lindeberg, T.: Hand gesture using multi-scale colour features, hierarchical models and particle filtering. In: IEEE Int. Conf. on Automatic Face and Gesture Recognition (FGR’02), pp. 405–410. Washington D.C. (2002)

  9. Brèthes, L.: Suivi visuel par filtrage particulaire. Application à l’interaction homme-robot. Ph.D. thesis, Université Paul Sabatier, LAAS-CNRS, Toulouse (2006)

  10. Bullock D., Zelek J.: Real-time tracking for visual interface applications in cluttered and occluding situations. J. Vis. Image Comput. 22, 1083–1091 (2004)

    Article  Google Scholar 

  11. Chen, H., Liu, T.: Trust-region methods for real-time tracking. In: IEEE Int. Conf. on Computer Vision (ICCV’01), vol. 2, pp. 717–722. Vancouver, Canada (2001)

  12. Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. In: IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 25, pp. 564–575 (2003)

  13. Doucet A., De Freitas N., Gordon N.J.: Sequential Monte Carlo Methods in Practice. Series Statistics For Engineering and Information Science. Springer, New York (2001)

    Google Scholar 

  14. Doucet A., Godsill S.J., Andrieu C.: On sequential monte carlo sampling methods for bayesian filtering. Stat. Comput. 10(3), 197–208 (2000)

    Article  Google Scholar 

  15. Gavrila D.M.: The visual analysis of human movement : a survey. Comput. Vis. Image Underst. 1, 82–98 (1999)

    Article  Google Scholar 

  16. Germa, T., Brèthes, L., Lerasle, F., Simon, T.: Data fusion and eigenface based tracking dedicated to a tour-guide robot. In: Int. Conf. on Vision Systems (ICVS’07). Bielefeld, Germany (2007)

  17. Giebel, J., Gavrila, D.M., Schnorr, C.: A bayesian framework for multi-cue 3D object. In: Eur. Conf. on Computer Vision (ECCV’04). Prague, Czech Republic (2004)

  18. Haritaoglu I., Harwood D., Davis L.: W4 : Real-time surveillance of people and their activities. IEEE Trans. Pattern Anal. Mach. Intell. 8(22), 809–830 (2000)

    Article  Google Scholar 

  19. Hu W., Tan T., Wang L., Maybank S.: A survey on visual surveillance of object motion and behaviors. IEEE Trans. Syst. Man Cybernet. 34(3), 334–352 (2004)

    Article  Google Scholar 

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

    Article  Google Scholar 

  21. Isard, M., Blake, A.: Icondensation: Unifying low-level and high-level tracking in a stochastic framework. In: Eur. Conf. On Computer Vision (ECCV’98), pp. 893–908. London, UK (1998)

  22. Isard, M.A., Blake, A.: A mixed-state condensation tracker with automatic model-switching. In: IEEE Int. Conf. on Computer Vision (ICCV’98), pp. 107–112. Bombay, India (1998)

  23. Jones, M., Rehg, J.: Color detection. Tech. rep., Compaq Cambridge Research Lab (1998)

  24. Julier, S., Uhlmann, J.: A general method for approximating nonlinear transformations of probability distributions. Tech. rep., RRG, Dept. of Engineering Science, University of Oxford (1994)

  25. Kitagawa G.: Monte carlo filter and smoother for non-gaussian nonlinear state space models. J. Comput. Graph. Stat. 5(1), 1–25 (1996)

    Article  MathSciNet  Google Scholar 

  26. Li, P., Zhang, T.: Visual contour based on sequential importance sampling/resampling algorithm. In: IEEE Int. Conf. on Pattern Recognition (ICPR’02), pp. 564–568. Quebec, Canada (2002)

  27. MacCormick J., Blake A.: A probabilistic exclusion principle for tracking multiple objects. Int. J. Comput. Vis. 39(1), 57–71 (2000)

    Article  MATH  Google Scholar 

  28. MacCormick, J., Isard, M.: Partitioned sampling, articulated objects, and interface-quality hand tracking. In: Eur. Conf. on Computer Vision (ECCV’00), pp. 3–19. Springer, London, UK (2000)

  29. Moeslund T., Granum E.: A survey on computer vision-based human motion capture. Comput. Vis. Image Underst. 81, 231–268 (2001)

    Article  MATH  Google Scholar 

  30. Nummiaro K., Koller-Meier E., Gool L.V.: An adaptative color-based particle filter. J. Image Vis. Comput. 21, 90–110 (2003)

    Google Scholar 

  31. Pitt M., Shephard N.: Filtering via simulation: auxiliary particle filters. J. Am. Stat. Assoc. 94(446), 590–599 (1999)

    Article  MathSciNet  MATH  Google Scholar 

  32. Pérez, P., Hue, C., Vermaak, J., Gangnet, M.: Color-based probabilistic tracking. In: Eur. Conf. on Computer Vision (ECCV’02), pp. 661–675. Berlin, Germany (2002)

  33. Pérez P., Vermaak J., Blake A.: Data fusion for visual tracking with particles. Proc. IEEE 92(3), 495–513 (2004)

    Article  Google Scholar 

  34. Rui, Y., Chen, Y.: Better proposal distributions: Object tracking using unscented particle filter. In: IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR’01), pp. 786–793. Kauai, HI (2001)

  35. Schwerdt, K., Crowley, J.L.: Robust face tracking using color. In: Int. Conf. on Face and Gesture Recognition (FGR’00), pp. 90–95. Grenoble, France (2000)

  36. Thayananthan, A., Stenger, B., Torr, P., Cipolla, R.: Learning a kinematic prior for tree-based filtering. In: British Machine Vision Conf. (BMVC’03), vol. 2, pp. 589–598. Norwich, UK (2003)

  37. Torma, P., Szepesvári, C.: Sequential importance sampling for visual tracking reconsidered. In: AI and Statistics, pp. 198–205 (2003)

  38. Turk, M.A., Pentland, A.P.: Face recognition using eigenfaces. In: IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR’91), pp. 586–591. Maui, HI (1991)

  39. Van Der Merwe, R., De Freitas, N., Doucet, A., Wan, E.: The unscented particle filter. In: Advances in Neural Information Processing Systems, vol. 13 (2001)

  40. Vermaak J., Andrieu C., Doucet A., Godsill S.: Particle methods for bayesian modeling and enhancement of speech signals. IEEE Trans. Speech Audio Process. 10(3), 173–185 (2002)

    Article  Google Scholar 

  41. Vermaak, J., Blake, A.: A nonlinear filtering for speaker tracking in noisy and reverberant environments. In: IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP’00). Istanbul, Turkey (2000)

  42. Vermaak, J., Doucet, A., Pérez, P.: Maintaining multi-modality through mixture tracking. In: IEEE Int. Conf. on Computer Vision (ICCV’03). Nice, France (2003)

  43. Vermaak, J., Pérez, P., Gangnet, M., Blake, A.: Towards improved observation models for visual tracking: Selective adaptation. In: Eur. Conf. on Computer Vision (ECCV’02), pp. 645–660. Berlin, Germany (2002)

  44. Vezhnevets, V., Sazonov, V., Andreeva, A.: A survey on pixel-based skin color detection techniques. In: Proc. Graphicon-2003 pp. 85–92 (2003)

  45. Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR’01). Kauai, HI (2001)

  46. Wachter S., Nagel H.: Tracking persons in monocular image sequences. Comput. Vis. Image Underst. 74(3), 174–192 (1999)

    Article  Google Scholar 

  47. Wu, Y., Huang, T.: A co-inference approach to robust visual tracking. In: IEEE Int. Conf. on Computer Vision (ICCV’01), vol. 2, pp. 26–33. Vancouver, Canada (2001)

Download references

Author information

Authors and Affiliations

  1. LAAS-CNRS, 7 avenue du Colonel Roche, 31077, Toulouse, France

    Ludovic Brèthes, Frédéric Lerasle, Patrick Danès & Mathias Fontmarty

  2. Univ. Paul Sabatier, 118 rte de Narbonne, 31062, Toulouse, France

    Frédéric Lerasle & Patrick Danès

Authors
  1. Ludovic Brèthes
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Frédéric Lerasle
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Patrick Danès
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mathias Fontmarty
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Frédéric Lerasle.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Brèthes, L., Lerasle, F., Danès, P. et al. Particle filtering strategies for data fusion dedicated to visual tracking from a mobile robot. Machine Vision and Applications 21, 427–448 (2010). https://doi.org/10.1007/s00138-008-0174-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00138-008-0174-7

Keywords

Search

Navigation