Skip to main content
SpringerLink
Log in

Tracking-by-detection of multiple persons by a resample-move particle filter

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

Abstract

Camera networks make an important component of modern complex perceptual systems with widespread applications spanning surveillance, human/machine interaction and healthcare. Smart cameras that can perform part of the perceptual data processing improve scalability in both processing power and network resources. Based on these insights, this paper presents a particle filter for multiple person tracking designed for an FPGA-based smart camera. We propose a new joint Markov Chain Monte Carlo-based particle filter (MCMC-PF) with short Markov chains, devoted to each individual particle, in order to sample the particle swarm in relevant regions of the high dimensional state-space with increased particle diversity. Finding an efficient sampling method has become another challenge when designing particle filters, especially for those devoted to more than two or three targets. A proposal distribution, combining diffusion dynamics, learned HOG + SVM person detections, and adaptive background mixture models, limits here the well-known burst in terms of particles and MCMC iterations. This informed proposal based on saliency maps has only been marginally used in the literature in a joint state space PF framework. The presented qualitative and quantitative results—for proprietary and public video datasets—clearly show that our tracker outperforms the well-known MCMC-PF in terms of (1) tracking performances, i.e. robustness and precision, and (2) parallelization capabilities as the MCMC-PF processes the particles sequentially.

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.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Notes

  1. for “Conditional Density Propagation”.

  2. i.e. a color distribution in the particle weighting stage.

  3. Even if only Gaussian mixtures are considered in this work.

  4. In fact two histograms to represent the appearance of the upper and lower human body.

  5. See the URL www.cvg.cs.rdg.ac.uk/slides/pets.html.

References

  1. Delta Technologies Society (DTSO), Toulouse. http://www.delta-technologies.fr

  2. Andriluka, M., Roth, S., Schiele, B.: People-tracking-by-detection and people-detection-by-tracking. In: International Conference on Computer Vision and Pattern Recognition (CVPR’08). Anchorage, Alaska (2008)

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

    Article  Google Scholar 

  4. Avidan, S.: Ensemble tracking. Trans. Pattern Anal. Mach. Intell. (PAMI’07) 29(2), 261–271 (2007)

    Article  Google Scholar 

  5. Bar-Shalom, Y., Jaffer, A.: Tracking and Data Association. Academic Press, San Diego (1998)

    Google Scholar 

  6. Bardet, F., Chateau, T., Ramasadan, D.: Illumination aware mcmc particle filter for long-term outdoor multi-object simultaneous tracking and classification. In: International Conference on Computer Vision (ICCV’09), Kyoto, Japan (2009)

  7. Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the clear mot metrics. J. Image Video Process. 2008, 1 (2008)

    Article  Google Scholar 

  8. Berzuini, C., Gilks, W.: RESAMPLE-MOVE filtering with cross-model jumps. Series Statistics For Engineering and Information Science. Springer, New York (2000)

    Google Scholar 

  9. Breitenstein, M., Reichlin, F., Leibe, B., Koller-Meier, E., Van Gool, L.: Robust tracking-by-detection using a detector confidence particle filter. In: International Conference on Computer Vision (ICCV’09), Kyoto, Japan, pp. 1515–1522 (2009)

  10. Cai, Y., De Freitas, N., Little, J.: Robust visual tracking for multiple targets. In: European Conference on Computer Vision (ECCV’06), Graz, Austria (2006)

  11. Chang, C., Ansari, R., Khokhar, A.: Multiple object tracking with kernel particle filter. In: International Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, USA (2005)

  12. Cho, J., Hun Jin, S., Dai Pham, X., Jeon, J.: Multiple object tracking circuit using particle filters with multiple features. In: International Conference on Robotics and Automation (ICRA’07), , Roma, Italy, pp. 4639–4644 (2007)

  13. Choi, W., Savarese, S.: Multiple target tracking in world coordinate with single, minimally calibrated camera. In: Computer Vision—ECCV 2010, pp. 553–567 (2010)

  14. Choudhury Verma, R., Schmid, C., Mikolajczyk, K.: Face detection and tracking in a video by propagating detection probabilities. Trans. Pattern Anal. Mach. Intell. (PAMI’03) 25(10), (2003)

  15. Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: International Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, USA (2005)

  16. Everingham, M., others (34 authors): The 2005 PASCAL visual object classification challenge. In: PASCAL Challenges Workshop, Graz, Austria (2006)

  17. Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. Trans. Pattern Anal. Mach. Intell. (PAMI’09) 99(1) (2009)

  18. Gabriel, P., Verly, J., Piater, J., Genon, A.: The state of the art in multiple object tracking under occlusion in video sequences. In: International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS’03), Ghent, Belgium (2003)

  19. Gatica-Perez, D., Odobez, J., Ba, S., Smith, K., Lathoud, G.: Tracking people in meetings with particles. In: Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS’05), Montreux, Switzerland (2005)

  20. Grabner, H., Bischof, H.: On-line boosting and vision. In: International Conference on Computer Vision and Pattern Recognition (CVPR’06), New York, USA (2006)

  21. Green, P.: Reversible jump Markov Chain Monte Carlo computation and bayesian model determination. Biometrika 82(4), 711–732 (1995)

    Article  MathSciNet  MATH  Google Scholar 

  22. Gumpp, T., Azad, P., Welke, K., Oztop, E., Dillman, R., Cheng, G.: Unconstrained real-time markerless hand tracking for humanoid interaction. In: International Conference on Humanoid Robots (HUMANOID’06), Genoa, Italy (2006)

  23. Hue, C., Le Cadre, J., Pérez, P.: Sequential Monte Carlo methods for multiple target tracking and data fusion. Trans. Signal Process. 50(2), 309–325 (2002)

    Article  Google Scholar 

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

    Article  Google Scholar 

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

  26. Isard, M., MacCormick, J.: BraMBLe: a bayesian multiple blob tracker. In: International Conference on Computer Vision (ICCV’01), vol. 1, pp. 34–41. Vancouver, Canada (2001)

  27. Khan, Z., Balch, T., Dellaert, F.: MCMC-based particle filtering for tracking a variable number of interacting targets. Trans. Pattern Anal. Mach. Intell. (PAMI’05) 27(11), 1805–1818 (2005)

    Article  Google Scholar 

  28. Laptev, I.: Improvements of object detection using boosted histograms. In: British Machine Vision Conference (BMVC’06). Edinburgh, UK, pp. 949–958 (2006)

  29. Leibe, B., Schindler, K., Gool, L.: Coupled detection and trajectory estimation for multi-object tracking. In: International Conference on Computer Vision (ICCV’07), Rio de Janeiro, Brazil (2007)

  30. Li, Y., Huang, C., Nevatia, R.: Learning to associate: hybridboosted multi-target tracker for crowded scene. In: International Conference on Computer Vision and Pattern Recognition (CVPR’09), Miami, USA (2009)

  31. MacCormick, J., Blake, A.: A probabilistic exclusion principle for tracking multiple objects. Int. J. Comput. Vis. (IJCV’00) 39(1), 57–71 (2000)

    Article  MATH  Google Scholar 

  32. Mc Kenna, S., Nait-Charif, H.: Tracking human motion using auxiliary particle filters and iterated likelihood weighting. Image Vis. Comput. (IVC’07) 25(6), 852–862 (2007)

    Article  Google Scholar 

  33. Van der Merwe, R., Doucet, A., De Freitas, J., Wan, E.: The unscented particle filter. Adv. Neural Inf. Process. Syst. 8, 351–357 (2000)

    Google Scholar 

  34. Okuma, K., Taleghani, A., De Freitas, N.: A boosted particle filter: multitarget detection and tracking. In: European Conference on Computer Vision (ECCV’04), Prague, Czech Republic (2004)

  35. Qu, W., Schonfeld, D., Mohamed, M.: Distributed bayesian multiple-target tracking in crowded environments using multiple collaborative cameras. EURASIP J. Adv. Signal Process. (2007)

  36. Rui, Y., Chen, Y.: Better proposal distributions: object tracking using unscented particle filter. In: Int. Conference on Computer Vision and Pattern Recognition (CVPR’01), Kauai, USA, pp. 786–793 (2001)

  37. Smith, K., Gatica-Perez, D., Odobez, J.: Using particles to track varying numbers of interacting people. In: International Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, USA, pp. 962–969 (2005)

  38. Songhwai, O., Russell, S., Sastry, S.: Markov chain monte carlo data association for general multiple-target. In: International Conference on Decision and Control (CDC’04), Atlantis, Bahamas, pp. 735–742 (2004)

  39. Stauffer, C., Grimson, W.: Adaptative background mixture models for real-time tracking. In: International Conference on Computer Vision and Pattern Recognition (CVPR’99), Fort Collins, USA, vol. 2, pp. 22–46 (1999)

  40. Vacchetti, L., Lepetit, V., Fua, P.: Stable real-time 3D tracking using online and offline information. Trans. Pattern Anal. Mach. Intell. (PAMI’04) 26(10), 1385–1391 (2004)

    Article  Google Scholar 

  41. Vermaak, J., Doucet, A., Pérez, P.: Maintining multi modality through mixture tracking. In: International Conference on Computer Vision (ICCV’03), Nice, France (2003)

  42. Wu, B., Nevatia, R.: Detection and tracking of multiple, partially, occluded humans by Bayesian combination of edgelet based part detectors. Trans. Pattern Anal. Mach. Intell. (PAMI’07) 75(2), 247–266 (2007)

    Google Scholar 

  43. Yang, C., Duraiswami, R., Davis, L.: Fast multiple object tracking via a hierarchical particle filter. In: International Conference on Computer Vision (ICCV’05), Beijing, China, pp. 212–219 (2005)

  44. Yang, M., Lv, F., Xu, W., Gong, Y.: Detection driven adaptive multi-cue integration for multiple human tracking. In: International Conference on Computer Vision (ICCV’09), Kyoto, Japan, pp. 1554–1561 (2009)

  45. Yu, T., Wu, Y.: Collaborative tracking of multiple targets. In: International Conference on Computer Vision and Pattern Recognition (CVPR’04), Washington, USA, pp. 834–841 (2004)

  46. Zhao, T., Nevatia, R.: Tracking multiple humans in crowded environment. In: International Conference on Computer Vision and Pattern Recognition (CVPR’04), Washington, USA (2004)

  47. Zuriarrain, I., Arana, N., Lerasle, F.: Implementation analysis for a hybrid particle filter on a FPGA based smart camera. In: International Conference on Computer Vision Theory and Applications (VISAPP’10), Angers, France (2010)

Download references

Author information

Authors and Affiliations

  1. Goi Eskola Politeknikoa, Mondragon Goi Unibertsitatea, Mondragon, Spain

    Iker Zuriarrain & Nestor Arana

  2. LAAS-CNRS, 7 Avenue Colonel Roche, 31077 , Toulouse, France

    Alhayat Ali Mekonnen

  3. Université de Toulouse, UPS, INSA, INP, ISAE, LAAS, 31077 , Toulouse, France

    Frédéric Lerasle

Authors
  1. Iker Zuriarrain
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Alhayat Ali Mekonnen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Frédéric Lerasle
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nestor Arana
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Iker Zuriarrain.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Zuriarrain, I., Mekonnen, A.A., Lerasle, F. et al. Tracking-by-detection of multiple persons by a resample-move particle filter. Machine Vision and Applications 24, 1751–1765 (2013). https://doi.org/10.1007/s00138-013-0534-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00138-013-0534-9

Keywords

Search

Navigation