access icon free Online multi-person tracking with two-stage data association and online appearance model learning

This study addresses the automatic multi-person tracking problem in complex scenes from a single, static, uncalibrated camera. In contrast with offline tracking approaches, a novel online multi-person tracking method is proposed based on a sequential tracking-by-detection framework, which can be applied to real-time applications. A two-stage data association is first developed to handle the drifting targets stemming from occlusions and people's abrupt motion changes. Subsequently, a novel online appearance learning is developed by using the incremental/decremental support vector machine with an adaptive training sample collection strategy to ensure reliable data association and rapid learning. Experimental results show the effectiveness and robustness of the proposed method while demonstrating its compatibility with real-time applications.

Inspec keywords: object detection; sensor fusion; learning (artificial intelligence); image sensors; object tracking; support vector machines

Other keywords: static camera; decremental support vector machine; uncalibrated camera; online multiperson tracking method; automatic multiperson tracking problem; sequential tracking-by-detection framework; two-stage data association; incremental support vector machine; drifting targets; adaptive training sample collection strategy; single camera; rapid learning; online appearance model learning

Subjects: Sensor fusion; Knowledge engineering techniques; Optical, image and video signal processing; Image sensors; Computer vision and image processing techniques

References

    1. 1)
      • 4. Andriyenko, A., Roth, S., Schindler, K.: ‘Continuous energy minimization for multitarget tracking’, IEEE Trans. Pattern Anal. Mach. Intell., 2014, 36, (1), pp. 5872.
    2. 2)
      • 24. Keni, B., Rainer, S.: ‘Evaluating multiple object tracking performance: the CLEAR MOT metrics’, EURASIP J. Image Video Process., 2008, 2008, (1), pp. 110.
    3. 3)
      • 26. Dicle, C., Camps, O., Sznaier, M.: ‘The way they move: tracking multiple targets with similar appearance’. Proc. Int. Conf. on Computer Vision, Sydney, NSW, December 2013, pp. 23042311.
    4. 4)
      • 25. Li, Y., Huang, C., Nevatia, R.: ‘Learning to associate: HybridBoosted multi-target tracker for crowded scene’. Proc. Computer Vision and Pattern Recognition, Miami, USA, June 2009, pp. 29532960.
    5. 5)
      • 11. Yang, J., Shi, Z., Vela, P., et al: ‘Probabilistic multiple people tracking through complex situations’. Proc. Int. Workshop on Performance Evaluation of Tracking and Surveillance, Miami, USA, June 2009, pp. 7986.
    6. 6)
      • 3. Berclaz, J., Fleuret, F., Turetken, E., et al: ‘Multiple object tracking using K-shortest paths optimization’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (9), pp. 18061819.
    7. 7)
      • 17. Bae, S.H., Yoon, K.J.: ‘Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning’. Proc. Computer Vision and Pattern Recognition, Columbus, OH, June 2014, pp. 12181225.
    8. 8)
      • 7. Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: ‘Globally-optimal greedy algorithms for tracking a variable number of objects’. Proc. Computer Vision and Pattern Recognition, Providence, USA, June 2011, pp. 12011208.
    9. 9)
      • 18. Grabner, H., Bischof, H.: ‘On-line boosting and vision’. Proc. Computer Vision and Pattern Recognition, New York, USA, June 2006, pp. 260267.
    10. 10)
      • 10. Choi, W.: ‘Near-online multi-target tracking with aggregated local flow descriptor’. Proc. Int. Conf. on Computer Vision, Santiago, Chile, December 2015, pp. 30293037.
    11. 11)
      • 14. Yamaguchi, K., Berg, A., Ortiz, L., et al: ‘Who are you with and where are you going?’. Proc. Computer Vision and Pattern Recognition, Providence, USA, June 2011, pp. 13451352.
    12. 12)
      • 9. Yang, B., Nevatia, R.: ‘Multi-target tracking by online learning of non-linear motion patterns and robust appearance models’. Proc. Computer Vision and Pattern Recognition, Providence, USA, June 2012, pp. 19181925.
    13. 13)
      • 21. ‘PETS 2009 Dataset’. Available at http://www.cvg.reading.ac.uk/PETS2009/, accessed 2 November 2015.
    14. 14)
      • 8. Yang, B., Nevatia, R.: ‘An online learned CRF model for multitarget tracking’. Proc. Computer Vision and Pattern Recognition, Providence, USA, June 2012, pp. 20342041.
    15. 15)
      • 23. ‘MOT Challenge Dataset’. Available at http://www.motchallenge.net/, accessed 9 January 2016.
    16. 16)
      • 1. Dollar, P., Appel, R., Belongie, S., et al: ‘Fast feature pyramids for object detection’, IEEE Trans. Pattern Anal. Mach. Intell., 2014, 36, (8), pp. 15321545.
    17. 17)
      • 5. Leal-Taixe, L., Pons-Moll, G., Rosenhahn, B.: ‘Everybody needs somebody: modeling social and grouping behavior on a linear programming multiple people tracker’. Proc. Int. Conf. on Computer Vision Workshops, Barcelona, Spain, November 2011, pp. 120127.
    18. 18)
      • 12. Breitenstein, M.D., Reichlin, F., Leibe, B., et al: ‘Online multiperson tracking-by-detection from a single, uncalibrated camera’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (9), pp. 18201833.
    19. 19)
      • 15. Yan, X., Wu, X., Kakadiaris, I., et al: ‘To track or to detect? An ensemble framework for optimal selection’. Proc. European Conf. on Computer Vision, Florence, Italy, October 2012, pp. 594607.
    20. 20)
      • 19. Cauwenberghs, G., Poggio, T.: ‘Incremental and decremental support vector machine learning’, in Leen, Todd K., Dietterich, Thomas G., Tresp, Volker (Eds.): ‘Advances in neural information processing systems 13’ (MIT Press, Cambridge, MA, 2001), pp. 409415.
    21. 21)
      • 27. Geiger, A., Lauer, M., Wojek, C., et al: ‘3d traffic scene understanding from movable platforms’, IEEE Trans. Pattern Anal. Mach. Intell., 2013, 36, (5), pp. 10121025.
    22. 22)
      • 2. Ouyang, W., Zeng, X., Wang, X.: ‘Single-pedestrian detection aided by 2-pedestrian detection’, IEEE Trans. Pattern Anal. Mach. Intell., 2014, 37, (9), pp. 18751889.
    23. 23)
      • 6. Huang, C., Wu, B., Nevatia, R.: ‘Robust object tracking by hierarchical association of detection responses’. Proc. European Conf. on Computer Vision, Marseille, France, October 2008, pp. 788801.
    24. 24)
      • 16. Yoon, J.H., Yang, M.H., Lim, J., et al: ‘Bayesian multi-object tracking using motion context from multiple objects’. Proc. Conf. on Applications of Computer Vision, Waikoloa, HI, January 2015, pp. 3340.
    25. 25)
      • 13. Pellegrini, S., Ess, A., Schindler, K., et al: ‘You'll never walk alone: modeling social behavior for multitarget tracking’. Proc. Int. Conf. on Computer Vision, Kyoto, Japan, September 2009, pp. 261268.
    26. 26)
      • 20. Platt, J.: ‘Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods’, in Smola, Alexander J., Bartlett, Peter, Schölkopf, Bernhard, Schuurmans, Dale (Eds.): ‘Advances in large margin classifiers’ (MIT Press, Cambridge, MA, 1999), pp. 6174.
    27. 27)
      • 22. ‘Town-Centre Dataset’. Available at http://www.robots.ox.ac.uk/ActiveVision/Research/Projects/2009bbenfold_headpose/project.html, accessed 2 November 2015.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2016.0068
Loading

Related content

content/journals/10.1049/iet-cvi.2016.0068
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading