access icon free Multi-object tracking using dominant sets

© The Institution of Engineering and Technology
Received 07/08/2015, Accepted 18/03/2016, Revised 26/02/2016, Published 23/03/2016

Multi-object tracking is an interesting but challenging task in the field of computer vision. Most previous works based on data association techniques merely take into account the relationship between detection responses in a locally limited temporal domain, which makes them inherently prone to identity switches and difficulties in handling long-term occlusions. In this study, a dominant set clustering based tracker is proposed, which formulates the tracking task as a problem of finding dominant sets in an auxiliary edge weighted graph. Unlike most techniques which are limited in temporal locality (i.e. few frames are considered), the authors utilised a pairwise relationships (in appearance and position) between different detections across the whole temporal span of the video for data association in a global manner. Meanwhile, temporal sliding window technique is utilised to find tracklets and perform further merging on them. The authors’ robust tracklet merging step renders the tracker to long term occlusions with more robustness. The authors present results on three different challenging datasets (i.e. PETS2009-S2L1, TUD-standemitte and ETH dataset (‘sunny day’ sequence)), and show significant improvements compared with several state-of-art methods.

Inspec keywords: pattern clustering; graph theory; video signal processing; computer vision; image fusion; object tracking; set theory

Other keywords: long term occlusion; dominant set clustering based tracker; data association technique; pairwise relationship; temporal sliding window technique; multiobject tracking; auxiliary edge weighted graph; video temporal span; tracklet merging; locally limited temporal domain; computer vision

Subjects: Video signal processing; Computer vision and image processing techniques; Optical, image and video signal processing; Combinatorial mathematics; Combinatorial mathematics

References

    1. 1)
      • 15. Porikli, F., Tuzel, O., Meer, P.: ‘Covariance tracking using model update based on lie algebra’. CVPR (1), 2006, pp. 728–735.
    2. 2)
      • 33. Wang, H., Weng, C., Yuan, J.: ‘Multi-feature spectral clustering with minimax optimization’. The IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2014.
    3. 3)
      • 35. Lourenço, A., Bulò, S.R., Rebagliati, N., et al: ‘Probabilistic consensus clustering using evidence accumulation’, Mach. Learn., 2015, 98, (1–2), pp. 331–357.
    4. 4)
      • 28. Coppi, D., Calderara, S., Cucchiara, R.: ‘People appearance tracing in video by spectral graph transduction’. ICCV Workshops, 2011, pp. 920–927.
    5. 5)
      • 37. Yang, B., Nevatia, R.: ‘Multi-target tracking by online learning a CRF model of appearance and motion patterns’, Int. J. Comput. Vis., 2014, 107, (2), pp. 203–217.
    6. 6)
      • 3. Ess, A., Leibe, B., Schindler, K., et al: ‘A mobile vision system for robust multi-person tracking’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'08), June 2008.
    7. 7)
      • 12. Berclaz, J., Fleuret, F., Türetken, E., et al: ‘Multiple object tracking using k-shortest paths optimization’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (9), pp. 1806–1819.
    8. 8)
      • 39. Milan, A., Leal-Taix, L., Schindler, K., et al: ‘Joint tracking and segmentation of multiple targets’. CVPR, 2015, pp. 5397–5406.
    9. 9)
      • 38. Leal-Taixé, L., Milan, A., Reid, I., et al: ‘Motchallenge 2015: Towards a benchmark for multi-target tracking’. arXiv:1504.01942 [cs], April 2015, arXiv: 1504.01942.
    10. 10)
      • 19. Zhang, L., Li, Y., Nevatia, R.: ‘Global data association for multi-object tracking using network flows’. 2008 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (CVPR 2008), 24–26 June 2008, Anchorage, Alaska, USA, 2008.
    11. 11)
      • 11. Jiang, H., Fels, S., Little, J.J.: ‘A linear programming approach for multiple object tracking’. 2007 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (CVPR 2007), 18–23 June 2007, Minneapolis, Minnesota, USA, 2007.
    12. 12)
      • 13. Brendel, W., Amer, M.R., Todorovic, S.: ‘Multiobject tracking as maximum weight in dependent set’. The 24th IEEE Conf. on Computer Vision and Pattern Recognition, CVPR 2011, Colorado Springs, CO, USA, 20–25 June 2011, 2011, pp. 1273–1280.
    13. 13)
      • 8. Yang, B., Nevatia, R.: ‘Online learned discriminative part-based appearance models for multi-human tracking’. Computer Vision – ECCV 2012 – 12th European Conf. on Computer Vision, Florence, Italy, 7–13 October 2012, Proc. Part I, 2012, pp. 484–498.
    14. 14)
      • 36. Yang, B., Nevatia, R.: ‘An online learned CRF model for multi-target tracking’. 2012 IEEE Conf. on Computer Vision and Pattern Recognition, Providence, RI, USA, 16–21 June 2012, 2012, pp. 2034–2041.
    15. 15)
      • 21. Shitrit, H.B., Berclaz, J., Fleuret, F., et al: ‘Tracking multiple people under global appearance constraints’. IEEE Int. Conf. on Computer Vision, ICCV 2011, Barcelona, Spain, 6–13 November 2011, 2011, pp. 137–144.
    16. 16)
      • 43. Milan, A., Schindler, K., Roth, S.: ‘Detection- and trajectory-level exclusion in multiple object tracking’. 2013 IEEE Conf. on Computer Vision and Pattern Recognition, Portland, OR, USA, 23–28 June 2013, 2013, pp. 3682–3689.
    17. 17)
      • 14. Shu, G., Dehghan, A., Oreifej, O., et al: ‘Part-based multiple-person tracking with partial occlusion handling’. 2012 IEEE Conf. on Computer Vision and Pattern Recognition, Providence, RI, USA, 16–21 June 2012, 2012, pp. 1815–1821.
    18. 18)
      • 24. Pavan, M., Pelillo, M.: ‘Graph-theoretic approach to clustering and segmentation’. CVPR (1), 2003, pp. 145–152.
    19. 19)
      • 17. Reid, D.B.: ‘An algorithm for tracking multiple targets’, IEEE Trans. Autom. Control, 1979, 24, pp. 843–854.
    20. 20)
      • 9. Zamir, A.R., Dehghan, A., Shah, M.: ‘Gmcp-tracker: Global multi-object tracking using generalized minimum clique graphs’. Computer Vision – ECCV 2012 – 12th European Conf. on Computer Vision, Florence, Italy, October 7-13, 2012, Proc., Part II, 2012, pp. 343–356.
    21. 21)
      • 32. Zhong, C., Yue, X., Zhang, Z., et al: ‘A clustering ensemble: Two-level-refined co-association matrix with path-based transformation’, Pattern Recogn., 2015, 48, (8), pp. 2699–2709.
    22. 22)
      • 34. Premachandran, V., Kakarala, R.: ‘Consensus of k-nns for robust neighborhood selection on graph-based manifolds’. 2013 IEEE Conf. on Computer Vision and Pattern Recognition, Portland, OR, USA, 23–28 June 2013, 2013, pp. 1594–1601.
    23. 23)
      • 6. Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: ‘Globally-optimal greedy algorithms for tracking a variable number of objects’. in The 24th IEEE Conf. on Computer Vision and Pattern Recognition, CVPR 2011, Colorado Springs, CO, USA, 20–25 June 2011, 2011, pp. 1201–1208.
    24. 24)
      • 29. Liu, Y., Li, G., Shi, Z.: ‘Covariance tracking via geometric particle filtering’, EURASIP J. Adv. Signal Process, 2010, 2010, pp. 1–22.
    25. 25)
      • 1. Ellis, A., Ferryman, J.M.: ‘PETS2010 and PETS2009 evaluation of results using individual ground truthed single views’. Seventh IEEE Int. Conf. on Advanced Video and Signal Based Surveillance, AVSS 2010, Boston, MA, USA, 29 August–1 September 2010, 2010, pp. 135–142.
    26. 26)
      • 25. Bulò, S.R., Pelillo, M., Bomze, I.M.: ‘Graph-based quadratic optimization: a fast evolutionary approach’, Comput. Vis. Image Underst., 2011, 115, (7), pp. 984–995.
    27. 27)
      • 4. Yilmaz, A., Javed, O., Shah, M.: ‘Object tracking: a survey’, ACM Comput. Surv., 2006, 38, (4), pp. 1–45.
    28. 28)
      • 2. Andriyenko, A., Schindler, K.: ‘Multi-target tracking by continuous energy minimization’. The 24th IEEE Conf. on Computer Vision and Pattern Recognition, CVPR 2011, Colorado Springs, CO, USA, 20–25 June 2011, 2011, pp. 1265–1272.
    29. 29)
      • 41. Bernardin, K., Stiefelhagen, R.: ‘Evaluating multiple object tracking performance: The CLEAR MOT metrics’, EURASIP J. Image Video Process., 2008, 2008, pp. 1:1–1:10.
    30. 30)
      • 20. Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: ‘Globally-optimal greedy algorithms for tracking a variable number of objects’. The 24th IEEE Conf. on Computer Vision and Pattern Recognition, CVPR 2011, Colorado Springs, CO, USA, 20–25 June 2011, 2011, pp. 1201–1208.
    31. 31)
      • 30. Metternich, M.J., Worring, M., Smeulders, A.W.M.: ‘Color based tracing in real-life surveillance data’, T. Data Hiding Multimedia Secur., 2010, 5, pp. 18–33.
    32. 32)
      • 26. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. 2005 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (CVPR 2005), 20–26 June 2005, San Diego, CA, USA, 2005, pp. 886–893.
    33. 33)
      • 7. Xing, J., Ai, H., Lao, S.: ‘Multi-object tracking through occlusions by local tracklets filtering and global tracklets association with detection responses’. 2009 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (CVPR 2009), 20–25 June 2009, Miami, Florida, USA, 2009, pp. 1200–1207.
    34. 34)
      • 18. Yang, T., Li, S.Z., Pan, Q., et al: ‘Real-time multiple objects tracking with occlusion handling in dynamic scenes’. 2005 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (CVPR 2005), 20–26 June 2005, San Diego, CA, USA, 2005, pp. 970–975.
    35. 35)
      • 10. Wu, B., Nevatia, R.: ‘Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet based part detectors’, Int. J. Comput. Vis., 2007, 75, (2), pp. 247–266.
    36. 36)
      • 23. Pavan, M., Pelillo, M.: ‘Dominant sets and pairwise clustering’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (1), pp. 167–172.
    37. 37)
      • 27. Coppi, D., Calderara, S., Cucchiara, R.: ‘Appearance tracking by transduction in surveillance scenarios’. AVSS, 2011, pp. 142–147.
    38. 38)
      • 22. Pavan, M., Pelillo, M.: ‘A new graph-theoretic approach to clustering and segmentation’. Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2003, pp. 145–152.
    39. 39)
      • 42. Fragkiadaki, K., Zhang, W., Zhang, G., et al: ‘Two-granularity tracking: Mediating trajectory and detection graphs for tracking under occlusions’. Computer Vision – ECCV 2012 – 12th European Conf. on Computer Vision, Florence, Italy, 7–13 October, 2012, Proc., Part V, 2012, pp. 552–565.
    40. 40)
      • 31. Frstner, W., Moonen, B.: ‘A metric for covariance matrices’. Technical Report, Dept. Geodesy Geoinform., Stuttgart Univ., Stuttgart, Germany, 1999.
    41. 41)
      • 16. Fortmann, T.E., Bar-Shalom, Y., Scheffe, M.: ‘Multi-target tracking using joint probabilistic data association’. 19th IEEE Conf. on Decision and Control Including the Symp. on Adaptive Processes, 1980, vol. 19.
    42. 42)
      • 5. Perera, A.G.A., Srinivas, C., Hoogs, A., et al: ‘Multi-object tracking through simultaneous long occlusions and split-merge conditions’. 2006 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (CVPR 2006), 17–22 June 2006, New York, NY, USA, 2006, pp. 666–673.
    43. 43)
      • 40. Kuo, C., Nevatia, R.: ‘How does person identity recognition help multi-person tracking?’. The 24th IEEE Conf. on Computer Vision and Pattern Recognition, CVPR 2011, Colorado Springs, CO, USA, 20–25 June 2011, 2011, pp. 1217–1224.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2015.0297
Loading

Related content

content/journals/10.1049/iet-cvi.2015.0297
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading