Multimedia Tools and Applications

, Volume 77, Issue 3, pp 3623–3637 | Cite as

Multiple person tracking based on slow feature analysis

Article
  • 82 Downloads

Abstract

Object tracking is one of the most important components in numerous applications of computer vision. However, it still has many challenges to be solved, such as occlusion, matching, data association, etc. In this paper, we proposed to utilize slow feature analysis (SFA) method to handle the multiple person tracking problem. First, the part-based model is utilized to detect pedestrian in each frame. Then, a set of reliable tracklets is generated by utilizing spatial-temporal information of detection results. Third, SFA method is leveraged to extract slow-feature for these reliable tracklets. Finally, the traditional graph matching method is utilized to handle data association problem and consequently generate the final trajectory for individual tracking object. Some popular datasets are used in this study. The extensive comparison experiments demonstrate the superiority of the proposed method.

Keywords

Multiple person tracking Object tracking Slow feature analysis 

Notes

Acknowledgment

This work was supported by the National High-Tech Research and Development Program of China (program 863, 2012AA10A401), the Grants of the Major State Basic Research Development Program of China (program 973, 2012CB114405), the National Key Technology R&D Program (2011BAD13B07 and 2011BAD13B04), the National Natural Science Foundation of China (31770904, 21106095), the Natural Science Foundation of Tianjin (15JCYBJC30700), the project of introducing one thousand high level talents in three years (5KQM110003), the Foundation for Introducing Talents to Tianjin Normal University (5RL123), the Academic Innovation Promotion Project of Tianjin Normal University for young teachers (52XC1403), the 131 Innovative Talents Cultivation of Tianjin (ZX110170) and Tianjin Normal University Application and Development Program (52XK1502).

References

  1. 1.
    Bae SH, Yoon K-J (2014) Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning. CVPR, pp 1218–1225Google Scholar
  2. 2.
    Babenko B, Yang MH, Belongie S (2011) Robust object tracking with online multiple instance learning. IEEE Trans Pattern Anal Mach Intell 33(8):1619–1632CrossRefGoogle Scholar
  3. 3.
    Bazzani L, Cristani M, Murino V (2012) Decentralized particle filter for joint individual-group tracking. In: CVPR, pp 1886–1893Google Scholar
  4. 4.
    Benfold B, Reid ID (2011) Stable multi-target tracking in real-time surveillance video. In: The 24th IEEE conference on computer vision and pattern recognition, CVPR 2011, Colorado Springs, CO, USA, 20-25 June 2011, pp 3457–3464Google Scholar
  5. 5.
    Benfold B, Reid I (2011) Stable multi-target tracking in real-time surveillance video. In: CVPR, pp 3457–3464Google Scholar
  6. 6.
    Chang X, Yang Y (2016) Semi-supervised feature analysis by mining correlations among multiple tasks. In: IEEE transactions on neural networks and learning systems (99), pp 1–12Google Scholar
  7. 7.
    Chang X, Ma Z, Lin M, Yang Y, Hauptmann AG (2017) Feature interaction augmented sparse learning for fast kinect motion detection. IEEE Trans Image Process 26(8):3911–3920MathSciNetCrossRefGoogle Scholar
  8. 8.
    Chang X, Ma Z, Yang Y, Zeng Z, Hauptmann AG (2017) Bi-level semantic representation analysis for multimedia event detection. IEEE Trans Cybernetics 47(5):1180–1197CrossRefGoogle Scholar
  9. 9.
    Chang X, Nie F, Wang S, Yang Y, Zhou X, Zhang C (2016) Compound rank-k projections for bilinear analysis. IEEE Trans Neural Netw Learning Syst 27(7):1502–1513MathSciNetCrossRefGoogle Scholar
  10. 10.
    Chang X, Yu Y, Yang Y, Xing EP (2017) Semantic pooling for complex event analysis in untrimmed videos. IEEE Trans Pattern Anal Mach Intell 39(8):1617–1632CrossRefGoogle Scholar
  11. 11.
    Felzenszwalb PF, McAllester DA, Ramanan D (2008) A discriminatively trained, multiscale, deformable part model. In: 2008 IEEE computer society conference on computer vision and pattern recognition (CVPR 2008), 24–26 June 2008, Anchorage, Alaska, USA.  https://doi.org/10.1109/CVPR.2008.4587597
  12. 12.
    Fisher RB (2004) Pets04 surveillance ground truth data set. In: Sixth IEEE international workshop on performance evaluation of tracking and surveillance, pp 3457–3464Google Scholar
  13. 13.
    Gall J, Lempitsky VS (2009) Class-specific Hough forests for object detection. CVPR, pp 1022–1029Google Scholar
  14. 14.
    Gao Y, Dai Q, Wang M, Zhang N (2011) 3d model retrieval using weighted bipartite graph matching. Signal Process Image Commun 26(1):39–47CrossRefGoogle Scholar
  15. 15.
    Gorur P, Amrutur B (2011) Speeded up gaussian mixture model algorithm for background subtraction. In: AVSS, pp 386–391Google Scholar
  16. 16.
    Granstrom K, Lundquist C (2013) On the use of multiple measurement models for extended target tracking. In: 2013 16th international conference on information fusion (FUSION), pp 1534–1541Google Scholar
  17. 17.
    Granström K, Orguner U (2012) A phd filter for tracking multiple extended targets using random matrices. IEEE Trans Signal Process 60(11):5657–5671MathSciNetCrossRefGoogle Scholar
  18. 18.
    Han Z, Ye Q, Jiao J (2008) Online feature evaluation for object tracking using kalman filter. In: ICPR, pp 1–4Google Scholar
  19. 19.
    Kalal Z, Mikolajczyk K, Matas J (2012) Tracking-learning-detection. IEEE Trans Pattern Anal Mach Intell 34(7):1409–1422CrossRefGoogle Scholar
  20. 20.
    Kwon J, Lee KM (2010) Visual tracking decomposition. CVPR, pp 1269–1276Google Scholar
  21. 21.
    Leal-Taixé L, Pons-Moll G, Rosenhahn B (2011) Everybody needs somebody: modeling social and grouping behavior on a linear programming multiple people tracker. In: ICCV Workshops, pp 120–127Google Scholar
  22. 22.
    Li Z, Yabuta K, Kitazawa H (2010) Exclusive block matching for moving object extraction and tracking. Ieice Transactions on Information & Systems 93(5):1263–1271CrossRefGoogle Scholar
  23. 23.
    Liu A, Nie W, Gao Y, Su Y (2016) Multi-modal clique-graph matching for view-based 3d model retrieval. IEEE Trans. Image Process. 25(5):2103–2116MathSciNetCrossRefGoogle Scholar
  24. 24.
    Liu A, Su Y, Jia P-P, Gao Z, Hao T, Yang Z (2015) Multipe/single-view human action recognition via part-induced multitask structural learning. IEEE Trans Cybernetics 45(6):1194–1208CrossRefGoogle Scholar
  25. 25.
    Liu A, Su Y, Nie W, Kankanhalli MS (2017) Hierarchical clustering multi-task learning for joint human action grouping and recognition. IEEE Trans Pattern Anal Mach Intell 39(1):102–114CrossRefGoogle Scholar
  26. 26.
    Luo C, Cai X, Zhang J (2008) Robust object tracking using the particle filtering and level set methods: a comparative experiment. In: IEEE workshop on multimedia signal processing, pp 359–364Google Scholar
  27. 27.
    Makris A, Prieur C (2014) Bayesian multiple-hypothesis tracking of merging and splitting targets. IEEE Trans Geosci Remote Sens 52(12):7684–7694CrossRefGoogle Scholar
  28. 28.
    Marcenaro L, Morerio P, Regazzoni CS (2012) Performance evaluation of multi-camera visual tracking. In: Ninth IEEE international conference on advanced video and signal-based surveillance, AVSS 2012. Beijing, China, September 18-21, 2012, pp 464–469Google Scholar
  29. 29.
    Nie W, Liu A, Su Y (2012) Multiple person tracking by spatiotemporal tracklet association. In: AVSS, pp 481–486Google Scholar
  30. 30.
    Nie W, Liu A, Su Y, Luan H-B, Yang Z, Cao L, Ji R (2014) Single/cross-camera multiple-person tracking by graph matching. Neurocomputing 139:220–232CrossRefGoogle Scholar
  31. 31.
    Nie W, Liu A, Su Y, Wei S (2017) Multi-view feature extraction based on slow feature analysis. Neurocomputing 252:49–57CrossRefGoogle Scholar
  32. 32.
    Oja E (1982) Simplified neuron model as a principal component analyzer. J Math Biol 15(3):267–273MathSciNetCrossRefMATHGoogle Scholar
  33. 33.
    Oja E (1992) Principal components, minor components, and linear neural networks. Neural Netw 5(6):927–935CrossRefGoogle Scholar
  34. 34.
    Ottlik A, Nagel HH (2008) Initialization of model-based vehicle tracking in video sequences of inner-city intersections. Int J Comput Vis 80(2):211–225CrossRefGoogle Scholar
  35. 35.
    Pellegrini S, Ess A, Van Gool LJ (2010) Improving data association by joint modeling of pedestrian trajectories and groupings. In: ECCV (1), pp 452–465Google Scholar
  36. 36.
    Peng D, Yi Z, Luo W (2007) Convergence analysis of a simple minor component analysis algorithm. Neural Netw 20(7):842–850CrossRefMATHGoogle Scholar
  37. 37.
    Perez P, Vermaak J, Blake A (2004) Data fusion for visual tracking with particles. Proc IEEE 92(3):495–513CrossRefGoogle Scholar
  38. 38.
    Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, pp 91–99Google Scholar
  39. 39.
    Schmidhuber J, Prelinger D (1993) Discovering predictable classifications. Neural Comput 5(4):625– 635CrossRefGoogle Scholar
  40. 40.
    Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y (2013) Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv:1312.6229
  41. 41.
    Shu G, Dehghan A, Oreifej O, Hand E, Shah M (2012) Part-based multiple-person tracking with partial occlusion handling. In: CVPR, pp 1815–1821Google Scholar
  42. 42.
    Tu J, Tao H, Huang TS (2006) Online updating appearance generative mixture model for meanshift tracking. In: ACCV (1), pp 694–703Google Scholar
  43. 43.
    Wen L, Lei Z, Lyu S, Li SZ, Yang M-H (2016) Exploiting hierarchical dense structures on hypergraphs for multi-object tracking. IEEE Trans Pattern Anal Mach Intell 38(10):1983–1996.  https://doi.org/10.1109/TPAMI.2015.2509979 CrossRefGoogle Scholar
  44. 44.
    Weng M, Huang G, Da X (2010) A new interframe difference algorithm for moving target detection. In: 2010 3rd international congress on image and signal processing (CISP), pp 285–289Google Scholar
  45. 45.
    Weng J, Zhang Y, Hwang W-S (2003) Candid covariance-free incremental principal component analysis. IEEE Trans Pattern Anal Mach Intell 25(8):1034–1040CrossRefGoogle Scholar
  46. 46.
    Yamaguchi K, Berg AC, Ortiz LE, Berg TL (2011) Who are you with and where are you going?. In: CVPR, pp 1345–1352Google Scholar
  47. 47.
    Zhang L, Li Y, Nevatia R (2008) Global data association for multi-object tracking using network flows. In: CVPRGoogle Scholar
  48. 48.
    Zhang Y, Weng J (2001) Convergence analysis of complementary candid incremental principal component analysis. Michigan State UniversityGoogle Scholar
  49. 49.
    Zhu L, Zhou J, Song J (2008) Tracking multiple objects through occlusion with online sampling and position estimation. Pattern Recogn 41(8):2447–2460CrossRefMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  1. 1.Tianjin Key Laboratory of Animal and Plant Resistance/College of Life SciencesTianjin Normal UniversityTianjinChina
  2. 2.Tianjin Bohai Fisheries Research InstituteTianjinChina

Personalised recommendations