Advertisement

Transfer Learning Based Visual Tracking with Gaussian Processes Regression

  • Jin Gao
  • Haibin Ling
  • Weiming Hu
  • Junliang Xing
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8691)

Abstract

Modeling the target appearance is critical in many modern visual tracking algorithms. Many tracking-by-detection algorithms formulate the probability of target appearance as exponentially related to the confidence of a classifier output. By contrast, in this paper we directly analyze this probability using Gaussian Processes Regression (GPR), and introduce a latent variable to assist the tracking decision. Our observation model for regression is learnt in a semi-supervised fashion by using both labeled samples from previous frames and the unlabeled samples that are tracking candidates extracted from the current frame. We further divide the labeled samples into two categories: auxiliary samples collected from the very early frames and target samples from most recent frames. The auxiliary samples are dynamically re-weighted by the regression, and the final tracking result is determined by fusing decisions from two individual trackers, one derived from the auxiliary samples and the other from the target samples. All these ingredients together enable our tracker, denoted as TGPR, to alleviate the drifting issue from various aspects. The effectiveness of TGPR is clearly demonstrated by its excellent performances on three recently proposed public benchmarks, involving 161 sequences in total, in comparison with state-of-the-arts.

Keywords

Object Tracking Target Sample Observation Model Visual Tracking Transfer Learn 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Adam, A., Rivlin, E., Shimshoni, I.: Robust fragments-based tracking using the integral histogram. In: CVPR (2006)Google Scholar
  2. 2.
    Babenko, B., Yang, M.-H., Belongie, S.: Visual tracking with online multiple instance learning. In: CVPR (2009)Google Scholar
  3. 3.
    Bao, C., Wu, Y., Ling, H., Ji, H.: Real time robust ℓ1 tracker using accelerated proximal gradient approach. In: CVPR (2012)Google Scholar
  4. 4.
    Dinh, T.B., Vo, N., Medioni, G.: Context tracker: Exploring supporters and distracters in unconstrained environments. In: CVPR (2011)Google Scholar
  5. 5.
    Erdem, E., Dubuisson, S., Bloch, I.: Fragments based tracking with adaptive cue integration. Computer Vision and Image Understanding 116(7), 827–841 (2012)CrossRefGoogle Scholar
  6. 6.
    Grabner, H., Grabner, M., Bischof, H.: Real-time tracking via on-line boosting. In: BMVC (2006)Google Scholar
  7. 7.
    Grabner, H., Leistner, C., Bischof, H.: Semi-supervised on-line boosting for robust tracking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 234–247. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  8. 8.
    Hare, S., Saffari, A., Torr, P.H.S.: Struck: Structured output tracking with kernels. In: ICCV (2011)Google Scholar
  9. 9.
    He, S., Yang, Q., Lau, R., Wang, J., Yang, M.-H.: Visual tracking via locality sensitive histograms. In: CVPR (2013)Google Scholar
  10. 10.
    Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: Exploiting the circulant structure of tracking-by-detection with kernels. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol. 7575, pp. 702–715. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  11. 11.
    Herbrich, R.: Kernel classifiers from a bayesian perspective. Learning Kernel Classifiers: Theory and Algorithms. MIT Press (2002)Google Scholar
  12. 12.
    Hu, W., Li, X., Luo, W., Zhang, X., Maybank, S., Zhang, Z.: Single and multiple object tracking using log-euclidean riemannian subspace and block-division appearance model. Trans. on PAMI 34(12), 2420–2440 (2012)CrossRefGoogle Scholar
  13. 13.
    Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. International Journal of Computer Vision 29(1), 5–28 (1998)CrossRefGoogle Scholar
  14. 14.
    Jia, X., Lu, H., Yang, M.-H.: Visual tracking via adaptive structural local sparse appearance model. In: CVPR (2012)Google Scholar
  15. 15.
    Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. Trans. on PAMI 34(7), 1409–1422 (2012)CrossRefGoogle Scholar
  16. 16.
    Kristan, M., Pflugfelder, R., et al.: The visual object tracking vot2013 challenge results. In: Vis. Obj. Track. Challenge VOT 2013, In conjunction with ICCV (2013)Google Scholar
  17. 17.
    Kwon, J., Lee, K.M.: Visual tracking decomposition. In: CVPR (2010)Google Scholar
  18. 18.
    Kwon, J., Lee, K.M.: Tracking by sampling trackers. In: ICCV (2011)Google Scholar
  19. 19.
    Kwon, J., Lee, K.M.: Minimum uncertainty gap for robust visual tracking. In: CVPR (2013)Google Scholar
  20. 20.
    Li, G., Qin, L., Huang, Q., Pang, J., Jiang, S.: Treat samples differently: object tracking with semi-supervised online covboost. In: ICCV (2011)Google Scholar
  21. 21.
    Li, X., Shen, C., Dick, A., van den Hengel, A.: Learning compact binary codes for visual tracking. In: CVPR (2013)Google Scholar
  22. 22.
    Li, X., Shen, C., Shi, Q., Dick, A., van den Hengel, A.: Non-sparse linear representations for visual tracking with online reservoir metric learning. In: CVPR (2012)Google Scholar
  23. 23.
    Li, Y., Ai, H., Yamashita, T., Lao, S., Kawade, M.: Tracking in low frame rate video: A cascade particle filter with discriminative observers of different lifespans. In: CVPR (2007)Google Scholar
  24. 24.
    Liu, B., Huang, J., Yang, L., Kulikowsk, C.: Robust tracking using local sparse appearance model and k-selection. In: CVPR (2011)Google Scholar
  25. 25.
    Mei, X., Ling, H.: Robust visual tracking and vehicle classification via sparse representation. Trans. on PAMI 33(11), 2259–2272 (2011)CrossRefGoogle Scholar
  26. 26.
    Mei, X., Ling, H., Wu, Y., Blasch, E., Bai, L.: Minimum error bounded efficient ℓ1 tracker with occlusion detection. In: CVPR (2011)Google Scholar
  27. 27.
    Oron, S., Bar-Hillel, A., Levi, D., Avidan, S.: Locally orderless tracking. In: CVPR (2012)Google Scholar
  28. 28.
    Pang, Y., Ling, H.: Finding the best from the second bests - inhibiting subjective bias in evaluation of visual tracking algorithms. In: ICCV (2013)Google Scholar
  29. 29.
    Ross, D.A., Lim, J., Lin, R., Yang, M.-H.: Incremental learning for robust visual tracking. Int. J. Comp. Vis. 77(1), 125–141 (2008)CrossRefGoogle Scholar
  30. 30.
    Song, S., Xiao, J.: Tracking revisited using rgbd camera: Unified benchmark and baselines. In: ICCV (2013)Google Scholar
  31. 31.
    Supančič, J.S., Ramanan, D.: Self-paced learning for long-term tracking. In: CVPR (2013)Google Scholar
  32. 32.
    Wang, D., Lu, H., Yang, M.-H.: Least soft-thresold squares tracking. In: CVPR (2013)Google Scholar
  33. 33.
    Wang, N., Yeung, D.Y.: Learning a deep compact image representation for visual tracking. In: NIPS (2013)Google Scholar
  34. 34.
    Wang, Q., Chen, F., Yang, J., Xu, W., Yang, M.-H.: Transferring visual prior for online object tracking. Trans. on IP 21(7), 3296–3305 (2012)MathSciNetGoogle Scholar
  35. 35.
    Wu, Y., Lim, J., Yang, M.-H.: Online object tracking: A benchmark. In: CVPR (2013)Google Scholar
  36. 36.
    Xing, J., Gao, J., Li, B., Hu, W., Yan, S.: Robust object tracking with online multi-lifespan dictionary learning. In: ICCV (2013)Google Scholar
  37. 37.
    Yao, R., Shi, Q., Shen, C., Zhang, Y., van den Hengel, A.: Part-based visual tracking with online latent structural learning. In: CVPR (2013)Google Scholar
  38. 38.
    Yao, Y., Doretto, G.: Boosting for transfer learning with multiple sources. In: CVPR (2010)Google Scholar
  39. 39.
    Yilmaz, A., Javed, O., Shah, M.: Object tracking: A survey. ACM Comput. Surv. 38(4) (2006)Google Scholar
  40. 40.
    Zelnik-Manor, L., Perona, P.: Self-tuning spectral clustering. In: NIPS (2005)Google Scholar
  41. 41.
    Zhang, K., Zhang, L., Yang, M.-H.: Real-time compressive tracking. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 864–877. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  42. 42.
    Zhang, L., van der Maaten, L.: Structure preserving object tracking. In: CVPR (2013)Google Scholar
  43. 43.
    Zhang, T., Ghanem, B., Liu, S., Ahuja, N.: Low-rank sparse learning for robust visual tracking. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol. 7577, pp. 470–484. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  44. 44.
    Zhang, T., Ghanem, B., Liu, S., Ahuja, N.: Robust visual tracking via multi-task sparse learning. In: CVPR (2012)Google Scholar
  45. 45.
    Zhong, W., Lu, H., Yang, M.-H.: Robust object tracking via sparsity-based collaborative model. In: CVPR (2012)Google Scholar
  46. 46.
    Zhu, X., Ghahramani, Z., Lafferty, J.: Semi-supervised learning using gaussian fields and harmonic functions. In: ICML (2003)Google Scholar
  47. 47.
    Zhu, X., Lafferty, J., Ghahramani, Z.: Semi-supervised learning: From gaussian fields to gaussian processes. Tech. Rep. CMU-CS-03-175, School of Computer Science, Carnegie Mellon University, Pittsburgh, Pennsylvania (August 2003)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Jin Gao
    • 1
    • 2
  • Haibin Ling
    • 2
  • Weiming Hu
    • 1
  • Junliang Xing
    • 1
  1. 1.National Laboratory of Pattern RecognitionInstitute of Automation, CASBeijingChina
  2. 2.Department of Computer and Information SciencesTemple UniversityPhiladelphiaUSA

Personalised recommendations