access icon free Fast deformable structure regression tracking

Visual object tracking is a challenging task because designing an effective and efficient appearance model is difficult. Current online tracking algorithms treat tracking as a classification task and use labelled samples to update appearance model. However, it is not clear to evaluate instance confidence belongs to the object. In this study, the authors propose a simple and efficient tracking algorithm with a deformable structure appearance. In their method, model updates with continuous labelled samples which are dense sampling. To improve the accuracy, they introduce a coupled-layer regression model which prevents negative background from impacting on the model learning rather than traditional classification. The proposed deformable structure regression tracker runs in real time and performs favourably against state-of-the-art trackers on various challenging sequences.

Inspec keywords: regression analysis; image classification; image sampling; object tracking; learning (artificial intelligence)

Other keywords: visual object tracking; fast deformable structure regression tracking; coupled-layer regression model; classification task; dense sampling; effective appearance model; model learning; efficient appearance model; negative background prevention

Subjects: Other topics in statistics; Computer vision and image processing techniques; Image recognition; Other topics in statistics; Knowledge engineering techniques

References

    1. 1)
    2. 2)
      • 8. Wu, Y., Lim, J., Yang, M.-H.: ‘Online object tracking: A benchmark’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2013.
    3. 3)
      • 10. Henriques, J.F., Caseiro, R., Martins, P., et al: ‘Exploiting the circulant structure of tracking-by-detection with kernels’. Computer Vision–ECCV 2012.Springer, 2012, pp. 702715.
    4. 4)
      • 2. Grabner, H., Grabner, M., Bischof, H.: ‘Real-time tracking via on-line boosting’. Proc. BMVC, vol. 1, 2006, p. 6.
    5. 5)
      • 26. Adam, A., Rivlin, E., Shimshoni, I.: ‘Robust fragments-based tracking using the integral histogram’. 2006 IEEE Computer Society Conf. on Proc. Computer Vision and Pattern Recognition, 2006, pp. 798805.
    6. 6)
    7. 7)
      • 5. Zhang, K., Zhang, L., Yang, M.-H.: ‘Real-time compressive tracking’. Computer Vision–ECCV 2012.Springer, 2012, pp. 864877.
    8. 8)
      • 25. Kalal, Z., Matas, J., Mikolajczyk, K.: ‘Pn learning: bootstrapping binary classifiers by structural constraints’. 2010 IEEE Conf. on Proc. Computer Vision and Pattern Recognition (CVPR), 2010, pp. 4956.
    9. 9)
      • 23. Jordan, A.: ‘On discriminative vs. generative classifiers: a comparison of logistic regression and naive Bayes’, Adv. Neural Inf. Process. Syst., 2002, 14, p. 841.
    10. 10)
    11. 11)
    12. 12)
      • 14. Zhu, L., Chen, Y., Yuille, A., et al: ‘Latent hierarchical structural learning for object detection’. 2010 IEEE Conf. on Proc. Computer Vision and Pattern Recognition (CVPR), 2010, pp. 10621069.
    13. 13)
      • 11. Zhang, K., Zhang, L., Yang, M.-H., et al: ‘Fast tracking via spatio-temporal context learning’, arXiv preprint arXiv:1311.1939, 2013.
    14. 14)
      • 27. Kwon, J., Lee, K.M.: ‘Visual tracking decomposition’. 2010 IEEE Conf. on Proc. Computer Vision and Pattern Recognition (CVPR), 2010, pp. 12691276.
    15. 15)
      • 18. Shoujue, W., Jiangliang, L.: ‘First step to multi-dimensional space biomimetic informatics M’ (National Defense Industry Press, Beijing, 2008).
    16. 16)
      • 9. Bolme, D.S., Beveridge, J.R., Draper, B.A., et al: ‘Visual object tracking using adaptive correlation filters’. 2010 IEEE Conf. on Proc. Computer Vision and Pattern Recognition (CVPR), 2010, pp. 25442550.
    17. 17)
    18. 18)
      • 15. Rublee, E., Rabaud, V., Konolige, K., et al: ‘ORB: an efficient alternative to SIFT or SURF’. 2011 IEEE Int. Conf. on Proc. Computer Vision (ICCV), 2011, pp. 25642571.
    19. 19)
      • 30. Zhang, L., van der Maaten, L.: ‘Structure preserving object tracking’. 2013 IEEE Conf. on IEEE Computer Vision and Pattern Recognition (CVPR), 2013, pp. 18381845.
    20. 20)
      • 22. Cehovin, L., Kristan, M., Leonardis, A.: ‘An adaptive coupled-layer visual model for robust visual tracking’. 2011 IEEE Int. Conf. on Proc. Computer Vision (ICCV), 2011, pp. 13631370.
    21. 21)
    22. 22)
    23. 23)
    24. 24)
      • 16. Leutenegger, S., Chli, M., Siegwart, R.Y.: ‘BRISK: Binary robust invariant scalable keypoints’. 2011 IEEE Int. Conf. on Proc. Computer Vision (ICCV), 2011, pp. 25482555.
    25. 25)
      • 28. Learned-Miller, E.G., Lara, L.S.: ‘Distribution fields for tracking’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2012.
    26. 26)
      • 7. Hare, S., Saffari, A., Torr, P.H.: ‘Struck: structured output tracking with kernels’. 2011 IEEE Int. Conf. on Proc. Computer Vision (ICCV), 2011, pp. 263270.
    27. 27)
      • 21. Duan, G., Huang, C., Ai, H., et al: ‘Boosting associated pairing comparison features for pedestrian detection’. 2009 IEEE 12th Int. Conf. on in Proc. Computer Vision Workshops (ICCV Workshops), 2009, pp. 10971104.
    28. 28)
      • 20. Chen, D., Cao, X., Wen, F., et al: ‘Blessing of dimensionality: High-dimensional feature and its efficient compression for face verificationIEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 30253032.
    29. 29)
    30. 30)
      • 13. Dean, T., Ruzon, M.A., Segal, M., et al: ‘Fast, accurate detection of 100,000 object classes on a single machine’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2013.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2014.0315
Loading

Related content

content/journals/10.1049/iet-cvi.2014.0315
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading