access icon free Robust visual tracking via online informative feature selection

© The Institution of Engineering and Technology
Received 24/05/2014, Published 01/12/2014

An efficient and effective algorithm which online exploits informative features for visual tracking is presented. First, a high-dimensional multi-scale spatio-colour image feature vector is developed, which takes into account both appearance and spatial layout information; secondly, this feature vector is randomly projected onto a low-dimensional feature space, where its projections preserve intrinsic information of the high-dimensional feature vector but effectively avoid the curse of dimensionality; and finally, an online feature selection technique to design an adaptive appearance model is proposed, which explores the most informative features from the projections via maximising entropy energy. Experiments on extensive challenging sequences demonstrate the superiority of the proposed method over some state-of-the-art algorithms.

Inspec keywords: feature selection; entropy; object tracking

Other keywords: high-dimensional multiscale spatio-colour image feature vector; online informative feature selection; low-dimensional feature space; adaptive appearance model; spatial layout information; entropy energy; robust visual tracking

Subjects: Image recognition; Computer vision and image processing techniques

References

    1. 1)
      • 3. Zhang, T., Ghanem, B., Liu, S., Ahuja, N.: ‘Robust visual tracking via multi-task sparse learning’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, June 2012, pp. 2042–2049.
    2. 2)
      • 1. Kwon, J., Lee, K.: ‘Visual tracking decomposition’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Florence, Italy, October 2010, pp. 1269–1276.
    3. 3)
    4. 4)
      • 11. Zhong, W., Lu, H., Yang, M.-H.: ‘Robust object tracking via sparsity based collaborative model’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, June 2012, pp. 1838–1845.
    5. 5)
    6. 6)
      • 3. Zhang, T., Ghanem, B., Liu, S., Ahuja, N.: ‘Robust visual tracking via multi-task sparse learning’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, June 2012, pp. 2042–2049.
    7. 7)
      • 6. Zhang, K., Zhang, L., Yang, M.-H.: ‘Fast compressive tracking’, IEEE Trans. Pattern Anal. Mach. Intell., 2014.
    8. 8)
      • 4. Zhang, K., Zhang, L., Yang, M.-H.: ‘Real-time compressive tracking’. European Conf. on Computer Vision (ECCV), Florence, Italy, October 2012, pp. 864–877.
    9. 9)
      • 9. Grabner, H., Grabner, M., Bischof, H.: ‘Real-time tracking via online boosting’. British Machine Vision Conf. (BMVC), Edinburgh, Scotland, September 2006, pp. 47–56.
    10. 10)
      • 7. Hare, S., Saffari, A., Torr, P.: ‘Struck: structured output tracking with kernels’. IEEE Int. Conf. on Computer Vision (ICCV), Barcelona, Spain, November 2011, pp. 263–270.
    11. 11)
      • 12. Jia, X., Lu, H., Yang, M.-H.: ‘Visual tracking via adaptive structural local sparse appearance model’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA, June 2012, pp. 1822–1829.
    12. 12)
      • 8. Kalal, Z., Matas, J., Mikolajczyk, K.: ‘Pn learning: bootstrapping binary classifiers by structural constraints’. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA, June 2010, pp. 49–56.
    13. 13)
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2014.1911
Loading

Related content

content/journals/10.1049/el.2014.1911
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading