INCREMENTAL LEARNING AND VALIDATION OF SEQUENTIAL PREDICTORS IN VIDEO BROWSING APPLICATION

David Hurych, Tomáš Svoboda

2010

Abstract

Loss-of-track detection (tracking validation) and automatic tracker adaptation to new object appearances are attractive topics in computer vision. We apply very efficient learnable sequential predictors in order to address both issues. Validation is done by clustering of the sequential predictor responses. No aditional object model for validation is needed. The paper also proposes an incremental learning procedure that accommodates changing object appearance, which mainly improves the recall of the tracker/detector. Exemplars for the incremental learning are collected automatically, no user interaction is required. The aditional training examples are selected automatically using the tracker stability computed for each potential aditional training example. Coupled with a sparsely applied SIFT or SURF based detector the method is employed for object localization in videos. Our Matlab implementation scans videosequences up to eight times faster than the actual frame rate. A standard-length movie can be thus searched through in terms of minutes.

References

  1. Bay, H., Ess, A., Tuytelaars, T., and Van Gool, L. (2006). Speeded-up robust features. In Proceedings of IEEE European Conference on Computer Vision, pages 404-417.
  2. Ellis, L., Matas, J., and Bowden, R. (2008). On-line learning and partitioning of linear displacement predictors for tracking. In Proceedings of the 19th British Machine Vision Conference, pages 33-42.
  3. Hinterstoisser, S., Benhimane, S., Navab, N., Fua, P., and Lepetit, V. (2008). Online learning of patch perspective rectification for efficient object detection. In Conference on Computer Vision and Pattern Recognition, pages 1-8.
  4. Jepson, A., Fleet, D., and El-Maraghi, T. (2008). Robust online appearance models for visual tracking. In IEEE Conference on Computer Vision and Pattern Recognition, volume 1, pages 415-422.
  5. Lowe, D. (2004). Distinctive image features from scaleinvariant keypoints. International Journal on Computer Vision, 60(2):91-110.
  6. Matthews, I., Ishikawa, T., and Baker, S. (2004). The template update problem. IEEE transactions on pattern analysis and machine intelligence, 26(6):810-815.
  7. Murphy-Chutorian, E. and Trivedi, M. (2009). Head pose estimation in computer vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(4):607-626.
  8. Ross, D., Lim, J., Lin, R., and Yang, M. (2008). Incremental learning for robust visual tracking. International Journal of Computer Vision, 77(1-3):125-141.
  9. Shi, J. and Tomasi, C. (1994). Good features to track. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 593-600.
  10. Sivic, J. and Zisserman, A. (2009). Efficient Visual Search of Videos Cast as Text Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(4):591-606.
  11. Yilmaz, A., Javed, O., and Shah, M. (2006). Object tracking: A survey. ACM Computing Surveys (CSUR), 38(4):13-36.
  12. Zimmermann, K., Svoboda, T., and Matas, J. (2009). Anytime learning for the NoSLLiP tracker. Image and Vision Computing, Special Issue: Perception Action Learning, 27(11):1695-1701.
Download


Paper Citation


in Harvard Style

Hurych D. and Svoboda T. (2010). INCREMENTAL LEARNING AND VALIDATION OF SEQUENTIAL PREDICTORS IN VIDEO BROWSING APPLICATION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-028-3, pages 467-474. DOI: 10.5220/0002836504670474


in Bibtex Style

@conference{visapp10,
author={David Hurych and Tomáš Svoboda},
title={INCREMENTAL LEARNING AND VALIDATION OF SEQUENTIAL PREDICTORS IN VIDEO BROWSING APPLICATION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={467-474},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002836504670474},
isbn={978-989-674-028-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)
TI - INCREMENTAL LEARNING AND VALIDATION OF SEQUENTIAL PREDICTORS IN VIDEO BROWSING APPLICATION
SN - 978-989-674-028-3
AU - Hurych D.
AU - Svoboda T.
PY - 2010
SP - 467
EP - 474
DO - 10.5220/0002836504670474