FUSION OF MOTION SEGMENTATION WITH ONLINE ADAPTIVE NEURAL CLASSIFIER FOR ROBUST TRACKING

Sławomir Bąk, Sundaram Suresh, François Brémond, Monique Thonnat

2009

Abstract

This paper presents a method to fuse the information from motion segmentation with online adaptive neural classifier for robust object tracking. The motion segmentation with object classification identify new objects present in the video sequence. This information is used to initialize the online adaptive neural classifier which is learned to differentiate the object from its local background. The neural classifier can adapt to illumination variations and changes in appearance. Initialized objects are tracked in following frames using the fusion of their neural classifiers with the feedback from the motion segmentation. Fusion is used to avoid drifting problems due to similar appearance in the local background region. We demonstrate the approach in several experiments using benchmark video sequences with different level of complexity.

References

  1. Avidan, S. (2007). Ensemble tracking. IEEE Trans. Pattern Anal. Machine Intell., 29(2):261-271.
  2. Ba?k, S., Suresh, S., Bremond, F., and Thonnat, M. (2008). Fusion of motion segmentation and learning based tracker for visual surveillance. In Internal report: INRIA Sophia Antipolis, http://wwwsop.inria.fr/pulsar/personnel/Francois.Bremond/topicsText/ neuralProject.html, volume 1, pages 1-10.
  3. Collins, R. T., Liu, Y., and Leordeanu, M. (2005). Online selection of discriminative tracking features. IEEE Trans. Pattern Anal. Machine Intell., 27(10):1631- 1643.
  4. Cootes, T., Edwards, G., and Taylor, C. (2001). Active appearance models. IEEE Trans. Pattern Anal. Machine Intell., 25(5):681-685.
  5. Jepson, A. D., Fleet, D. J., and El-Maraghi, T. (2003). Robust online appearance model for visual tracking. IEEE Trans. Pattern Anal. Machine Intell., 25(10):1296-1311.
  6. Nummiaro, K., Koller-Meier, E., and Van Gool, L. (2003). An adaptive color-based particle filter. Image Vision Computing, 21(1):99-110.
  7. Stauffer, C. and Brady, J. (2000). Learning patterns of activity using real-time tracking. IEEE Trans. Pattern Anal. Machine Intell., 22(8):747-757.
  8. Suresh, S., Sundararajan, N., and Saratchandran, P. (2008a). Risk sensitive loss functions for sparse multicategory classification problems. Information Sciences, 178(12):2621-2638.
  9. Suresh, S., Sundararajan, N., and Saratchandran, P. (2008b). A sequential multi-category classifier using radial basis function networks. Neurocomputing, 71(7- 9):1345-1358.
  10. Williams, O., Blake, A., and Cipolla, R. (2005). Sparse bayesian learning for efficient visual tracking. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 27(8):1292-1304.
  11. Yilmaz, A., Javed, O., and Shah, M. (2006). Object tracking: A survey. ACM Computing Surveys, 38(4):1-45.
  12. Zouba, N., Boulay, B., Bre mond, F., and Thonnat, M. (2008). Monitoring activities of daily living (adls) of elderly based on 3d key human postures. In Proc. of International Cognitive Vision Workshop, pages xxxx, Greece.
  13. Zún˜iga, M., Brémond, F., and M.Thonnat (2006). Fast and reliable object classification in video based on a 3d generic model. In Proceedings of the International Conference on Visual Information Engineering (VIE2006), pages 433-440, Bangalore, India.
Download


Paper Citation


in Harvard Style

Bąk S., Suresh S., Brémond F. and Thonnat M. (2009). FUSION OF MOTION SEGMENTATION WITH ONLINE ADAPTIVE NEURAL CLASSIFIER FOR ROBUST TRACKING . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 410-416. DOI: 10.5220/0001769604100416


in Bibtex Style

@conference{visapp09,
author={Sławomir Bąk and Sundaram Suresh and François Brémond and Monique Thonnat},
title={FUSION OF MOTION SEGMENTATION WITH ONLINE ADAPTIVE NEURAL CLASSIFIER FOR ROBUST TRACKING},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={410-416},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001769604100416},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)
TI - FUSION OF MOTION SEGMENTATION WITH ONLINE ADAPTIVE NEURAL CLASSIFIER FOR ROBUST TRACKING
SN - 978-989-8111-69-2
AU - Bąk S.
AU - Suresh S.
AU - Brémond F.
AU - Thonnat M.
PY - 2009
SP - 410
EP - 416
DO - 10.5220/0001769604100416