Video Segmentation based on Multi-kernel Learning and Feature Relevance Analysis for Object Classification

S. Molina-Giraldo, J. Carvajal-González, A. M. Álvarez-Meza, G. Castellanos-Domínguez

2013

Abstract

A methodology to automatically detect moving objects in a scene using static cameras is proposed. Using Multiple Kernel Representations, we aim to incorporate multiple information sources in the process, and employing a relevance analysis, each source is automatically weighted. A tuned Kmeans technique is employed to group pixels as static or moving objects. Moreover, the proposed methodology is tested for the classification of abbandoned objects. Attained results over real-world datasets, show how our approach is stable using the same parameters for all experiments.

References

  1. Chen, T.-W., Hsu, S.-C., and Chien, S.-Y. (2007). Robust video object segmentation based on k-means background clustering and watershed in ill-conditioned surveillance systems. In Multimedia and Expo, 2007 IEEE International Conference on, pages 787 -790.
  2. Cuesta-Frau, D., Pérez-Cortés, J., and Andreu-Garcia, G. (2003). Clustering of electrocardiograph signals in computer-aided holter analysis. Computer methods and programs in Biomedicine, 72(3):179-196.
  3. Daza-Santacoloma, G., Arias-Londoo, J. D., GodinoLlorente, J. I., Senz-Lechn, N., Osma-Ruz, V., and Castellanos-Domnguez, G. (2009). Dynamic feature extraction: An application to voice pathology detection. Intelligent Automation and Soft Computing.
  4. Elgammal, A., Duraiswami, R., Harwood, D., and Davis, L. (2002). Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proceedings of the IEEE, 90(7):1151- 1163.
  5. Gonen, M. and Alpaydin, E. (2010). Localized multiple kernel regression. In Proceedings of the 20th International Conference on Pattern Recognition (ICPR).
  6. González, J. C., Í lvarez-Meza, A., and CastellanosDomínguez, G. (2012). Feature selection by relevance analysis for abandoned object classification. In CIARP, pages 837-844.
  7. Gutchess, D., Trajkovics, M., Cohen-Solal, E., Lyons, D., and Jain, A. (2001). A background model initialization algorithm for video surveillance. In Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on, volume 1, pages 733- 740. IEEE.
  8. Klare, B. and Sarkar, S. (2009). Background subtraction in varying illuminations using an ensemble based on an enlarged feature set. In Computer Vision and Pattern Recognition Workshops, 2009. CVPR Workshops 2009. IEEE Computer Society Conference on, pages 66 -73.
  9. Maddalena, L. and Petrosino, A. (2008). A self-organizing approach to background subtraction for visual surveillance applications. Image Processing, IEEE Transactions on, 17(7):1168-1177.
  10. Rakotomamonjy, A., Bach, F. R., Canu, S., and Grandvalet, Y. (2008). SimpleMKL. Journal of Machine Learning Research, 9:2491-2521.
  11. Raty, T. (2010). Survey on contemporary remote surveillance systems for public safety. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, 40(5):493-515.
Download


Paper Citation


in Harvard Style

Molina-Giraldo S., Carvajal-González J., M. Álvarez-Meza A. and Castellanos-Domínguez G. (2013). Video Segmentation based on Multi-kernel Learning and Feature Relevance Analysis for Object Classification . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 396-401. DOI: 10.5220/0004269403960401


in Bibtex Style

@conference{icpram13,
author={S. Molina-Giraldo and J. Carvajal-González and A. M. Álvarez-Meza and G. Castellanos-Domínguez},
title={Video Segmentation based on Multi-kernel Learning and Feature Relevance Analysis for Object Classification},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={396-401},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004269403960401},
isbn={978-989-8565-41-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Video Segmentation based on Multi-kernel Learning and Feature Relevance Analysis for Object Classification
SN - 978-989-8565-41-9
AU - Molina-Giraldo S.
AU - Carvajal-González J.
AU - M. Álvarez-Meza A.
AU - Castellanos-Domínguez G.
PY - 2013
SP - 396
EP - 401
DO - 10.5220/0004269403960401