UNSUPERVISED ALGORITHMS FOR SEGMENTATION AND CLUSTERING APPLIED TO SOCCER PLAYERS CLASSIFICATION

P. Spagnolo, P. L. Mazzeo, M. Leo, T. D’Orazio

2007

Abstract

In this work we consider the problem of soccer player detection and classification. The approach we propose starts from the monocular images acquired by a still camera. Firstly, players are detected by means of background subtraction. An algorithm based on pixels energy content has been implemented in order to detect moving objects. The use of energy information, combined with a temporal sliding window procedure, allows to be substantially independent from motion hypothesis. Then players are assigned to the correspondent team by means of an unsupervised clustering algorithm that works on colour histograms in RGB space. It is composed by two distinct modules: firstly, a modified version of the BSAS clustering algorithm builds the clusters for each class of objects. Then, at runtime, each player is classified by evaluating its distance, in the features space, from the classes previously detected. Algorithms have been tested on different real soccer match of the Italian Serie A.

References

  1. Assfalg, J., Bestini, M., Colombo, C., Del Bimbo, A., Nunziati, W. , 2003. Semantic annotation of soccer videos: automatic highlights identification, in CVIU 92(2) pp. 285-305.
  2. Zhang, Di, Chang, S.F., 2004. Real-time view recognition and event detection for sports video, in J. Vis. Commun. Image r. 15, pp. 330-347.
  3. LeXing Xie, Peng Xu, Shih-Fu Chang, Divakaran, A., 2004. Structure analysis of soccer video with domain knowledge and Hidden Markov Models, in Patt. Rec. Lett. 25 pp. 767-75.
  4. Ekin, A., Tekalp, A.M., Mehrotra, R., 2003. Automatic soccer video analysis and summarization, in IEEE Trans. on Image Processing, 12(7), pp 796-807
  5. Kanade, T., Collins, T., Lipton, A., 1998. Advances in Cooperative Multi-Sensor Video Surveillance, in Darpa Image Und. Work., Morgan Kaufmann,pp.3-24.
  6. Toyama, K., Krumm, J., Brumitt, B., Meyers, B., 1999. Wallflower: Principles and practice of background maintenance, in ICCV, pp. 255-261
  7. Theodoridis, S., Koutroumbas, K., 2003. Pattern Recognition, Academic Press, San Diego, ISBN 0-12- 686140-4.
  8. Naemura, M., Fukuda, A., Mizutani, Y., Izumi, Y., Tanaka, Y., Enami, K., 2000. Morphological Segmentation of Sport Scenes using Color Information, in IEEE Tr. on Br.,46(3) pp.181-8.
  9. Misu, T., Gohshi, S., Izumi, Y., Fujita, Y., Naemura, M., 2004. Robust tracking of athletes using multiple features of multiple views, Journ. of WSCG, vol.12, 1-3
  10. Xu, M., Orwell, J., Lowey, L., Thirde, D., 2005. Architecture and algorithms for tracking football players with multiple cameras, in IEE Proc. Vis. Im. and Sign. Proc,152 (2) pp.232-41.
  11. Xu, Z., Shi, P., 2005. Segmentation of players and team discrimination in soccer videos, in IEEE int. Work. VLSI Design & Video Tech., May 28-30, Suzhou, China.
  12. Mathes, T., Piater, J., 2005. Robust Non-rigid Object tracking using Point Distribution Models, in BMVC
  13. Vandenbroucke, N., Macaire, L., Postaire, J.G., 2003. Color image segmentation by pixel classification in an adapted hybrid color space. Application to soccer image analysis, CVIU(90), 2, pp. 190-216.
  14. Ekin, A., Tekalp, A.M., 2003. Robust dominant color region detection and color-based applications for sports video, in ICIP (1), pp. 21-24.
  15. Yu, X., Sen Hay, T., Yan, X., Chng, E., 2005. A PlayerPossession Acquisition System for Broadcast Soccer Video, in ICME July, 6-8, Singapore, pp. 522-525.
  16. Beetz, M., Bandouch, J., Gedikli, S., 2006. Camera-based Observation of Football Games for Analyzing Multiagent Activities, in Proc. of AAMAS, pp. 42-49.
Download


Paper Citation


in Harvard Style

Spagnolo P., L. Mazzeo P., Leo M. and D’Orazio T. (2007). UNSUPERVISED ALGORITHMS FOR SEGMENTATION AND CLUSTERING APPLIED TO SOCCER PLAYERS CLASSIFICATION . In Proceedings of the Second International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2007) ISBN 978-989-8111-13-5, pages 129-134. DOI: 10.5220/0002139501290134


in Bibtex Style

@conference{sigmap07,
author={P. Spagnolo and P. L. Mazzeo and M. Leo and T. D’Orazio},
title={UNSUPERVISED ALGORITHMS FOR SEGMENTATION AND CLUSTERING APPLIED TO SOCCER PLAYERS CLASSIFICATION},
booktitle={Proceedings of the Second International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2007)},
year={2007},
pages={129-134},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002139501290134},
isbn={978-989-8111-13-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2007)
TI - UNSUPERVISED ALGORITHMS FOR SEGMENTATION AND CLUSTERING APPLIED TO SOCCER PLAYERS CLASSIFICATION
SN - 978-989-8111-13-5
AU - Spagnolo P.
AU - L. Mazzeo P.
AU - Leo M.
AU - D’Orazio T.
PY - 2007
SP - 129
EP - 134
DO - 10.5220/0002139501290134