Probabilistic Background Modelling for Sports Video Segmentation

Nikolas Ladas, Paris Kaimakis, Yiorgos Chrysanthou

2017

Abstract

This paper introduces a segmentation algorithm based on the probabilistic modelling of the background color using a Lambertian formulation of the scene’s appearance. Central in our formulation is the computation of the degree of light visibility at the scene location depicted by each pixel. Because our approach specifically models the formation of shadows, segmentation results are of high accuracy. The quality of our results is further boosted by utilizing key observations about scene appearance. A qualitative and quantitative evaluation indicates that the proposed method performs better than commonly used segmentation algorithms, both for sports as well as for generic datasets.

References

  1. Barnich, O. and Van Droogenbroeck, M. (2011). ViBe: A universal background subtraction algorithm for video sequences. IEEE Transactions on Image Processing, 20(6):1709-1724.
  2. Chen, C.-C. and Aggarwal, J. (2010). Human Shadow Removal with Unknown Light Source. In 20th International Conference on Pattern Recognition, volume 27, pages 2407-2410, Istanbul, Turkey.
  3. Duncan, K. and Sarkar, S. (2012). Saliency in images and video: a brief survey. IET Computer Vision, 6(6):514- 523.
  4. Godbehere, A. B. and Goldberg, K. (2014). Algorithms for Visual Tracking of Visitors Under Variable-Lighting Conditions for a Responsive Audio Art Installation. In Controls and Art, pages 181-204. Springer International Publishing, Cham.
  5. Graham, T. (2012). Sports tv applications of computer vision. BBC Research & Development White Paper WHP220.
  6. Hsieh, J.-W., Hu, W.-F., Chang, C.-J., and Chen, Y.- S. (2003). Shadow elimination for effective moving object detection by Gaussian shadow modeling. Image and Vision Computing, 21(6):505-516.
  7. Huerta, I., Amato, A., Roca, X., and González, J. (2013). Exploiting multiple cues in motion segmentation based on background subtraction. Neurocomputing, 100:183-196.
  8. Kaimakis, P. and Tsapatsoulis, N. (2013). Background Modeling Methods for Visual Detection of Maritime Targets. In In Proc. Int. Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream, pages 67-76, Barcelona, Spain.
  9. Khan, S. H., Bennamoun, M., Sohel, F., and Togneri, R. (2014). Automatic Feature Learning for Robust Shadow Detection. In Proc. Conf. Comp. Vision and Pattern Recognition, pages 1939-1946, Columbus, Ohio, USA.
  10. Leone, A. and Distante, C. (2007). Shadow detection for moving objects based on texture analysis. Pattern Recognition, 40(4):1222-1233.
  11. Levin, A., Lischinski, D., and Weiss, Y. (2008). A ClosedForm Solution to Natural Image Matting. Trans. Pattern Analysis and Machine Intelligence, 30(2):228- 242.
  12. Maddalena, L. and Petrosino, A. (2015). Towards Benchmarking Scene Background Initialization. In Proc Int. Conf. Image Analysis and Processing, volume 9281, pages 469-476.
  13. Perazzi, F., Krahenbuhl, P., Pritch, Y., and Hornung, A. (2012). Saliency filters: Contrast based filtering for salient region detection. In Proc. Conf. Comp. Vision and Pattern Recognition, pages 733-740.
  14. Pettersen, S. A., Halvorsen, P., Johansen, D., Johansen, H., Berg-Johansen, V., Gaddam, V. R., Mortensen, A., Langseth, R., Griwodz, C., and Stensland, H. K. (2014). Soccer video and player position dataset. In Proc. Multimedia Systems Conf., pages 18-23, New York, USA.
  15. Rijsbergen, C. J. V. (1979). Information Retrieval. Butterworth-Heinemann, Newton, MA, USA, 2nd edition.
  16. Sanin, A., Sanderson, C., and Lovell, B. C. (2010). Improved Shadow Removal for Robust Person Tracking in Surveillance Scenarios. In Proc. Int. Conf. on Pattern Recognition, pages 141-144.
  17. Sanin, A., Sanderson, C., and Lovell, B. C. (2012). Shadow detection: A survey and comparative evaluation of recent methods. Pattern Recognition, 45(4):1684-1695.
  18. Shahrian, E., Rajan, D., Price, B., and Cohen, S. (2013). Improving Image Matting Using Comprehensive Sampling Sets. In Proc. Conf. Computer Vision and Pattern Recognition, pages 636-643.
  19. Stone, J. E., Gohara, D., and Shi, G. (2010). OpenCL: A parallel programming standard for heterogeneous computing systems. Computing in Science & Engineering, 12(3):66-73.
  20. Wang, J. and Cohen, M. F. (2007). Image and Video Matting: A Survey. Foundations and Trends in Computer Graphics and Vision, 3(2):97-175.
  21. Yan, Q., Xu, L., Shi, J., and Jia, J. (2013). Hierarchical saliency detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1155-1162.
  22. Zivkovic, Z. (2004). Improved adaptive Gaussian mixture model for background subtraction. In Proc. 17th International Conf. on Pattern Recognition, volume 2, pages 28-31 Vol.2, Washington, DC, USA.
Download


Paper Citation


in Harvard Style

Ladas N., Kaimakis P. and Chrysanthou Y. (2017). Probabilistic Background Modelling for Sports Video Segmentation . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-225-7, pages 517-525. DOI: 10.5220/0006135505170525


in Bibtex Style

@conference{visapp17,
author={Nikolas Ladas and Paris Kaimakis and Yiorgos Chrysanthou},
title={Probabilistic Background Modelling for Sports Video Segmentation},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={517-525},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006135505170525},
isbn={978-989-758-225-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)
TI - Probabilistic Background Modelling for Sports Video Segmentation
SN - 978-989-758-225-7
AU - Ladas N.
AU - Kaimakis P.
AU - Chrysanthou Y.
PY - 2017
SP - 517
EP - 525
DO - 10.5220/0006135505170525