Video Segmentation by Event Detection: A Novel One-class Classification Approach

Mahesh Venkata Krishna, Paul Bodesheim, Joachim Denzler

Abstract

Segmenting videos into meaningful image sequences of some particular activities is an interesting problem in computer vision. In this paper, a novel algorithm is presented to achieve this semantic video segmentation. The goal is to make the system work unsupervised and generic in terms of application scenarios. The segmentation task is accomplished through event detection in a frame-by-frame processing setup. For event detection, we use a one-class classification approach based on Gaussian processes, which has been proved to be successful in object classification. The algorithm is tested on videos from a publicly available change detection database and the results clearly show the suitability of our approach for the task of video segmentation.

References

  1. Bosch, A., Zisserman, A., and Munoz, X. (2007). Representing shape with a spatial pyramid kernel. In Proceedings of the 6th ACM international conference on Image and video retrieval (CIVR'07), pages 401-408, New York, NY, USA. ACM.
  2. Goyette, N., Jodoin, P.-M., Porikli, F., Konrad, J., and Ishwar, P. (2012). changedetection.net: A new change detection benchmark dataset. In Proceedings of the IEEE Workshop on Change Detection (CDW'12) at CVPR'12.
  3. Kemmler, M., Rodner, E., and Denzler, J. (2010). One-class classification with gaussian processes. In Proceedings of the Asian Conference on Computer Vision (ACCV'10), pages 489-500.
  4. Koprinska, I. and Carrato, S. (2001). Temporal video segmentation: A survey. Signal Processing: Image Communication, 16(5):477 - 500.
  5. Liu, T., Zhang, H.-J., and Qi, F. (2003). A novel video key-frame-extraction algorithm based on perceived motion energy model. IEEE Transactions on Circuits and Systems for Video Technology, 13(10):1006 - 1013.
  6. Parzen, E. (1962). On estimation of a probability density function and mode. The annals of mathematical statistics, 33(3):1065-1076.
  7. Rasmussen, C. E. and Williams, C. K. I. (2006). Gaussian Processes for Machine Learning. The MIT Press.
  8. Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., and Williamson, R. C. (2001). Estimating the support of a high-dimensional distribution. Neural Computation, 13(7):1443- 1471.
  9. Tax, D. M. J. and Duin, R. P. W. (2004). Support vector data description. Machine Learning, 54(1):45-66.
Download


Paper Citation


in Harvard Style

Venkata Krishna M., Bodesheim P. and Denzler J. (2013). Video Segmentation by Event Detection: A Novel One-class Classification Approach . In Proceedings of the 4th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-4, (VISIGRAPP 2013) ISBN 978-989-8565-50-1, pages 73-81. DOI: 10.5220/0004394100730081


in Bibtex Style

@conference{imta-413,
author={Mahesh Venkata Krishna and Paul Bodesheim and Joachim Denzler},
title={Video Segmentation by Event Detection: A Novel One-class Classification Approach},
booktitle={Proceedings of the 4th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-4, (VISIGRAPP 2013)},
year={2013},
pages={73-81},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004394100730081},
isbn={978-989-8565-50-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-4, (VISIGRAPP 2013)
TI - Video Segmentation by Event Detection: A Novel One-class Classification Approach
SN - 978-989-8565-50-1
AU - Venkata Krishna M.
AU - Bodesheim P.
AU - Denzler J.
PY - 2013
SP - 73
EP - 81
DO - 10.5220/0004394100730081