Motion Characterization of a Dynamic Scene

Arun Balajee Vasudevan, Srikanth Muralidharan, Shiva Pratheek Chintapalli, Shanmuganathan Raman

2014

Abstract

Given a video, there are many algorithms to separate static and dynamic objects present in the scene. The proposed work is focused on classifying the dynamic objects further as having either repetitive or non-repetitive motion. In this work, we propose a novel approach to achieve this challenging task by processing the optical flow fields corresponding to the video frames of a dynamic natural scene. We design an unsupervised learning algorithm which uses functions of the flow vectors to design the feature vector. The proposed algorithm is shown to be effective in classifying a scene into static, repetitive, and non-repetitive regions. The proposed approach finds significance in various vision and computational photography tasks such as video editing, video synopsis, and motion magnification.

References

  1. Black, M. J. and Anandan, P. (1996). The robust estimation of multiple motions: Parametric and piecewisesmooth flow fields. Computer Vision and Image Understanding, 63(1):75 - 104.
  2. Brox, T. and Malik, J. (2011). Large displacement optical flow: descriptor matching in variational motion estimation. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 33(3):500-513.
  3. den Bergh, M. V. and Gool, L. J. V. (2012). Real-time stereo and flow-based video segmentation with superpixels. In WACV, pages 89-96. IEEE.
  4. Derpanis, K. G. and Wildes, R. (2012). Spacetime texture representation and recognition based on a spatiotemporal orientation analysis. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 34(6):1193-1205.
  5. Horn, B. K. and Schunck, B. G. (1981). Determining optical flow. Artificial intelligence, 17(1):185-203.
  6. Lucas, B. D. and Kanade, T. (1981). An iterative image registration technique with an application to stereo vision (ijcai). In Proceedings of the 7th International Joint Conference on Artificial Intelligence (IJCAI 7881), pages 674-679.
  7. Ochs, P. and Brox, T. (2012). Higher order motion models and spectral clustering. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pages 614-621. IEEE.
  8. Peterson, B. (2010). Understanding Exposure: How to Shoot Great Photographs with Any Camera. Amphoto Books.
  9. Pritch, Y., Rav-Acha, A., and Peleg, S. (2008). Nonchronological video synopsis and indexing. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 30(11):1971-1984.
  10. Ren, X. and Malik, J. (2003). Learning a classification model for segmentation. In Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on, pages 10-17 vol.1.
  11. Stauffer, C. and Grimson, W. E. L. (1999). Adaptive background mixture models for real-time tracking. In Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., volume 2. IEEE.
  12. Wadhwa, N., Rubinstein, M., Durand, F., and Freeman, W. T. (2013). Phase-based video motion processing. ACM Trans. Graph. (Proceedings SIGGRAPH 2013), 32(4).
Download


Paper Citation


in Harvard Style

Vasudevan A., Muralidharan S., Chintapalli S. and Raman S. (2014). Motion Characterization of a Dynamic Scene . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-003-1, pages 702-707. DOI: 10.5220/0004852607020707


in Bibtex Style

@conference{visapp14,
author={Arun Balajee Vasudevan and Srikanth Muralidharan and Shiva Pratheek Chintapalli and Shanmuganathan Raman},
title={Motion Characterization of a Dynamic Scene},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={702-707},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004852607020707},
isbn={978-989-758-003-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2014)
TI - Motion Characterization of a Dynamic Scene
SN - 978-989-758-003-1
AU - Vasudevan A.
AU - Muralidharan S.
AU - Chintapalli S.
AU - Raman S.
PY - 2014
SP - 702
EP - 707
DO - 10.5220/0004852607020707