DYNAMIC WEIGHTING BASED ACTIVE CURVE PROPAGATION METHOD FOR VIDEO OBJECT SELECTION

Marwen Nouri, Emmanuel Marilly, Olivier Martinot, Nicole Vincent

2012

Abstract

Improving video user experience is an essential task allowing video based algorithms and systems to be more user-friendly. This paper addresses the problem of video object selection by introducing a new interactive framework based on the minimization of the Active Curve energy. Prior assumption and supervised learning can be used to segment images using both color and morphological information. To deal with the segmentation of arbitrary high level object, user interaction is needed to avoid the semantic gap. Hard constraints such scribbles can be drown by user on the first video frame, to roughly mark the object of interest, and there are then automatically propagated to designate the same object in the remainder of the sequence. The resulting scribbles can be used as hard constraints to achieve the whole segmentation process. The active curve model is adapted and new forces are included to govern the curves evolution frame by frame. A spatiotemporal optimization is used to ensure a coherent propagation. To avoid weight definition problem, as in classical active curve based algorithms, a new concept of dynamically adjusted weighting is introduced in order to improve the robustness of our curve propagation.

References

  1. Bai, X. and Sapiro, G., 2007. A geodesic framework for fast interactive image and video segmentation and matting. In Proc.of IEEE ICCV.
  2. Bai, X., Wang, J. Simons, D. and Sapiro, G., 2009.Video snapcut: Robust video object cutout using localized classifiers. In SIGGRAPH 2009, New York, NY, USA, ACM.
  3. Baker, S. and Matthews, I., 2004. Lucas-Kanade 20 years on: A unifying framework. IJCV, 56(3):221-255.
  4. Boykov, Y., Veksler, O., and Zabih, R. 2001. Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Analysis and Machine Intelligence 23, 11, 1222-1239.
  5. Chuang, Y.-Y., Curless, B., Salesin, D. H., and Szeliski, R., 2001. “A bayesian approach to digital matting,” in Proceedings of IEEE CVPR, pp. 264-271.
  6. Etyngier, P., Segonne, F., and Keriven, R., 2007. Active contour based image segmentation using machine learning techniques. in MICCAI, ser. Lecture Notes in Computer Science, vol. 4791. Springer, pp.891-899.
  7. Joshi, N., Matusik, W., and Avidan, S., 2006. “Natural video matting using camera arrays,” in Proc. of ACM SIGGRAPH, pp. 779-786, 2006.
  8. Kass, M. Witkin, A. and Terzopoulos, D. 1987. Snakes: Active contour models. IJCV, 1(4):321-331.
  9. Lefevre, S. and Vincent, N., 2004. Real time multiple object tracking based on active contours. In International Conference on Image Analysis and Recognition, volume 3212 of Lecture Notes in Computer Sciences, Springer, pages 606-613.
  10. Levin, A., Lischinski, D. and Weiss, Y., 2008. A closedform solution to natural image matting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(2):228-242.
  11. McGuire, M., Matusik, W., Pfister, W., Hughes, J. F. and Durand, F., 2005, “Defocus video matting,” in Proceedings of ACM SIGGRAPH, pp. 567-576.
  12. Shi, J., Tomasi, C., 1994. Good features to track. Proceedings of the IEEE CVPR. p. 593-600.
  13. Wang J., Bhat, P., Colburn, R. A., Agrawala, M., Cohen, M., 2005. Interactive video cutout. SIGGRAPH'05, 24(3):585-594.
  14. Wang, J. and Cohen, M., 2005. “An iterative optimization approach for unified image segmentation and matting,” in Proceedings of ICCV, pp. 936-943.
  15. Wang, J. and Cohen, M., 2007. Image and video matting: A survey. Foundations and Trends. In Computer Graphics and Vision 3, 2, 97-175.
  16. Williams, D. J. and Shah. M., 1992 A Fast Algorithm for Active Contours and Curvature Estimation, VIGP Computer Vision Graphics Image Process Image Understanding, vol. 55, n° 1, p. 14-26.
Download


Paper Citation


in Harvard Style

Nouri M., Marilly E., Martinot O. and Vincent N. (2012). DYNAMIC WEIGHTING BASED ACTIVE CURVE PROPAGATION METHOD FOR VIDEO OBJECT SELECTION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 5-11. DOI: 10.5220/0003818500050011


in Bibtex Style

@conference{visapp12,
author={Marwen Nouri and Emmanuel Marilly and Olivier Martinot and Nicole Vincent},
title={DYNAMIC WEIGHTING BASED ACTIVE CURVE PROPAGATION METHOD FOR VIDEO OBJECT SELECTION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={5-11},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003818500050011},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - DYNAMIC WEIGHTING BASED ACTIVE CURVE PROPAGATION METHOD FOR VIDEO OBJECT SELECTION
SN - 978-989-8565-03-7
AU - Nouri M.
AU - Marilly E.
AU - Martinot O.
AU - Vincent N.
PY - 2012
SP - 5
EP - 11
DO - 10.5220/0003818500050011