Sparse Motion Segmentation using Propagation of Feature Labels

Pekka Sangi, Jari Hannuksela, Janne Heikkilä, Olli Silvén

Abstract

The paper considers the problem of extracting background and foreground motions from image sequences based on the estimated displacements of a small set of image blocks. As a novelty, the uncertainty of local motion estimates is analyzed and exploited in the fitting of parametric object motion models which is done within a competitive framework. Prediction of patch labels is based on the temporal propagation of labeling information from seed points in spatial proximity. Estimates of local displacements are then used to predict the object motions which provide a starting point for iterative refinement. Experiments with both synthesized and real image sequences show the potential of the approach as a tool for tracking based online motion segmentation.

References

  1. Fradet, M., Robert, P., and Pérez, P. (2009). Clustering point trajectories with various life-spans. In Proc. Conf. on Visual Media Production, pages 7-13.
  2. Hannuksela, J., Barnard, M., Sangi, P., and Heikkilä, J. (2011). Camera-based motion recognition for mobile interaction. ISRN Signal Processing, Art. Id 425621.
  3. Kalal, Z., Mikolajczyk, K., and Matas, J. (2010). Forwardbackward error: automatic detection of tracking failures. In Proc. Int. Conf. on Pattern Recognition, pages 2756-2759.
  4. Karavasilis, V., Blekas, K., and Nikou, C. (2011). Motion segmentation by model-based clustering of incomplete trajectories. In ECML PKDD, volume 6912 of LNAI, pages 146-161. Springer-Verlag.
  5. Lim, T., Han, B., and Han, J. H. (2012). Modeling and segmentation of floating foreground and background in videos. Pattern Recognition, 45(4):1696 - 1706.
  6. Nickels, K. and Hutchinson, S. (2001). Estimating uncertainty in SSD-based feature tracking. Image and Vision Computing, 20:47-58.
  7. Odobez, J. and Bouthemy, P. (1995a). Robust multiresolution estimation of parametric motion models. J. Visual. Comm. Image Repr., 6(4):348-365.
  8. Odobez, J.-M. and Bouthemy, P. (1995b). Direct modelbased image motion segmentation for dynamic scene analysis. In Proc. Asian Conf. on Computer Vision, pages 306-310.
  9. Pundlik, S. J. and Birchfield, S. (2008). Real-time motion segmentation of sparse feature points at any speed. IEEE Trans. SMC-B, 38(3):731-742.
  10. Sangi, P., Hannuksela, J., and Heikkilä, J. (2007). Global motion estimation using block matching with uncertainty analysis. In Proc. European Signal Processing Conf., pages 1823-1827.
  11. Tao, H., Sawhney, H. S., and Kumar, R. (2002). Object tracking with Bayesian estimation of dynamic layer representations. IEEE Trans. PAMI, 24(1):75-89.
  12. Tekalp, A. M. (2000). Video segmentation. In Bovik, A., editor, Handbook of Image & Video Processing, chapter 4.9. Academic Press, San Diego.
  13. Tsai, D., Flagg, M., and Rehg, J. M. (2010). Motion coherent tracking with multi-label MRF optimization. In Proc. British Machine Vision Conf.
  14. Wills, J., Agarwal, S., and Belongie, S. (2003). What went where. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, volume 1, pages 37-45.
  15. Wong, K. Y. and Spetsakis, M. E. (2004). Motion segmentation by EM clustering of good features. In Proc. CVPR Workshop, pages 166-173.
  16. Zappella, L., Lladó, X., and Salvi, J. (2009). New trends in motion segmentation. In Yin, P.-Y., editor, Pattern Recognition, pages 31-46. INTECH.
Download


Paper Citation


in Harvard Style

Sangi P., Hannuksela J., Heikkilä J. and Silvén O. (2013). Sparse Motion Segmentation using Propagation of Feature Labels . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-48-8, pages 396-401. DOI: 10.5220/0004281203960401


in Bibtex Style

@conference{visapp13,
author={Pekka Sangi and Jari Hannuksela and Janne Heikkilä and Olli Silvén},
title={Sparse Motion Segmentation using Propagation of Feature Labels},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={396-401},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004281203960401},
isbn={978-989-8565-48-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)
TI - Sparse Motion Segmentation using Propagation of Feature Labels
SN - 978-989-8565-48-8
AU - Sangi P.
AU - Hannuksela J.
AU - Heikkilä J.
AU - Silvén O.
PY - 2013
SP - 396
EP - 401
DO - 10.5220/0004281203960401