Unsupervised Camera Motion Estimation and Moving Object Detection in Videos
Keywords:
estimation, object detection, parameterAbstract
In this article, we consider the robust estimation of a location parameter using M-estimators. We propose coupling this estimation with the robust scale estimate introduced in [Dahyot and Wilson, 2006]. The resulting procedure is completely unsupervised. It is applied to camera motion estimation and moving object detection in videos. Experimental results on different video materials demonstrate the adaptability and the accuracy of this new robust approach.
References
A. C. Kokaram, R. Dahyot, F. Pitie, and H. Denman, "Simultaneous luminance and position stabilization for film and video," in Visual Communications and Image Processing, pp. 688-699, San Jose, California, USA, 2003.
B. Aiazzi, L. Alparone, and S. Baronti, "Estimation based on entropy matching for generalized Gaussian PDF modeling," IEEE Signal Processing Letters, vol. 6, no. 6, pp. 138-140, 1999.
D. Hasler, L. Sbaiz, S. Susstrunk, and M. Vetterli, "Outlier modeling in image matching," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 3, pp. 301-315, 2003.
F. Coldefy, P. Bouthemy, M. Betser, and G. Gravier, "Tennis video abstraction from audio and visual cues," in Proceedings IEEE Workshop on Multimedia Signal Processing, MMSP'2004, pp. 163-166, Siena, Italy, 2004.
H. Chen and P. Meer, "Robust regression with projection based M-estimators," in International Conference on Computer Vision, pp. 878-885, Nice, France, 2003.
M. A. Fischler and R. C. Bolles, "Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography," Commun. ACM, vol. 24, no. 6, pp. 381-395, 1981.
P. Bouthemy, M. Gelgon, and F. Ganansia, "A unified approach to shot change detection and camera motion characterization," IEEE Transactions on Circuits and Systems for Video Technology, vol. 9, pp. 1030-1044, 1999.
R. Dahyot and A. Kokaram, "Comparison of two algorithms for robust M-estimation of global motion parameters," in Proceedings of Irish Machine Vision and Image Processing Conference, pp. 224-231, Dublin, Ireland, 2004.
R. Dahyot and S. Wilson, "Robust scale estimation for the generalized Gaussian probability density function," Advances in Methodology and Statistics (Metodoloski zvezki), vol. 3, 2006.
R. Dahyot, N. Rea, A. Kokaram, and N. Kingsbury, "Inlier modeling for multimedia data analysis," in IEEE International Workshop on MultiMedia Signal Processing, pp. 482-485, Siena, Italy, 2004.
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.