Semi-Nonnegative Matrix Factorization for Motion Segmentation with Missing Data
Motion segmentation is an old problem that is receiving renewed interest because of its role in video analysis. In this paper, we present a Semi-Nonnegative Matrix Factorization (SNMF)method that models dense point tracks in terms of their optical flow, and decomposes sets of point tracks into semantically meaningful motion components. We show that this formulation of SNMF with missing values outperforms the state-of-the-art algorithm of Brox and Malik in terms of accuracy on 10-frame video segments from the Berkeley test set, while being over 100 times faster. We then show how SNMF can be applied to longer videos using sliding windows. The result is competitive in terms of accuracy with Brox and Malik’s algorithm, while still being two orders of magnitude faster.
KeywordsMotion Segmentation Semi-Nonnegative Matrix Factorization(SNMF) Missing Data
Unable to display preview. Download preview PDF.
- 4.Rao, S., Tron, R., Vidal, R., Ma, Y.: Motion segmentation via robust subspace separation in the presence of outlying, incomplete, or corrupted trajectories. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2008)Google Scholar
- 6.Elhamifar, E., Vidal, R.: Sparse subspace clustering. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2790–2797. IEEE (2009)Google Scholar
- 7.Cheriyadat, A., Radke, R.: Non-negative matrix factorization of partial track data for motion segmentation. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 865–872. IEEE (2009)Google Scholar
- 11.Hartley, R., Schaffalitzky, F.: Powerfactorization: 3d reconstruction with missing or uncertain data. In: Australia-Japan Advanced Workshop on Computer Vision, vol. 74, pp. 76–85 (2003)Google Scholar
- 12.Sundaram, N., Brox, T., Keutzer, K.: Dense point trajectories by gpu-accelerated large displacement optical flow. In: Proceedings of the 11th European Conference on Computer Vision, pp. 438–451 (2010)Google Scholar
- 13.Thurau, C.: PyMF: Python matrix factorization library (2010), http://code.google.com/p/pymf/
- 14.Tron, R., Vidal, R.: A benchmark for the comparison of 3-d motion segmentation algorithms. In: IEEE Conference on Computer Vision and Pattern Recognition 2007, pp. 1–8. IEEE (2007)Google Scholar