Apply GPCA to Motion Segmentation - Intelligent Video Event Analysis and Understanding - page 35

However, it can be noted that our algorithm relies on a given optical flow field.
In our experiments, many available optical flow algorithms do not seem suitable
for the scenarios with a salient rotation element. This will restrict the applications
of our algorithm. It is crucial to further develop a robust optical flow algorithm.
Our future work will aim to tackle this challenge.
References
1. Yu, W., Sommer, G., Daniilidis, K.: Multiple motion analysis: in spatial or in spectral
domain? Computer Vision and Image Understanding 90(2), 129-152 (2003)
2. Fleet, D.J., Black, M.J., Yacoob, Y., Jepson, A.D.: Design and use of linear models for
image motion analysis. Int. J. Comput. Vis. 36(3), 171-193 (2000)
3. Wang, J.Y.A., Adelson, E.H.: Layered representation for motion analysis. In: IEEE
Conf. on Computer Vision and Pattern Recognition, pp. 361-366 (June 1993)
4. Szeliski, R., Avidan, S., Anandan, P.: Layer extraction from multiple images contain-
ing reflections and transparency. In: IEEE Conf. on Computer Vision and Pattern Rec-
ognition, vol. I, pp. 246-253 (June 2000)
5. Black, M.J., Fleet, D.J.: Probabilistic detection and tracking of motion boundaries. Int.
J. Comput. Vis. 38(3), 231-245 (2000)
6. Smith, P., Drummond, T., Cipolla, R.: Layered Motion Segmentation and Depth Or-
dering by Tracking Edges. IEEE Trans. on Pattern Analysis and Machine Intelli-
gence 26(4), 479-494 (2004)
7. Ogale, A.S., Fermuller, C., Aloimonos, Y.: Motion Segmentation Using Occlusions.
IEEE Trans. on Pattern Analysis and Machine Intelligence 27(6), 988-992 (2005)
8. Kumar, M.P., Torr, P.H.S., Zisserma, A.: Learning Layered Motion Segmentation of
Video. In: Proc. of the Tenth IEEE Int. Conf. on Computer Vision, vol. 1, pp. 33-40
(2005)
9. Irani, M., Anandan, P., Bergen, J., Kumar, R., Hsu, S.: Efficient Representations of
Video Sequences and Their Representations. Signal Processing: Image Comm. 8(4),
327-351 (1996)
10. Irani, M., Rousso, B., Peleg, S.: Computing occluding and transparent motions. Int. J.
of Computer Vision 2(1), 5-16 (1994)
11. Csurka, G., Bouthemy, P.: Direct Identification of Moving Objects and Background
from 2D Motion Models. In: Proc. of IEEE Int. Conf. of Computer Vision, pp.
566-571 (1999)
12. Vidal, R., Ma, Y., Sastry, S.: Generalized Principal Component Analysis (GPCA).
IEEE Trans. on Pattern Analysis and Machine Intelligence 27(12), 1-15 (2005)
13. Vidal, R.: Generalized Principal Component Analysis (GPCA): an Algebraic Geomet-
ric Approach to Subspace Clustering and Motion Segmentation, Ph.D. Thesis, Electri-
cal Engineering and Computer Sciences, Univer-sity of California at Berkeley (August
2003)
14. Vidal, R., Ma, Y.: A Unified Algebraic Approach to 2-D and 3-D Motion Segmenta-
tion. J. of Mathematical Imaging and Vision 25(3), 403-421 (2006)
15. Ogale, A.S., Aloimonos, Y.: A Roadmap to the Integration of Early Visual Modules.
Int. J. of Computer Vision 72(1), 9-25 (2007)
16. GPCA matlab codes, http://perception.csl.uiuc.edu/gpca/