Abstract
In this paper, we present a motion segmentation approach based on the subspace segmentation technique, the generalized PCA. By incorporating the cues from the neighborhood of intensity edges of images, motion segmentation is solved under an algebra framework. Our main contribution is to propose a post-processing procedure, which can detect the boundaries of motion layers and further determine the layer ordering. Test results on real imagery have confirmed the validity of our method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
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)
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)
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)
Szeliski, R., Avidan, S., Anandan, P.: Layer extraction from multiple images containing reflections and transparency. In: IEEE Conf. on Computer Vision and Pattern Recognition, vol. I, pp. 246–253 (June 2000)
Black, M.J., Fleet, D.J.: Probabilistic detection and tracking of motion boundaries. Int. J. Comput. Vis. 38(3), 231–245 (2000)
Smith, P., Drummond, T., Cipolla, R.: Layered Motion Segmentation and Depth Ordering by Tracking Edges. IEEE Trans. on Pattern Analysis and Machine Intelligence 26(4), 479–494 (2004)
Ogale, A.S., Fermuller, C., Aloimonos, Y.: Motion Segmentation Using Occlusions. IEEE Trans. on Pattern Analysis and Machine Intelligence 27(6), 988–992 (2005)
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)
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)
Irani, M., Rousso, B., Peleg, S.: Computing occluding and transparent motions. Int. J. of Computer Vision 2(1), 5–16 (1994)
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)
Vidal, R., Ma, Y., Sastry, S.: Generalized Principal Component Analysis (GPCA). IEEE Trans. on Pattern Analysis and Machine Intelligence 27(12), 1–15 (2005)
Vidal, R.: Generalized Principal Component Analysis (GPCA): an Algebraic Geometric Approach to Subspace Clustering and Motion Segmentation, Ph.D. Thesis, Electrical Engineering and Computer Sciences, Univer-sity of California at Berkeley (August 2003)
Vidal, R., Ma, Y.: A Unified Algebraic Approach to 2-D and 3-D Motion Segmentation. J. of Mathematical Imaging and Vision 25(3), 403–421 (2006)
Ogale, A.S., Aloimonos, Y.: A Roadmap to the Integration of Early Visual Modules. Int. J. of Computer Vision 72(1), 9–25 (2007)
GPCA matlab codes, http://perception.csl.uiuc.edu/gpca/
Papadimitriou, T., Diamantaras, K.I., et al.: Video Scene Segmentation Using Spatial Contours and 3D Robust Motion Estimation. IEEE Trans. On Circuits and Systems For Video Technology 14(4) (2004)
Video sequences, http://www.cipr.rpi.edu/resource/sequences/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Yu, H., Zhang, J.J. (2011). Apply GPCA to Motion Segmentation. In: Zhang, J., Shao, L., Zhang, L., Jones, G.A. (eds) Intelligent Video Event Analysis and Understanding. Studies in Computational Intelligence, vol 332. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17554-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-17554-1_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17553-4
Online ISBN: 978-3-642-17554-1
eBook Packages: EngineeringEngineering (R0)