This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Oriented Structure of the Occlusion Distortion: Is It Reliable?
September 2002 (vol. 24 no. 9)
pp. 1286-1290

Abstract—In the energy spectrum of an occlusion sequence, the distortion term has the same orientation as the velocity of the occluding signal. Recent works claimed that this oriented structure can be used to distinguish the occluding velocity from the occluded one. Here, we argue that the orientation structure of the distortion cannot always work as a reliable feature due to the rapidly decreasing energy contribution. This already weak orientation structure is further blurred by a superposition of distinct distortion components. We also indicate that the superposition principle of Shizawa and Mase for multiple motion estimation needs to be adjusted.

[1] E.H. Adelson and J.R. Bergen, “Spatiotemporal Energy Models for the Perception of Motion,” J. Optical Soc. Am., vol. 1, no. 2, pp. 284-299, 1985.
[2] S.S. Beauchemin and J.L. Barron, “A Theory of Occlusion in the Context of Optical Flow,” Advances in Computer Vision, F. Solina, W. Kropatsch, R. Klette, and R. Bajcsy, eds., pp. 191-200, New York: Springer Wien, Nov. 1997.
[3] S.S. Beauchemin and J.L. Barron, “The Frequency Structure of 1D Occluding Image Signals,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, pp. 200-206, 2000.
[4] S.S. Beauchemin and J.L. Barron, “On the Fourier Properties of Discontinuous Visual Motion,” J. Math. Imaging and Vision, vol. 13, no. 3, pp. 155-172, 2000.
[5] W. Chen, G.B. Giannakis, and N. Nandhakumar, “Spatiotemporal Approach for Time-Varying Global Image Motion Estimation,” IEEE Trans. Image Processing, vol. 5, no. 10, pp. 1448-1461, 1996.
[6] W. Chen, G.B. Giannakis, and N. Nandhakumar, “A Harmonic Retrieval Framework for Discontinuous Motion Estimation,” IEEE Trans. Image Processing, vol. 7, no. 9, pp. 1242-1257, 1998.
[7] J.G. Daugman, “Complete Discrete 2D Gabor Transforms by Neural Networks for Image Analysis and Compression,” IEEE Trans. Acoustics, Speech, and Signal Processing, vol. 36, no. 7, 1988.
[8] D.J. Fleet, Measurement of Image Velocity. Norwell,Mass.: Kluwer Academic, 1992.
[9] D.J. Fleet and K. Langley, “Computational Analysis of Non-Fourier Motion,” Vision Research, vol. 34, pp. 3057-3079, 1994.
[10] D.J. Heeger, “Optical Flow Using Spatiotemporal Filters. Int'l J. Computer Vision, vol. 1, no. 4, pp. 279-302, 1987.
[11] F. Heitger, L. Rosenthaler, E. Peterhans, and O. Kuebler, “Simulation of Neural Contour Mechanisms: From Simple to End-Stopped Cells,” Vision Research, vol. 32, no. 5, pp. 963-981, 1992.
[12] B. Jähne, Spatio-Temporal Image Processing. Springer-Verlag, 1993.
[13] M.S. Langer and R. Mann, “Dimensional Analysis of Image Motion,” Proc. Int'l Conf. Computer Vision, vol. I, pp. 155-162, July 2001.
[14] T.S. Lee, “Image Representation Using 2D Gabor Wavelets,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 10, pp. 959-971, Oct. 1996.
[15] M. Shizawa and K. Mase, “A Unified Computational Theory for Motion Transparency and Motion Boundaries Based on Eigenenergy Analysis,” IEEE Conf. Computer Vision and Pattern Recognition, pp. 289-295, June 1991.
[16] W. Yu, K. Daniilidis, S. Beauchemin, and G. Sommer, “Detection and Characterization of Multiple Motion Points,“ IEEE Conf. Computer Vision and Pattern Recognition, vol. I, pp. 171-177, June 1999.
[17] J.M. Zanker, “Theta Motion: A Paradoxical Stimulus to Explore Higher Order Motion Extraction,” Vision Research, vol. 33, no. 4, pp. 553-569, 1993.

Index Terms:
Optical flow, occlusion, motion discontinuities, spectral analysis.
Citation:
Weichuan Yu, Gerald Sommer, Steven Beauchemin, Kostas Daniilidis, "Oriented Structure of the Occlusion Distortion: Is It Reliable?," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 9, pp. 1286-1290, Sept. 2002, doi:10.1109/TPAMI.2002.1033220
Usage of this product signifies your acceptance of the Terms of Use.