This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Nonlinear Motion Estimation Using the Supercoupling Approach
May 1998 (vol. 20 no. 5)
pp. 550-555

Abstract—This paper presents the application of a very efficient multiresolution transformation, which is related to the renormalization group approach of physics, to the problem of motion segmentation. The proposed approach is much faster and yields much better results than the full resolution approach. The problem is formulated as one of global optimization where a cost function is constructed to combine the information obtained by various processors as well as the constraints we impose to the problem. The cost function is optimized using the supercoupling multiresolution approach.

[1] J.K. Aggarwal and N. Nandakumar, "On the Computation of Motion From Sequence of Images—a Review," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 10, pp. 917-935, 1988.
[2] M. Bober and J. Kittler, "Robust Motion Analysis," Proc. CVPR, pp. 947-952,Seattle, June 1994.
[3] B. Gidas, "A Renormalization Group Approach to Image Processing Problems," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, pp. 164-180, 1989.
[4] F. Heitz and P. Bouthemy, Multimodal Estimation of Discontinuous Optical Flow Using Markov Random Fields IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 12, pp. 1217-1232, Dec. 1993.
[5] F. Heitz, P. Perez, and P. Bouthemy, "Multiscale Minimization of Global Energy Functions in Some Visual Recovery Problems," Computer Vision, Graphics and Image Processing, vol. 59, pp. 125-134, 1994.
[6] J. Konrad and E. Dubois, "Comparison of Stochastic and Deterministic Solution Methods in Bayesian Estimation of 2D Motion," Image and Vision Computing, vol. 8, pp. 304-317, 1990.
[7] G.K. Nicholls and M. Petrou, "On Multiresolution Image Restoration," Proc. Int'l Conf. Pattern Recognition, pp. 63-67,Jerusalem, Oct. 1994.
[8] P. Perez and F. Heitz, "Multiscale Markov Random Fields and Constrained Relaxation in Low-Level Image Analysis," Proc. 17th IEE Conf. Acoustics, Speech and Signal Processing, pp. III-61-III-64,San Francisco, Mar. 1992.
[9] M. Petrou, "Accelerated Optimization via the Renormalization Group Transform," D.M. Titterington, ed., Complex Stochastic Systems and Engineering.London: Clarendon Press, 1993, pp. 105-120.
[10] P. Schroeter, S. Ayer, and J. Bigun, "Segmentation of Moving Objects by Robust Motion Parameter Estimation Over Multiple Frames," J.O. Eklundh, ed., Proc. European Conf. Computer Vision, vol. 2, pp. 316-327, 1994.
[11] A. Singh, Optic Flow Computation: A Unified Perspective.Los Alamitos, Calif.: IEEE CS Press, 1992.

Index Terms:
Motion analysis, motion segmentation, supercoupling approach, Markov random fields, stochastic relaxation.
Citation:
M. Bober, M. Petrou, J. Kittler, "Nonlinear Motion Estimation Using the Supercoupling Approach," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 5, pp. 550-555, May 1998, doi:10.1109/34.682185
Usage of this product signifies your acceptance of the Terms of Use.