This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Estimation of Occlusion and Dense Motion Fields in a Bidirectional Bayesian Framework
May 2002 (vol. 24 no. 5)
pp. 712-718

This paper presents new MRF models in a bidirectional Bayesian framework for accurate motion and occlusion fields estimation. With careful selection of the five free parameters required by the models, good experimental results have been obtained. The resultant computational speed is also 5.5 times faster compared with the conventional Iterated Conditional Mode relaxation using the proposed fast bidirectional relaxation.

[1] E. Dubois and J. Konrad, “Estimation of 2-D Fields from Image Sequences with Application to Motion-Compensated Processing,” Motion Analysis and Image Sequence Processing, M.I. Sezan and R.L. Lagendijk, eds. Norwell, Mass.: Kluwer, 1993.
[2] J. Zhang and G.G. Hanauer, “The Application of Mean Field Theory to Image Motion Estimation,” Trans. Image Processing, vol. 4, no. 1, pp. 19-32, 1995.
[3] A. Murat Tekalp, Digital Video Processing. Prentice Hall, 1995.
[4] J. Besag, “Spatial Interaction and the Statistical Analysis of Lattice Systems,” J. Royal Statistical Soc. B, vol. 36, no. 2, pp. 192-236, 1974.
[5] M. Hotter and R. Thoma, “Image Segmentation Based on Object Oriented Mapping Parameter Estimation,” Signal Processing, vol. 15, no. 3, pp. 315-334, Oct. 1988.
[6] S.Z. Li, Markov Random Field Modeling in Computer Vision. New York: Springer-Verlag, 1995.
[7] R. Depommier and E. Dubois, Motion Estimation With Detection of Occlusion Areas Proc. Int'l Conf. Acoustics, Speech, and Signal Processing, vol. 3, pp. 269-272, 1992.
[8] 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.
[9] M.J. Chahine, “Estimation of Accelerated Motion and Occlusions from Time-Varying Images,” Msc thesis, McGill, Montreal, Canada, 1994.
[10] J. Konrad and E. Dubois, Bayesian Estimation of Motion Vector Fields IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 9, pp. 910-927, Sept. 1992.
[11] P.A. Redert, E. Hendriks, and J. Biemond, “Correspondence Estimation in Image Pairs,” IEEE Signal Processing Magazine, pp. 29-46, May 1999.
[12] M. Black and P. Anandan, The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields J. Computer Vision and Image Understanding, vol. 63, no. 1, pp. 75-104, 1996.
[13] R. Thoma and M. Bierling, “Motion Compensating Interpolation Considering Covered and Uncovered Background,” Signal Processing, vol. 1, pp. 191-212, Oct. 1989.
[14] K. Matthews and N. Namazi, “A Bayes Decision Test for Detecting Uncovered Background and Moving Pixels in Image Sequences,” IEEE Trans. Image Processing, vol. 7, no. 5, pp. 720-728, May 1998.

Index Terms:
Occlusion detection, dense motion field estimation, Markov random field
Citation:
K.P. Lim, A. Das, M.N. Chong, "Estimation of Occlusion and Dense Motion Fields in a Bidirectional Bayesian Framework," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 712-718, May 2002, doi:10.1109/34.1000246
Usage of this product signifies your acceptance of the Terms of Use.