In this paper, we discuss a Markov Random Field (MR) modeling for multisource and multitemporal remotely sensed image fusion and classification. Satellite images provided by individual sensor are incomplete, inconsistent or imprecise. Additional sources may provide complementary information and the fusion of multisource data can create a more consistent interpretation of the scene in which the associated uncertainty is decreased and the reliability of analysis results is increased. Also, a temporal data from a single sensor can be considered as separate information sources. The combination of multitemporal data over the same scene enhances information on changes that might have occurred in the area observed over time. Using these available data through a fusion and classification process, our objective is to extract more information to achieve greater accuracy in assigning pixels to thematic classes. The best methodological framework which allows the realization of this process is a Markov Random Field (MRF).

1. Besag, J. 1986. On the Statistical Analysis of Dirty Pictures. Journal Royal of Statistics: Soc. B, 48, 3, pp. 259-302.
2. Braathen, B. , Pieczynski, W. , and Masson, P. 1993. Global and local methods of unsupervised Bayesian segmentation of images. Machine Graphics and vision, vol. 2, no. 1, pp. 39-52.
3. Byeungwoo, J. , and Landgrebe, D. A. 1999. Decision Fusion Approach for Multitemporel Classification. IEEE Transactions on Geoscience and Remote Sensing, vol. 37, no. 3, pp. 1227-1233.
4. Congalton, R. G. , 1991. A Review of Assessing the Accuracy of Classifications of Remotely Sensed Data. Remote Sensing of Environment, no. 37, pp. 35-46.
5. Descombes, X. , Morris, R. D. , Zerubia, J. , and Berthod, M. 1999. Estimation of Markov Random Field Prior Parameters Using Markov Chain Monte Carlo Maximum Likelihood. IEEE Trans. Geosci. Remote Sensing, vol. 8, no. 7, pp. 954-962.
6. Geman, S. , and Geman, D. 1984. Stochastic Relaxation, Gibbs Distribution, and the Bayesian Restoration of Images. IEEE Trans. Pattern Analysis and Machine Intelligence, PAMI-6, pp. 721-741.
7. Kheddam, R. , and Belhadj-Aissa, A. 2001. General Multisource Contextual Classification Model of Remotely Sensed Imagery based on MRF. IEEE / ISPRS Workshop on Remote Sensing and Data Fusion Over Urban Areas, Rome, Italy.
8. Kheddam, R. , Belhadj-Aissa, A. , and Ranchin, T. 2002. Study of ICM parameters influence on imges satellite contextual classification. In proceedings of the 22nd symposium of the European association of remote sensing laboratories, Prague, Czech, pp. 79-85.
9. Marroquin, J. , Mitter, S. , Poggio, T. 1987. Probabilistic solution of ill-posed problems in computational vision. Journal of the American Statistical Association, no. 82, pp. 76-89.
10. Pieczynski, W. 1989. Estimation of context in random fields. Journal of Applied Statistics, vol. 16, no. 2, pp. 283-289, 1989.
11. Schistad Solberg, A. H. , Taxt, T. , and Jain, A. K. 1993. Fusion of multitemporal satellite images and GIS data for land-use classification. In Proc. 8th Scandinavian Conf. Image Analysis, Tromso, Norway, Technical report.
12. Schistad Solberg, A. H. , Taxt, T. , and Jain, A. K. 1994. Multisourse classification of remotely sensed data: Fusion of Landsat TM and SAR images. IEEE Transactions on Geosciences and Remote Sensing, vol. 32, pp. 768-778.
13. Schistad Solberg, A. H. , Taxt, T. , and Jain, A. K. 1996. A Markov random field model for classification of multisource satellite imagery. IEEE Transactions on Geosciences and Remote Sensing, vol. 34, no. 1, pp. 100-113.
14. Schistad Solberg, A. H. 1999. Contextual data fusion applied to forest map revision. IEEE Transactions on Geosciences and Remote Sensing, vol. 37, no. 3, pp. 1234-1243.
15. Wald, L. 1999. Some terms of reference in data fusion. IEEE Transactions on Geosciences and Remote Sensing, 37, 3, pp. 1190-1193.

Markov Random Field (mrf) Satellite Images Fusion Classification