Improvement of Markov Random Field Technique for Unsupervised Change Detection from Multichannel SAR Images

Document Type : علمی - پژوهشی

Authors

1 M.Sc. of Dep. of Photogrammetry and Remote Sensing, K.N. Toosi University of Technology

2 Professor of Dep. of Photogrammetry and Remote Sensing, K.N. Toosi University of Technology

3 Associate Prof., Department of Photogrammetry and Remote Sensing, K. N. Toosi University of Technology

Abstract

In applications related to environmental monitoring and disaster management, multichannel synthetic aperture radar (SAR) data present a great potential, owing both to their insensitivity to atmospheric and Sun-illumination conditions and to the improved discrimination capability they may provide as compared with single-channel SAR. However, exploiting this potential requires accurate and automatic techniques to generate change maps from images acquired over the same geographic region in different polarizations or at different frequencies at different times. Furthermore, sensitivity to contextual information of each pixel reduces the error rates in labeling process, thus generates accurate change maps. The smoothing effect of despeckling and the isotropic formulation of the Markov Random Field model cause over-smoothing of the spatial boundaries between changed and unchanged areas in the final change maps. In order to reduce this drawback, edge-preserving MRF models could be integrated in the labeling process. This method improves the precision of edges at spatial boundaries and increases the change detection accuracy. In this paper, a contextual unsupervised change-detection technique (based on a data-fusion approach) is proposed for two-date multichannel SAR images. A Markov Random Field model is formulated by using “energy functions” that combines the information conveyed by each SAR channel, the spatial contextual information concerning the correlation among neighboring pixels and the edge information. In order to estimate the model parameters, the expectation–maximization algorithm is combined with the recently proposed “method of log-cumulants.” The proposed technique was experimentally validated with semisimulated data produced by ASAR-ENVISAT images. Experiments illustrate a significant improvement (average 12%) with the proposed technique over the other change detection approaches. Integrating edge information yielded accurate results in exploiting various levels of changes (low-medium-high) whereas contextual information and information conveyed by channels were unable to detect low and medium level changes. Considering the small number of iterations, computation time is reduced considerably. Generally the highest accuracy achieved by the proposed algorithm is 99/67%.

Keywords

References

  1. Aanæs, H., Nielsen, A.A., Carstensen, J.M., Larsen, R. & Ersbøll, B.K., 2009, Efficient Incorporation of Markov Random Fields in Change Detection, IEEE Trans. Geosci. Remote Sens., 8(4), PP. 689-692.
  2. Angiati, E., Dellepiane, S., Martino, M., Moser, G. & Serpico, S.B., 2010, Flooding and Change Maps from Cosmo-Skymed Images, Riunione Annuale- Brescia, 21-23 June.
  3. Besag, J., 1974, Spatial Interaction and the Statistical Analysis of Lattice Systems, Journal of the Royal Statistical Society Series B (Methodological), 36(2), PP. 192-236.
  4. Bruzzone, L. & Prieto, D.F., 2000, Automatic Analysis of the Difference Image for Unsupervised Change Detection, IEEE Trans. Geosci. Remote Sensing, 38(3), PP. 1171-1182.
  5. Bujor, F., Trouve, E., Valet, L., Nicolas, J.M. & Rudant, J.P., 2004, Application of Log-Cumulants to the Detection of Spatio-Temporal Discontinuities in Multitemporal SAR Images, IEEE Trans. Geosci.Remote Sens., 42(10), PP. 2073-2084.
  6. Celeux, G., Forbes, F. & Peyrand, N., 2003, EM Procedures Using Mean Field-Like Approximations for Markov Model-Based Image Segmentation, Pattern Recognit., 36(1), PP. 131-144.
  7. Dierking, W. & Skriver, H., 2002, Change Detection for Thematic Mapping by Means of Airborne Multi-Temporal Polarimetric SAR Imagery, IEEE Trans. Geosci. Remote Sens., 40(3), PP. 618-636.
  8. Dubes R.C., & Jain, A.K., 1989, Random Field Models in Image Analysis, J. Appl. Stat., 16(2), PP. 131-163.
  9. Fransson, J.E.S., Walter, F., Blennow, K., Gustavsson, A. & Ulander, L.M.H., 2002, Detection of Storm-Damaged Forested Areas Using Airborne CARABAS-II VHF SAR Image Data, IEEE Trans. Geosci. Remote Sens., 40(10), PP. 2170-2175.
  10. Geman, S. & Geman, D., 1984, Stochastic Relaxation Gibbs Distribution and the Bayesian Restoration of the Image, IEEE Trans. on Pattern Analysis and Machine Intelligence, 6(6), PP. 721-741.
  11. Jackson Q. & Landgrebe, D.A., 2001, An Adaptive Classiï‌er Design for High-Dimensional Data Analysis with a Limited Training Data Set, IEEE Trans. Geosci. Remote Sens., 39(12), PP. 2664-2679.
  12. Jackson, Q. & Landgrebe, D., 2002, Adaptive Bayesian Contextual Classiï‌cation Based on Markov Random Fields, IEEE Trans. Geosci. Remote Sens., 40(11), PP. 2454-2463.
  13. Li, S.Z., 2009, Markov Random Field Modeling in Image Analysis, London: Springer.
  14. Liang, L.R. & Looney, C.G., 2003, Competitive Fuzzy Edge Detection, Applied Soft Computing, 3, PP. 123-137.
  15. Liming, J., Mingsheng, L., Lu, Z.H. & Hui, L., 2007, Unsupervised Change Detection in Multitemporal SAR Images Using MRF Models, Geo-spatial Information Science, 10(2), PP. 111-116.
  16. Looney, C.G., 2001, A Fuzzy Classiï‌er Network with Ellipsoidal Epanechnikovs, Computer Science Department, University of Nevada, Reno, NV.
  17. Moser, G. & Serpico, S.B., 2006, Generalized Minimum-Error Thresholding for Unsupervised Change Detection from SAR Amplitude Imagery, IEEE Trans. Geosci. Remote Sens., 44(10), PP. 2972-2982.
  18. Moser, G. & Serpico, S.B., 2009, Unsupervised Change Detection from Multichannel SAR Data by Markovian Data Fusion, IEEE Trans. Geosci. Remote Sens., 47(7), PP. 2114-2127.
  19. Moser, G. & Serpico, S.B., 2010, Unsupervised Change Detection with Very High-Resolution SAR Images by Multiscale Analysis and Markov Random Fields, IEEE Trans. Geosci. Remote Sens., 8(4), PP. 3082-3085.
  20. Nicolas, J.M., 2002, Introduction aux statistiques de deuxième espece: Applications des log-moments et des log-cumulants a l’analyse des lois d’images radar, Trait. Signal, 19, PP. 139-167.
  21. Sneddon, I., 1972, The Use of Integral Transforms, New York: McGraw-Hill.
  22. Solberg, A.H.S., Taxt, T. & Jain, A.K., 1996, A Markov Random Field Model for Classiï‌cation of Multisource Satellite Imagery, IEEE Trans. Geosci.Remote Sens., 34(1), PP. 100-113.
  23. Tso, B. & Mather, M., 2001, Classification Methods for Remotely Sensed Data, London: Taylor and Francis Ltd.
  24. Touzi, R., Lopez, A. & Bousquet, P., 1988, A Statistical and Geometrical Edge Detector for SAR Images, IEEE Trans. Geosci. Remote Sens., 26(6), PP. 764-773.
  25. Vaccaro, R., Smits, P.C. & Dellepiane, S.G., 2000, Exploiting Spatial Correlation Features for SAR Image Analysis, IEEE Trans. Geosci.Remote Sens., 38(3), PP. 1212-1223.
Iranian Journal of Remote Sensing & GIS
Volume 9, Issue 2 - Serial Number 2
December 2017
Pages 21-40

Files

Share

How to cite

Statistics