UNSUPERVISED CHANGE DETECTION FOR MULTISPECTRAL IMAGES
This paper presents a novel approach to unsupervised change detection in multispectral remote-sensing images. The proposed approach aims at extracting the change information by jointly analyzing the spectral channels of multitemporal images without any training data. This is accomplished by using a selective Bayesian thresholding for deriving a pseudo training set that is necessary for initializing an adequately defined binary semisupervised support vector machine (S3VM) classifier. Starting from these initial seeds, the S3VM performs change detection in the original multitemporal feature space by gradually considering unlabeled patterns in the definition of the decision boundary between changed and unchanged pixels according to a semisupervised learning algorithm. The values of the classifier parameters are then defined according to a novel unsupervised model-selection technique based on a similarity measure between change-detection maps obtained with different settings.
 L. Bruzzone and S. B. Serpico, Detection of changes in remotely sensed images by the selective use of multi-spectral information,â€ Int. J. Remote Sens., vol. 18, no. 18, pp. 3883â€“3888, Dec. 1997.
 A. Singh, Digital change detection techniques using remotely-sensed data,â€ Int. J. Remote Sens., vol. 10, no. 6, pp. 989â€“1003, 1989.
 R. J. Radke, S. Andra, O. Al-Kofahi, and B. Roysam, Image change detection algorithms: A systematic survey,â€ IEEE Trans. Image Process., vol. 14, no. 3, pp. 294â€“307, Mar. 2005.
 L. Bruzzone and D. FernÃ¡ndez Prieto, Automatic analysis of the difference image for unsupervised change detection,â€ IEEE Trans. Geosci. Remote Sens., vol. 38, no. 3, pp. 1171â€“1182, May 2000.
 P. L. Rosin, Thresholding for change detection,â€ Comput. Vis. Image Underst., vol. 86, no. 2, pp. 79â€“95, May 2002.
 L. Bruzzone, M. Chi, and M. Marconcini, A novel transductive SVM for the semisupervised classification of remote-sensing images,â€ IEEE Trans. Geosci. Remote Sens., vol. 44, no. 11, pp. 3363â€“3373, Nov. 2006.
 N. Cristianini and J. Shawe-Taylor, An Introduction to Support Vector Machines. Cambridge, U.K.: Cambridge Univ. Press, 2000.
 F. Bovolo and L. Bruzzone, A split-based approach to unsupervised change detection in large-size multitemporal images: Application to tsunami damage assessment,â€ IEEE Trans. Geosci. Remote Sens., vol. 45, no. 6, pp. 1658â€“1670, Jun. 2007.
 F. Bovolo and L. Bruzzone, A theoretical framework for unsupervised change detection based on change vector analysis in the polar domain,â€ IEEE Trans. Geosci. Remote Sens., vol. 45, no. 1, pp. 218â€“236, Jan. 2007.