Change Detection Based on a Transductive Inference in SAR Images

Abstract:

As the change detection based on Synthetic Aperture Radar (SAR) images that are difficult and very limited to acquire labeled samples are of low detection rate and high error rate, Thus a progressive transductive SVM algorithm based on original feature space for unsupervised change detection of SAR images is proposed. The pseudo-training set of the difference image is obtained using K-means clustering method without any prior information; Starting from these initial seeds, the progressive transductive SVM 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 transductive inference algorithm. Using dynamic region labeling rule, the algorithm not only achieves its rules of progressive labeling and dynamic adjusting, but also raises its speed at the same time. Experimental results obtained on different multitemporal SAR images show that, transductive inference algorithm that extract the information of unlabeled patterns improve the SVM classifier accuracy. These results confirm the effectiveness of the proposed approach.

• Periodical: Applied Mechanics and Materials (Volumes 701-702)
• Pages: 463-467
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.701-702.463
• Online since: December 2014
• Authors: Song Tian*, Jian She Song, Qi An, Gang Yu
• Keywords: Change Detection, Progressive Transductive Inference, Support Vector Machine (SVM), Synthetic Aperture Radar Images

References

[1] A Bouaraba, A Younsi, A A Belhadj, et al. Robust techniques for coherent change detection using cosmo-skymed SAR images. Progress in Electromagnetics Research M, 22: 219-232(2012).

DOI: 10.2528/pierm11110707

[2] F Bovolo, C Marin, L Bruzzone. A Hierarchical Approach to Change Detection in Very High Resolution SAR Images for Surveillance Applications. IEEE Transactions on Geoscience and Remote Sensing, 51(4): 2042-2054(2013).

DOI: 10.1109/tgrs.2012.2223219

[3] C J C Burges. A tutorial on support vector machines for pattern recognition. Knowledge Discovery and Data Mining, 2(2): 121-167(1998).

[4] V N Vapnik. Statistical Learning Theory. New York: Wiley, (1998).

[5] U Maulik, D Chakraboty. Learning with transductive SVM for semisupervised pixel classification of remote sensing imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 77: 66-78(2013).

DOI: 10.1016/j.isprsjprs.2012.12.003

[6] C C Chang, C J Lin. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology(TIST), 2(3): 27(2011).

DOI: 10.1145/1961189.1961199