ISPRS-Annals ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences ISPRS-Annals ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci. 2194-9050 Copernicus Publications Göttingen, Germany 10.5194/isprsannals-I-7-227-2012 A CHANGE DETECTION METHOD FOR REMOTE SENSING IMAGE BASED ON MULTI-FEATURE DIFFERENCING KERNEL SVM Lin Y. 1 2 Liu B. 1 2 Lv Q.-l. 1 2 Pan C. 3 Lu Y. 1 Research Center of Remote Sensing and Spatial Information Technology, Tongji University, Shanghai, 200092, China Department of Surveying and Geoinformatics, Tongji University, Shanghai, 200092, China Shanghai Municipal Institute of Surveying and Mapping, Shanghai, 200063, China 17 07 2012 I-7 227 235 Copyright: © 2012 Y. Lin et al. 2012 This work is licensed under the Creative Commons Attribution 3.0 Unported License. To view a copy of this licence, visit https://creativecommons.org/licenses/by/3.0/ This article is available from https://isprs-annals.copernicus.org/articles/I-7/227/2012/isprs-annals-I-7-227-2012.html The full text article is available as a PDF file from https://isprs-annals.copernicus.org/articles/I-7/227/2012/isprs-annals-I-7-227-2012.pdf

Based on the support vector machine (SVM) tools and multiple kernel method, the combinations of kernel functions were mainly discussed. The construction method of image differencing kernel with multi-feature (spectral feature and textural feature) has been developed. Through this method and weighting of the categories' samples, the improved SVM change detection model has been proposed, which could realize the direct extraction of spatial distribution information from several change classes. From the experiments we can draw the following conclusions: with the help of multiple kernel function integrating spectral features and texture information, the new change detection model can achieve higher detection accuracy than the traditional methods and is suitable for the small-sample experiment. Furthermore, it avoids the complex and uncertainty in determining change threshold required in the old detection methods.