Evaluation of speckle filtering and texture analysis methods for land cover classification from SAR images

• Published in: International journal of remote sensing 2002-01, Vol.23 (9), p.1895-1925
• Main Authors: Nyoungui, A. Ndi, Tonye, E., Akono, A.
• Format: Article
• Language: English
• Subjects: Applied geophysics; Earth sciences; Earth, ocean, space; Exact sciences and technology; Internal geophysics; Soils; Surficial geology
• ISSN: 0143-1161; 1366-5901
• DOI: 10.1080/01431160110036157

This paper describes a comparative evaluation of several speckle reduction and texture analysis techniques, with particular emphasis on their applicability to supervised land cover classification from SAR images. Issues related to suppression of speckle in a uniform area, preservation of edges, and texture preservation are pursued in these filters. Quality of texture features is measured by the relevancy, discriminative power and ease of computation of the features. The discriminative power of texture features is measured using the Jeffreys-Matusita distance and classification performance measured on a validation set independent from the classifier's training set. Classifiers investigated are maximum-likelihood, multi-layer perceptron (MLP) and radial basis function (RBF) neural networks. Classification accuracy is measured by KHAT statistic calculated from confusion matrices. Two SAR images of ERS-1 and E-SAR programme showing different land cover categories within the regions of Douala and Ngaoundere (Cameroon), and a bi-polarized Synthetic Aperture Radar (SAR) image from an agricultural station near the city of Altona (Canada) are used for analysis. Speckle suppression techniques based on the wavelet transform performs the best, followed by the modified K-nearest neighbours and the Lee's local statistic filters. Depending on the nature of the land cover types being classified, texture features derived from second- and third-order histogram performed the best, followed by first-order statistics and features derived using the grey-level difference vector method. Among all classifiers considered, the MLP and the RBF neural networks performed the best, achieving up to 94% overall accuracy for the E-SAR image of Douala, for example.