Region-Based Classification of PolSAR Data Using Radial Basis Kernel Functions With Stochastic Distances
This work addresses robustness in PolSAR data classification for remote sensing applications, but it is incremental as it builds on existing stochastic distance methods.
The authors tackled the problem of region-based classification of PolSAR data being sensitive to errors in training samples by proposing an extension that combines radial basis kernel functions and stochastic distances with Support Vector Machines (SVM), showing that SVM achieves better performance than Minimum Distance classification, though with higher computational cost.
Region-based classification of PolSAR data can be effectively performed by seeking for the assignment that minimizes a distance between prototypes and segments. Silva et al (2013) used stochastic distances between complex multivariate Wishart models which, differently from other measures, are computationally tractable. In this work we assess the robustness of such approach with respect to errors in the training stage, and propose an extension that alleviates such problems. We introduce robustness in the process by incorporating a combination of radial basis kernel functions and stochastic distances with Support Vector Machines (SVM). We consider several stochastic distances between Wishart: Bhatacharyya, Kullback-Leibler, Chi-Square, Rényi, and Hellinger. We perform two case studies with PolSAR images, both simulated and from actual sensors, and different classification scenarios to compare the performance of Minimum Distance and SVM classification frameworks. With this, we model the situation of imperfect training samples. We show that SVM with the proposed kernel functions achieves better performance with respect to Minimum Distance, at the expense of more computational resources and the need of parameter tuning. Code and data are provided for reproducibility.