Region-based classification of PolSAR data using radial basis kernel functions with stochastic distances

• Published in: International journal of digital earth Vol. 12; no. 6; pp. 699 - 719
• Main Authors: Negri, Rogério G., Frery, Alejandro C., Silva, Wagner B., Mendes, Tatiana S. G., Dutra, Luciano V.
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 03-06-2019; Taylor & Francis Ltd; Taylor & Francis Group
• Subjects: Case studies; Classification; Computer applications; Computer simulation; Distance; Earth; Image classification; Imagery; Kernel functions; Mathematical models; minimum distance classifier; PolSAR; Prototypes; Remote sensing; Reproducibility; Robustness (mathematics); Segments; stochastic distance; Stochasticity; Support vector machines; SVM; Training
• ISSN: 1753-8947; 1753-8955
• DOI: 10.1080/17538947.2018.1474958

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. ["Classification of segments in PolSAR imagery by minimum stochastic distances between wishart distributions." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 6 (3): 1263-1273] 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.