© 2018, © 2018 Informa UK Limited, trading as Taylor & Francis Group. 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.

© 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature. The Earth’s environment is continually changing due to both human and natural factors. Timely identification of the location and kind of change is of paramount importance in several areas of application. Because of that, remote sensing change detection is a topic of great interest. The development of precise change detection methods is a constant challenge. This study introduces a novel unsupervised change detection method based on data clustering and optimization. The proposal is less dependent on radiometric normalization than classical approaches. We carried experiments with remote sensing images and simulated datasets to compare the proposed method with other unsupervised well-known techniques. At its best, the proposal improves by 50% the accuracy concerning the second best technique. Such improvement is most noticeable with uncalibrated data. Experiments with simulated data reveal that the proposal is better than all other compared methods at any practical significance level. The results show the potential of the proposed method.

© 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd. part of Springer Nature. The Earth’s environment is continually changing due to both human and natural factors. Timely identification of the location and kind of change is of paramount importance in several areas of application. Because of that, remote sensing change detection is a topic of great interest. The development of precise change detection methods is a constant challenge. This study introduces a novel unsupervised change detection method based on data clustering and optimization. The proposal is less dependent on radiometric normalization than classical approaches. We carried experiments with remote sensing images and simulated datasets to compare the proposed method with other unsupervised well-known techniques. At its best, the proposal improves by 50% the accuracy concerning the second best technique. Such improvement is most noticeable with uncalibrated data. Experiments with simulated data reveal that the proposal is better than all other compared methods at any practical significance level. The results show the potential of the proposed method.