info:eu-repo/semantics/article
Texture descriptors for robust SAR image segmentation
Fecha
2021-12-29Registro en:
Rey, Andrea; Gambini, Juliana; Delrieux, Claudio Augusto; Texture descriptors for robust SAR image segmentation; Society of Photo-Optical Instrumentation Engineers; Journal of Applied Remote Sensing; 15; 4; 29-12-2021; 046511; 1-20
1931-3195
CONICET Digital
CONICET
Autor
Rey, Andrea
Gambini, Juliana
Delrieux, Claudio Augusto
Resumen
SAR (synthetic aperture radar) and PolSAR (polarimetric synthetic aperture radar) images fulfill a fundamental role in Earth observation, due to their advantages over optical images. However, the presence of speckle noise hinders their automatic interpretation and unsupervised use, rendering traditional segmentation tools ineffective. For this reason, advanced image segmentation models are sought to overcome the limitations that make an adequate treatment of speckled images difficult. We propose a procedure for SAR and PolSAR image classification, based on texture descriptors, that combines fractal dimension, a specific probability distribution function, Tsallis entropy, and the entropic index. A vector of local texture features is built using a set of reference regions, then a support vector machine classifier is applied. The proposed algorithm is tested with synthetic and actual monopolarimetric and polarimetric SAR imagery, exhibiting visually remarkable and robust results in coincidence with quantitative quality metrics as accuracy and F1-score.