JavierAndresRedolfi/sartb/Install62017-10-05 14:32:17Jaarac52017-10-05 14:31:46Jaarac42017-10-05 14:31:12Jaarac32017-10-05 13:18:23Jaarac22017-10-05 13:11:59Jaarac12017-10-05 13:11:15JaaracFisher Vectors for PolSAR Image ClassificationCode used in paper: Javier Redolfi, Jorge Sánchez, and Ana Georgina Flesia "Fisher Vectors for PolSAR Image Classification" IEEE Geoscience and Remote Sensing Letters, 99, Septiembre 2017. (link)FeaturesThe library consist basically of the following python modules: PolSAR image manipulation: pseudocolor image generation, force SPD. PolSAR datasets: San Francisco Bay, Flevoland and Foulum. Train/test splits generation, manual selection of training points. Accuracy and Confusion Matrix computation. Smoothing algorithms: Potts, Graph Cut and Maximun. Unary potential generation from Complex Wishart, Real Wishart Mixture and FV (RWM based). Dependenciesvrl -> matplotlib numpy pygco -> pystruct -> scikit-image -> scikit-learn -> scikit-learn.org/ scipy Installation on Debian/Ubuntu(use sudo for Ubuntu) Install vrl using the README provided by the library. Install pygco using the gco_python/README.md provided by the library. Installing the moduleJust uncompress it. Example: Comparison with paper "Pol-SAR Classification Based on Generalized Polar Decomposition of Mueller Matrix"Download the dataset and uncompress it: -> Run the script: