Title :
Variable importance and random forest classification using RADARSAT-2 PolSAR data
Author :
Hariharan, Siddharth ; Tirodkar, Siddhesh ; De, Shaunak ; Bhattacharya, Avik
Author_Institution :
Centre of Studies in Resources Eng., IIT Bombay, Mumbai, India
Abstract :
In this paper we have classified Polarimetric Synthetic Aperture Radar (PolSAR) data using the Random Forest (RF) classifier. The variables were ranked using the mean decrease in accuracy permutation method for each terrain class. RADARSAT-2 (RS-2) data acquired over Mumbai, India was used in this study. This technique is able to efficiently classify the dataset, as well as rank the parameters used in that classifier.
Keywords :
geophysical image processing; geophysical techniques; image classification; radar polarimetry; remote sensing by radar; synthetic aperture radar; India; Mumbai; RADARSAT-2 PolSAR data; permutation method; polarimetric synthetic aperture radar; random forest classification; Accuracy; Correlation; Entropy; Radio frequency; Scattering; Support vector machines; Vegetation; Polarimetry; Random Forest Classification; Synthetic Aperture Radar;
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International
Conference_Location :
Quebec City, QC
DOI :
10.1109/IGARSS.2014.6946649
