Loading…
NECEC 2017 has ended
View analytic
Wednesday, November 15 • 10:40 - 11:00
A NOVEL HIERARCHICAL FRAMEWORK FOR WETLAND CLASSIFICATION BASED ON A MULTI-FREQUENCY AND MULTI-POLARIZATION SAR DATA

Sign up or log in to save this to your schedule and see who's attending!

In this study, a novel hierarchical object-based Random Forest classification approach is proposed for discriminating between different wetland classes in a sub-region located in the northeastern portion of the Avalon Peninsula. Particularly, multi-polarization and multi-frequency SAR data, including X-band TerraSAR-X single polarized (HH), L-band ALOS-2 dual polarized (HH/HV), and C-band RADARSAT-2 fully polarized images, were applied at different classification levels. The overall accuracy and kappa coefficient were determined in each classification level for evaluating the classification results. The importance of input features was also determined using the variable importance obtained by Random Forest. Using this new hierarchical RF classification approach, an overall accuracy of up to 92% was obtained for classifying different land cover types in the study area.


Wednesday November 15, 2017 10:40 - 11:00
Crush area 180 Portugal Cove Road, St. John's, NL, Canada