Page Banner

United States Department of Agriculture

Agricultural Research Service

Title: Improving Global-Scale Land Cover Classification with Multi-Directional Viea-Angle Data and a Decision Tree Classifier

item Dao, Thanh

Submitted to: Geoscience and Remote Sensing Symposium Proceedings
Publication Type: Proceedings
Publication Acceptance Date: April 15, 2002
Publication Date: N/A

Technical Abstract: Recent investigations indicate that the Bidirectional Reflectance Distribution Function (BRDF) contains information that can be used to augment spectral information for improved land cover classification accuracy. Prior studies on the addition of BRDF information to improve land cover classification have been conducted at local or regional scales. Thus, the potential benefits of adding BRDF information to improve global scale land cover classification have not been explored. A decision tree classifier was used to evaluate the performance of POLDER imagery with and without the inclusion of BRDF information. BRDF metrics for the eight month POLDER archive were developed that describe the temporal evolution of the BRDF as captured by a semi-empirical BRDF model. The C5.0 classifier was applied with a boosting option with the temporal metrics for spectral albedo as input for a first test, and with spectral albedo and BRDF metrics for a second test. Results were evaluated against 20 random subsets of the training data. Addition of BRDF metrics reduced the mean, overall classification error rates by 3.15% (from 18.1% to 14.95%) with larger improvements for producer's accuracies of individual classes such as Grasslands (+8.71%), Urban areas (+8.02%), and Wetlands (+7.82%). User's accuracies for the Urban (+7.42%) and Evergreen Broadleaf Forests (+6.70%) classes also resulted. The results indicate improvements to land cover classification that are possible with data from the current Multiangle Imaging Spectroradiometer (MISR) and the next generation POLDER.

Last Modified: 4/22/2015
Footer Content Back to Top of Page