Multisensor Classification of Wetland Environments using Airborne Multispectral and SAR Data
Research Objectives
Land cover classification using remotely sensed data is important for mapping and monitoring changes in coastal wetlands. Because of the similarity in spectral signatures and backscatter responses, we often find it difficult to separate individual classes within both herbaceous vegetation classes and upland shrubs using either optical or radar data.
Several approaches which utilize information from both multispectral and SAR sensors are investigated for classifying the landcover in these data sets. Differences in statistical characteristics of the data necessitate individual parametric models for observations from each sensor, so data are initially classified separately, then a final classification is obtained by combining results from the statistical models using different multisensor integration techniques. These integrated results are compared to single-sensor classification results, as well as to a multisensor classification based on artificial neural networks.
Area Description
Remotely Sensed Data
Results
Photo Gallery
|
Last Modified: Wed Apr 14, 1999
CSR/TSGC Team Web
|
