Use of Landsat TM image segmentation for smoothing ERS-1 SAR imagery in combined multi-sensor landscape classification

Abstract

The combination of Landsat TM and ERS-1 SAR data can potentially lead to improved land cover mapping. Initially however SAR data must undergo speckle noise filtering. In southern Europe where land cover units are very small conventional filtering techniques can remove valuable information. The paper describes the potential use of segmentation of Landsat TM data to describe boundaries which can serve as a basis for SAR speckle noise filtering prior to incorporation in integrated multi-sensor classification.<>