Radar stereo- and interferometry-derived digital elevation models: comparison and combination using Radarsat and ERS-2 imagery

Abstract

In this experiment, we derive and compare radar stereo and interferometric digital elevation models (DEMs) of a study site in Djibouti, East Africa. A Radarsat stereo pair, as well as Radarsat and ERS-2 interferometric data, comprise the test images. The primary objective of the study was to analyse and compare the results obtained by the two techniques and explore possible synergisms between them. We find that in regions of high coherence, the DEMs produced by interferometry are of much better quality than the stereo result. However, the corresponding error histograms also show some pronounced errors due to decorrelation and phase-unwrapping problems on forested mountain slopes. On the other hand, the more robust stereo reconstruction, with an error standard deviation of 45 m, is able to capture the general terrain shape, although finer surface details are lost. In the second part of our experiment, we demonstrate that merging the stereoscopic and interferometric DEMs by applying a user-defined weighting function to a filtered coherence map can significantly improve the accuracy of the computed elevation maps.