Estimating Digital Terrain Model in forest areas from TanDEM-X and Stereo-photogrammetric technique by means of Random Volume over Ground model

Abstract:

The Digital Terrain Model (DTM) in forest areas is invaluable information for various environmental, hydrological and ecological studies, for example, watershed delineation, vegetation canopy height, water dynamic modeling, forest biomass and carbon estimations. There are few solutions to extract bare-earth Digital Elevation Model information. Airborne lidar systems are widely and successfully used for estimating bare-earth DEMs with centimeter-order accuracy and high spatial resolution. However, expensive cost of operation and small image coverage prevent the use of airborne lidar sensors for large- or global-scale. Although IceSAT/GLAS (Ice, Cloud, and Land Elevation Satellite/Geoscience Laser Altimeter System) lidar data sets have been available for global DTM estimate with relatively lower cost, the large footprint size of 70 m and the interval of 172 m are insufficient for various applications.

In this study we propose to extract higher resolution bare-earth DEM over vegetated areas from the combination of interferometric complex coherence from single-pass TanDEM-X (TDX) data at HH polarization and Digital Surface Model (DSM) derived from high-resolution WorldView (WV) images by means of random volume over ground (RVoG) model. The RVoG model is a widely and successfully used model for polarimetric SAR interferometry (Pol-InSAR) forest canopy height inversion. The bare-earth DEM is obtained by complex volume decorrelation in the RVoG model with the DSM estimated by stereo-photogrammetric technique. Forest canopy height can be estimated by subtracting the estimated bare-earth model from the DSM. Finally, the DTM from airborne lidar system was used to validate the bare-earth DEM and forest canopy height estimates.