Exploring the applicability of semi-global matching for SAR-optical stereogrammetry of Urban scenes

Nowadays, a huge archive of data from different satellite sensors is available for diverse objectives. While every new sensor provides data with ever higher resolution and more sophisticated special properties, using the data acquired by only one sensor might sometimes still not be enough. As a result, data fusion techniques can be applied with the aim of jointly exploiting data from multiple sensors. One example is to produce 3D information from optical and SAR imagery by employing stereogrammetric methods. This paper investigates the application of the semi-global matching (SGM) framework for 3D reconstruction from SAR-optical image pairs. For this objective, first a multi-sensor block adjustment is carried out to align the optical image with a corresponding SAR image using an RPC-based formulation of the imaging models. Then, a dense image matching, SGM is implemented to investigate its potential for multi-sensor 3D reconstruction. While the results achieved with Worldview-2 and TerraSAR-X images demonstrate the general feasibility of SAR-optical stereogrammetry, they also show the limited applicability of SGM for this task in its out-of-the-box formulation.