The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-1/W1
https://doi.org/10.5194/isprs-archives-XLII-1-W1-639-2017
https://doi.org/10.5194/isprs-archives-XLII-1-W1-639-2017
31 May 2017
 | 31 May 2017

SAR AND OBLIQUE AERIAL OPTICAL IMAGE FUSION FOR URBAN AREA IMAGE SEGMENTATION

J. Fagir, A. Schubert, M. Frioud, and D. Henke

Keywords: Remote Sensing, Urban Area, Image Fusion, Image Segmentation, SAR, RGB Image

Abstract. The fusion of synthetic aperture radar (SAR) and optical data is a dynamic research area, but image segmentation is rarely treated. While a few studies use low-resolution nadir-view optical images, we approached the segmentation of SAR and optical images acquired from the same airborne platform – leading to an oblique view with high resolution and thus increased complexity. To overcome the geometric differences, we generated a digital surface model (DSM) from adjacent optical images and used it to project both the DSM and SAR data into the optical camera frame, followed by segmentation with each channel. The fused segmentation algorithm was found to out-perform the single-channel version.