Title :
Automatic extraction of geometric structures for 3D reconstruction from tomographic SAR data
Author :
Hondt, Olivier D. ; Guillaso, Stéphane ; Hellwich, Olaf
Author_Institution :
Comput. Vision & Remote Sensing Group, Tech. Univ. of Berlin, Berlin, Germany
Abstract :
In this paper we introduce a method that allows automatic extraction of planar features from tomographic SAR data. Our approach takes advantage of the spatial connectivity of pixels from tomographic height maps in order to retrieve planar patches from noise corrupted complex scenes. We demonstrate how our method outperforms the well-known RANSAC algorithm over synthetic and experimental data.
Keywords :
data acquisition; feature extraction; radar imaging; signal reconstruction; synthetic aperture radar; 3D reconstruction; RANSAC algorithm; automatic extraction; experimental data; geometric structures; noise corrupted complex scenes; planar features; planar patches; spatial connectivity; synthetic data; tomographic SAR data; tomographic height maps; Data mining; Feature extraction; Image reconstruction; Noise; Robustness; Synthetic aperture radar; Tomography; 3D reconstruction; SAR; feature extraction; primitives; tomography;
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2012 IEEE International
Conference_Location :
Munich
Print_ISBN :
978-1-4673-1160-1
Electronic_ISBN :
2153-6996
DOI :
10.1109/IGARSS.2012.6350507
