Paper
28 January 2002 Extraction of industrial buildings from stereoscopic airborne radar images
Elisabeth Simonetto, Helene Oriot, Rene Garello
Author Affiliations +
Proceedings Volume 4543, SAR Image Analysis, Modeling, and Techniques IV; (2002) https://doi.org/10.1117/12.453960
Event: International Symposium on Remote Sensing, 2001, Toulouse, France
Abstract
This paper deals with automatic extraction of 3-D buildings from stereoscopic high-resolution images recorded by the RAMSES sensor. Roofs are not very textured whereas typical strong L-shaped echoes are visible. These returns generally result from dihedral corners between ground and structures. They provide a part of the building footprints and the ground altitude, but not building heights. Thus, we present an adapted process including two main steps: - stereoscopic structure extraction from L-shaped echoes. Buildings are detected on each image using the Hough transform. Then they are recognised during a stereoscopic refinement stage based on a criterion minimisation. - height measurement. As most of previous extracted footprints indicate the ground altitude, building heights are found by monoscopic and stereoscopic measures. Between structures, ground altitudes are obtained by a dense matching process. This processing is applied on an industrial scene. Results are compared with a ground truth. Advantages and limitations of the method are brought out.
© (2002) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Elisabeth Simonetto, Helene Oriot, and Rene Garello "Extraction of industrial buildings from stereoscopic airborne radar images", Proc. SPIE 4543, SAR Image Analysis, Modeling, and Techniques IV, (28 January 2002); https://doi.org/10.1117/12.453960
Lens.org Logo
CITATIONS
Cited by 8 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Buildings

Image segmentation

Binary data

Image processing

Radar

3D image processing

Hough transforms

Back to Top