Improvement of road extraction in high resolution SAR data by a context-based approach

Virginie Amberg (1, 2, 3) , Marc Spigai (4) , Martial Coulon (2, 3) , Philippe Marthon (5, 3)

1 Alcatel Space Industries Toulouse (FRANCE)
2 IRIT-SC - Signal et Communications
3 Toulouse INP - Institut National Polytechnique (Toulouse)
4 TAS - Thales Alenia Space [Toulouse]
5 IRIT-TCI - Traitement et Compréhension d’Images

This paper deals with the problem of road extraction in high resolution SAR data. The presented method is an improvement of previous works. The process is an almost automatic algorithm based on a Hough transform and a road tracking algorithm. The main limitations of the process are due to the road context. First investigations to exploit contextual information in the process are presented.

Keywords: Data mining; Roads; Layout; Radar tracking; Object detection; Synthetic aperture radar; Urban areas; Remote sensing; Surveillance; Telecommunication traffic

Domains: Signal and Image Processing

Virginie Amberg, Marc Spigai, Martial Coulon, Philippe Marthon. Improvement of road extraction in high resolution SAR data by a context-based approach. IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2005), Jul 2005, Séoul, South Korea. ⟨10.1109/IGARSS.2005.1526218⟩. ⟨hal-03608801⟩