Title :
Adaptive directional order filters and mathematical morphology for road network extraction on SAR images
Author :
Chanussot, Jocelyn ; Issa, Imad ; Lambert, Patrick
Author_Institution :
Lab. d´Autom. et de Microlnformatique Ind., Univ. de Savoie, Annecy, France
Abstract :
In this paper, a method for automatic detection of linear features in SAR images, with application to road network extraction is proposed. A pre-filtering step is firstly performed using an adaptive directional weighted order filter. It aims to smooth the noise, enhance edges and preserve thin anisotropie structures. Then, the detection operator is applied : it is based on a geometrical model of the roads and uses morphological directional operators with appropriate structuring elements. Results are presented on real SAR ERS-1 satellite data.
Keywords :
adaptive filters; feature extraction; radar imaging; remote sensing by radar; roads; smoothing methods; synthetic aperture radar; SAR images; adaptive directional weighted order filter; anisotropic structures; automatic detection; geometrical model; linear features; mathematical morphology; morphological detection operators; prefiltering step; real SAR ERS-1 satellite data; road network extraction; structuring elements; Feature extraction; Image edge detection; Image reconstruction; Maximum likelihood detection; Noise; Roads; Synthetic aperture radar; SAR images; directional filters; mathematical morphology; non linear filtering; road detection; weighted order filters;
Conference_Titel :
Signal Processing Conference (EUSIPCO 1998), 9th European
Conference_Location :
Rhodes
Print_ISBN :
978-960-7620-06-4
