Title :
Comparison of prefiltering operators for road network extraction in SAR images
Author :
Bolon, P. ; Chanussot, Jocelyn ; Issa, I. ; Lambert, Peter
Author_Institution :
Lab. d´Autom. et MicroInf. Ind., Savoie Univ., Chambery, France
Abstract :
The problem of detection of road networks in Synthetic Aperture Radar (SAR) images is addressed. This task is important for the registration of SAR images to existing maps and for perfect superposition of multitemporal SAR images. SAR image analysis is a difficult task because of speckle noise and textures and low signal to noise ratios. The paper focuses on the comparison of filter performances in terms of road extraction. The study points out the interest of nonlinear adaptive filtering techniques. On the other hand, it is shown that techniques dedicated to speckle noise filtering are not always the most suited to road network extraction.
Keywords :
adaptive filters; image registration; nonlinear filters; object detection; radar imaging; synthetic aperture radar; SAR image analysis; SAR image registration; SAR images; Synthetic Aperture Radar; filter performances; multitemporal SAR images; noise filtering; nonlinear adaptive filtering techniques; perfect superposition; prefiltering operators; road network extraction; signal to noise ratios; speckle noise; Data mining; Image segmentation; Intelligent networks; Intersymbol interference; Pixel; Roads; Shape; Signal to noise ratio; Speckle; Synthetic aperture radar;
Conference_Titel :
Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on
Conference_Location :
Kobe
Print_ISBN :
0-7803-5467-2
DOI :
10.1109/ICIP.1999.823033
