Detection of linear features in SAR images: application to road network extraction

Author

Tupin, Florence ; Maitre, Henri ; Mangin, Jean-Francois ; Nicolas, Jean-Marie ; Pechersky, Eugene

Author_Institution

Ecole Nat. Superieure des Telecommun., Paris, France

Volume

36

Issue

2

fYear

1998

fDate

3/1/1998 12:00:00 AM

Firstpage

434

Lastpage

453

Abstract

The authors propose a two-step algorithm for almost unsupervised detection of linear structures, in particular, main axes in road networks, as seen in synthetic aperture radar (SAR) images. The first step is local and is used to extract linear features from the speckle radar image, which are treated as road-segment candidates. The authors present two local line detectors as well as a method for fusing information from these detectors. In the second global step, they identify the real roads among the segment candidates by defining a Markov random field (MRF) on a set of segments, which introduces contextual knowledge about the shape of road objects. The influence of the parameters on the road detection is studied and results are presented for various real radar images

Keywords

Markov processes; feature extraction; geophysical signal processing; geophysical techniques; image segmentation; radar imaging; remote sensing by radar; synthetic aperture radar; Markov random field; SAR; SAR image processing; contextual knowledge; geophysical measurement technique; image segmentation; land surface; linear feature extraction; linear structure; radar imaging; radar remote sensing; road network; speckle radar image; synthetic aperture radar; terrain mapping; two-step algor; unsupervised detection; Computer vision; Data mining; Detectors; Feature extraction; Image segmentation; Radar detection; Radar imaging; Roads; Speckle; Synthetic aperture radar;

fLanguage

English

Journal_Title

Geoscience and Remote Sensing, IEEE Transactions on

Publisher

ieee

ISSN

0196-2892

Type

jour

DOI

10.1109/36.662728

Filename

662728