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

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

doi:10.1109/36.662728

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

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

Telecom Paris

Research output: Contribution to journal › Article › peer-review

Abstract

We 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. We present two local line detectors as well as a method for fusing information from these detectors. In the second global step, we 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.

Original language	English
Pages (from-to)	434-453
Number of pages	20
Journal	IEEE Transactions on Geoscience and Remote Sensing
Volume	36
Issue number	2
DOIs	https://doi.org/10.1109/36.662728
Publication status	Published - 1 Jan 1998

Access to Document

10.1109/36.662728

Cite this

@article{60883eef46244b79bfe1836afc023247,

title = "Detection of linear features in SAR images: Application to road network extraction",

abstract = "We 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. We present two local line detectors as well as a method for fusing information from these detectors. In the second global step, we 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.",

author = "Florence Tupin and Henri Maitre and Mangin, \{Jean Francois\} and Nicolas, \{Jean Marie\} and Eugene Pechersky",

year = "1998",

month = jan,

day = "1",

doi = "10.1109/36.662728",

language = "English",

volume = "36",

pages = "434--453",

journal = "IEEE Transactions on Geoscience and Remote Sensing",

issn = "0196-2892",

number = "2",

}

TY - JOUR

T1 - Detection of linear features in SAR images

T2 - Application to road network extraction

AU - Tupin, Florence

AU - Maitre, Henri

AU - Mangin, Jean Francois

AU - Nicolas, Jean Marie

AU - Pechersky, Eugene

PY - 1998/1/1

Y1 - 1998/1/1

N2 - We 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. We present two local line detectors as well as a method for fusing information from these detectors. In the second global step, we 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.

AB - We 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. We present two local line detectors as well as a method for fusing information from these detectors. In the second global step, we 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.

U2 - 10.1109/36.662728

DO - 10.1109/36.662728

M3 - Article

AN - SCOPUS:0032028665

SN - 0196-2892

VL - 36

SP - 434

EP - 453

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

IS - 2

ER -

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

Abstract

Access to Document

Fingerprint

Cite this