Road network extraction in VHR SAR images of urban and suburban areas by means of class-aided feature-level fusion

Karin Hedman; Uwe Stilla; Gianni Lisini; Paolo Gamba

doi:10.1109/TGRS.2009.2025123

Road network extraction in VHR SAR images of urban and suburban areas by means of class-aided feature-level fusion

Karin Hedman, Uwe Stilla, Gianni Lisini, Paolo Gamba

Associate Professorship of Photogrammetry and Remote Sensing

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

52 Scopus citations

Abstract

In this paper, we propose to combine two road extractors from very high resolution synthetic aperture radar scenes: one more successful in rural areas and one explicitly designed for urban areas. In order to get the best combination of both, a rapid mapping filter for discriminating rural and urban scenes is utilized. Finally, the results are fused on a feature level and connected by means of a network optimization. The approach is tested and evaluated on TerraSAR-X data containing complex urban areas and urban-rural fringe scenes.

Original language	English
Article number	2025123
Pages (from-to)	1294-1296
Number of pages	3
Journal	IEEE Transactions on Geoscience and Remote Sensing
Volume	48
Issue number	3 PART 1
DOIs	https://doi.org/10.1109/TGRS.2009.2025123
State	Published - 2010

Keywords

Markov random field (MRF)
Rapid mapping
Road extraction
TerraSAR-X

Access to Document

10.1109/TGRS.2009.2025123

Cite this

@article{84acdf2116c14de09a3ffab948922850,

title = "Road network extraction in VHR SAR images of urban and suburban areas by means of class-aided feature-level fusion",

abstract = "In this paper, we propose to combine two road extractors from very high resolution synthetic aperture radar scenes: one more successful in rural areas and one explicitly designed for urban areas. In order to get the best combination of both, a rapid mapping filter for discriminating rural and urban scenes is utilized. Finally, the results are fused on a feature level and connected by means of a network optimization. The approach is tested and evaluated on TerraSAR-X data containing complex urban areas and urban-rural fringe scenes.",

keywords = "Markov random field (MRF), Rapid mapping, Road extraction, TerraSAR-X",

author = "Karin Hedman and Uwe Stilla and Gianni Lisini and Paolo Gamba",

year = "2010",

doi = "10.1109/TGRS.2009.2025123",

language = "English",

volume = "48",

pages = "1294--1296",

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

issn = "0196-2892",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3 PART 1",

}

TY - JOUR

T1 - Road network extraction in VHR SAR images of urban and suburban areas by means of class-aided feature-level fusion

AU - Hedman, Karin

AU - Stilla, Uwe

AU - Lisini, Gianni

AU - Gamba, Paolo

PY - 2010

Y1 - 2010

N2 - In this paper, we propose to combine two road extractors from very high resolution synthetic aperture radar scenes: one more successful in rural areas and one explicitly designed for urban areas. In order to get the best combination of both, a rapid mapping filter for discriminating rural and urban scenes is utilized. Finally, the results are fused on a feature level and connected by means of a network optimization. The approach is tested and evaluated on TerraSAR-X data containing complex urban areas and urban-rural fringe scenes.

AB - In this paper, we propose to combine two road extractors from very high resolution synthetic aperture radar scenes: one more successful in rural areas and one explicitly designed for urban areas. In order to get the best combination of both, a rapid mapping filter for discriminating rural and urban scenes is utilized. Finally, the results are fused on a feature level and connected by means of a network optimization. The approach is tested and evaluated on TerraSAR-X data containing complex urban areas and urban-rural fringe scenes.

KW - Markov random field (MRF)

KW - Rapid mapping

KW - Road extraction

KW - TerraSAR-X

UR - http://www.scopus.com/inward/record.url?scp=77957933896&partnerID=8YFLogxK

U2 - 10.1109/TGRS.2009.2025123

DO - 10.1109/TGRS.2009.2025123

M3 - Article

AN - SCOPUS:77957933896

SN - 0196-2892

VL - 48

SP - 1294

EP - 1296

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

IS - 3 PART 1

M1 - 2025123

ER -

Road network extraction in VHR SAR images of urban and suburban areas by means of class-aided feature-level fusion

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this