Bayesian Fusion of Multi-Scale Detectors for Road Extraction from SAR Images
This paper introduces an innovative road network extraction algorithm using synthetic aperture radar (SAR) imagery for improving the accuracy of road extraction. The state-of-the-art approaches, such as fraction extraction and road network optimization, failed to obtain continuous road segments in s...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-01-01
|
Series: | ISPRS International Journal of Geo-Information |
Subjects: | |
Online Access: | http://www.mdpi.com/2220-9964/6/1/26 |
id |
doaj-b8b206df0119428d886d91c7e8699f5b |
---|---|
record_format |
Article |
spelling |
doaj-b8b206df0119428d886d91c7e8699f5b2020-11-24T23:16:34ZengMDPI AGISPRS International Journal of Geo-Information2220-99642017-01-01612610.3390/ijgi6010026ijgi6010026Bayesian Fusion of Multi-Scale Detectors for Road Extraction from SAR ImagesRui Xu0Chu He1Xinlong Liu2Dong Chen3Qianqing Qin4State Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, ChinaState Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, ChinaElectronic and Information School, Wuhan University, Wuhan 430079, ChinaATR Key Lab, National University of Defense Technology, Changsha 410073, ChinaState Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430072, ChinaThis paper introduces an innovative road network extraction algorithm using synthetic aperture radar (SAR) imagery for improving the accuracy of road extraction. The state-of-the-art approaches, such as fraction extraction and road network optimization, failed to obtain continuous road segments in separate successions, since the optimization could not change the parts ignored by the fraction extraction. In this paper, the proposed algorithm integrates the fraction extraction and optimization procedure simultaneously to extract the road network: (1) the Bayesian framework is utilized to transfer the road network extraction to joint reasoning of the likelihood of fraction extraction and the priority of network optimization; (2) the multi-scale linear feature detector (MLFD) and the network optimization beamlet are introduced; (3) the conditional random field (CRF) is used to reason jointly. The result is the global optimum since the fraction extraction and network optimization are exploited at the same time. The proposed algorithm solves the problem that the fractions are bound to reduce in the process of network optimization and has demonstrated effectiveness in real SAR images applications.http://www.mdpi.com/2220-9964/6/1/26synthetic aperture radarroad networkconditional random fieldBayesianmulti-scale linear feature detector |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Rui Xu Chu He Xinlong Liu Dong Chen Qianqing Qin |
spellingShingle |
Rui Xu Chu He Xinlong Liu Dong Chen Qianqing Qin Bayesian Fusion of Multi-Scale Detectors for Road Extraction from SAR Images ISPRS International Journal of Geo-Information synthetic aperture radar road network conditional random field Bayesian multi-scale linear feature detector |
author_facet |
Rui Xu Chu He Xinlong Liu Dong Chen Qianqing Qin |
author_sort |
Rui Xu |
title |
Bayesian Fusion of Multi-Scale Detectors for Road Extraction from SAR Images |
title_short |
Bayesian Fusion of Multi-Scale Detectors for Road Extraction from SAR Images |
title_full |
Bayesian Fusion of Multi-Scale Detectors for Road Extraction from SAR Images |
title_fullStr |
Bayesian Fusion of Multi-Scale Detectors for Road Extraction from SAR Images |
title_full_unstemmed |
Bayesian Fusion of Multi-Scale Detectors for Road Extraction from SAR Images |
title_sort |
bayesian fusion of multi-scale detectors for road extraction from sar images |
publisher |
MDPI AG |
series |
ISPRS International Journal of Geo-Information |
issn |
2220-9964 |
publishDate |
2017-01-01 |
description |
This paper introduces an innovative road network extraction algorithm using synthetic aperture radar (SAR) imagery for improving the accuracy of road extraction. The state-of-the-art approaches, such as fraction extraction and road network optimization, failed to obtain continuous road segments in separate successions, since the optimization could not change the parts ignored by the fraction extraction. In this paper, the proposed algorithm integrates the fraction extraction and optimization procedure simultaneously to extract the road network: (1) the Bayesian framework is utilized to transfer the road network extraction to joint reasoning of the likelihood of fraction extraction and the priority of network optimization; (2) the multi-scale linear feature detector (MLFD) and the network optimization beamlet are introduced; (3) the conditional random field (CRF) is used to reason jointly. The result is the global optimum since the fraction extraction and network optimization are exploited at the same time. The proposed algorithm solves the problem that the fractions are bound to reduce in the process of network optimization and has demonstrated effectiveness in real SAR images applications. |
topic |
synthetic aperture radar road network conditional random field Bayesian multi-scale linear feature detector |
url |
http://www.mdpi.com/2220-9964/6/1/26 |
work_keys_str_mv |
AT ruixu bayesianfusionofmultiscaledetectorsforroadextractionfromsarimages AT chuhe bayesianfusionofmultiscaledetectorsforroadextractionfromsarimages AT xinlongliu bayesianfusionofmultiscaledetectorsforroadextractionfromsarimages AT dongchen bayesianfusionofmultiscaledetectorsforroadextractionfromsarimages AT qianqingqin bayesianfusionofmultiscaledetectorsforroadextractionfromsarimages |
_version_ |
1725586718497701888 |