File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Leveraging optical and SAR data with a UU-Net for large-scale road extraction

TitleLeveraging optical and SAR data with a UU-Net for large-scale road extraction
Authors
KeywordsRoad
Optical
SAR
OSM
U-Net
Issue Date2021
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/jag
Citation
International Journal of Applied Earth Observation and Geoinformation, 2021, v. 103, p. article no. 102498 How to Cite?
AbstractRoad datasets are fundamental and imperative for traffic management and urban planning. Different high-resolution optical remote sensing images are widely used for automatic road extraction but the results are usually limited to local scale and spectral confusions in barren and cropland, while accurate large-scale road extraction remains challenging. In this study, we incorporated medium resolution optical and SAR data, i.e., 10-meter resolution Sentinel-1 and Sentinel-2, for road extraction at a large scale and evaluated the contribution of different data sources. We developed a United U-Net (UU-Net) to fuse optical and SAR data for road extraction, which was trained and evaluated on a large-scale multisource road extraction dataset. The UU-Net achieved better accuracy than traditional deep convolutional networks with optical or SAR data alone, which obtained an average F1 of 0.5502 and an average IoU of 0.4021, outperforming in 160 out of 200 (80%) 0.5-by-0.5 degree evaluation grids. The results indicated that SAR contributes more to road extraction in barren land, while optical data contributes more to large slope areas. The road accuracy is positively related to elevation and urban percentage, which distributes higher in eastern China and lower in western. The road centerline from 10 m road showed comparable results with that from Open Street Map (OSM), indicating its promising applications to support large-scale urban transportation studies.
Persistent Identifierhttp://hdl.handle.net/10722/306538
ISSN
2023 Impact Factor: 7.6
2023 SCImago Journal Rankings: 2.108
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLin, Y-
dc.contributor.authorWan, L-
dc.contributor.authorZhang, H-
dc.contributor.authorWEI, S-
dc.contributor.authorMa, P-
dc.contributor.authorLi, Y-
dc.contributor.authorZhao, Z-
dc.date.accessioned2021-10-22T07:36:03Z-
dc.date.available2021-10-22T07:36:03Z-
dc.date.issued2021-
dc.identifier.citationInternational Journal of Applied Earth Observation and Geoinformation, 2021, v. 103, p. article no. 102498-
dc.identifier.issn1569-8432-
dc.identifier.urihttp://hdl.handle.net/10722/306538-
dc.description.abstractRoad datasets are fundamental and imperative for traffic management and urban planning. Different high-resolution optical remote sensing images are widely used for automatic road extraction but the results are usually limited to local scale and spectral confusions in barren and cropland, while accurate large-scale road extraction remains challenging. In this study, we incorporated medium resolution optical and SAR data, i.e., 10-meter resolution Sentinel-1 and Sentinel-2, for road extraction at a large scale and evaluated the contribution of different data sources. We developed a United U-Net (UU-Net) to fuse optical and SAR data for road extraction, which was trained and evaluated on a large-scale multisource road extraction dataset. The UU-Net achieved better accuracy than traditional deep convolutional networks with optical or SAR data alone, which obtained an average F1 of 0.5502 and an average IoU of 0.4021, outperforming in 160 out of 200 (80%) 0.5-by-0.5 degree evaluation grids. The results indicated that SAR contributes more to road extraction in barren land, while optical data contributes more to large slope areas. The road accuracy is positively related to elevation and urban percentage, which distributes higher in eastern China and lower in western. The road centerline from 10 m road showed comparable results with that from Open Street Map (OSM), indicating its promising applications to support large-scale urban transportation studies.-
dc.languageeng-
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/jag-
dc.relation.ispartofInternational Journal of Applied Earth Observation and Geoinformation-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.subjectRoad-
dc.subjectOptical-
dc.subjectSAR-
dc.subjectOSM-
dc.subjectU-Net-
dc.titleLeveraging optical and SAR data with a UU-Net for large-scale road extraction-
dc.typeArticle-
dc.identifier.emailZhang, H: zhanghs@hku.hk-
dc.identifier.authorityZhang, H=rp02616-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1016/j.jag.2021.102498-
dc.identifier.scopuseid_2-s2.0-85120954931-
dc.identifier.hkuros329224-
dc.identifier.volume103-
dc.identifier.spagearticle no. 102498-
dc.identifier.epagearticle no. 102498-
dc.identifier.isiWOS:000696913500002-
dc.publisher.placeNetherlands-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats