View in EDS HTML Full Text PDF Full Text

A method for landslide identification and detection in high-precision aerial imagery: progressive CBAM-U-net model.

Saved in:
Bibliographic Details
Title: A method for landslide identification and detection in high-precision aerial imagery: progressive CBAM-U-net model.
Authors: Lin, Hanjie1 (AUTHOR), Li, Li1 (AUTHOR) lily6636694@163.com, Qiang, Yue1 (AUTHOR), Xu, Xinlong1 (AUTHOR), Liang, Siyu1 (AUTHOR), Chen, Tao1 (AUTHOR), Yang, Wenjun1 (AUTHOR), Zhang, Yi1 (AUTHOR)
Source: Earth Science Informatics. Dec2024, Vol. 17 Issue 6, p5487-5498. 12p.
Subject Terms: *Deep learning, *Databases, *Reference values, *Learning ability, *Generalization, *Landslides
Abstract: Rapid identification and detection of landslides is of significance for disaster damage assessment and post-disaster relief. However, U-net for rapid landslide identification and detection suffers from semantic gap and loss of spatial information. For this purpose, this paper proposed the U-net with a progressive Convolutional Block Attention Module (CBAM-U-net) for landslide boundary identification and extraction from high-precision aerial imagery. Firstly, 109 high-precision aerial landslide images were collected, and the original database was extended by data enhancement to strengthen generalization ability of models. Subsequently, the CBAM-U-net was constructed by introducing spatial attention module and channel attention module for each down-sampling process in U-net. Meanwhile, U-net, FCN and DeepLabv3 + are used as comparison models. Finally, 6 evaluation metrics were used to comprehensively assess the ability of models for landslide identification and segmentation. The results show that CBAM-U-net exhibited better recognition and segmentation accuracies compared to other models, with optimal values of average row correct, dice coefficient, global correct, IoU and mean IoU of 98.3, 0.877, 95, 88.5 and 90.2, respectively. U-net, DeepLab V3 + , and FCN tend to confuse bare ground and roads with landslides. In contrast, CBAM-U-net has stronger ability of feature learning, feature representation, feature refinement and adaptation.The proposed method can improve the problems of semantic gap and spatial information loss in U-net, and has better accuracy and robustness in recognizing and segmenting high-precision landslide images, which can provide certain reference value for the research of rapid landslide recognition and detection. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 180989346
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A method for landslide identification and detection in high-precision aerial imagery: progressive CBAM-U-net model.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Lin%2C+Hanjie%22">Lin, Hanjie</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Li%22">Li, Li</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> lily6636694@163.com</i><br /><searchLink fieldCode="AR" term="%22Qiang%2C+Yue%22">Qiang, Yue</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xu%2C+Xinlong%22">Xu, Xinlong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liang%2C+Siyu%22">Liang, Siyu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Tao%22">Chen, Tao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yang%2C+Wenjun%22">Yang, Wenjun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Yi%22">Zhang, Yi</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Earth+Science+Informatics%22">Earth Science Informatics</searchLink>. Dec2024, Vol. 17 Issue 6, p5487-5498. 12p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Databases%22">Databases</searchLink><br />*<searchLink fieldCode="DE" term="%22Reference+values%22">Reference values</searchLink><br />*<searchLink fieldCode="DE" term="%22Learning+ability%22">Learning ability</searchLink><br />*<searchLink fieldCode="DE" term="%22Generalization%22">Generalization</searchLink><br />*<searchLink fieldCode="DE" term="%22Landslides%22">Landslides</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Rapid identification and detection of landslides is of significance for disaster damage assessment and post-disaster relief. However, U-net for rapid landslide identification and detection suffers from semantic gap and loss of spatial information. For this purpose, this paper proposed the U-net with a progressive Convolutional Block Attention Module (CBAM-U-net) for landslide boundary identification and extraction from high-precision aerial imagery. Firstly, 109 high-precision aerial landslide images were collected, and the original database was extended by data enhancement to strengthen generalization ability of models. Subsequently, the CBAM-U-net was constructed by introducing spatial attention module and channel attention module for each down-sampling process in U-net. Meanwhile, U-net, FCN and DeepLabv3 + are used as comparison models. Finally, 6 evaluation metrics were used to comprehensively assess the ability of models for landslide identification and segmentation. The results show that CBAM-U-net exhibited better recognition and segmentation accuracies compared to other models, with optimal values of average row correct, dice coefficient, global correct, IoU and mean IoU of 98.3, 0.877, 95, 88.5 and 90.2, respectively. U-net, DeepLab V3 + , and FCN tend to confuse bare ground and roads with landslides. In contrast, CBAM-U-net has stronger ability of feature learning, feature representation, feature refinement and adaptation.The proposed method can improve the problems of semantic gap and spatial information loss in U-net, and has better accuracy and robustness in recognizing and segmenting high-precision landslide images, which can provide certain reference value for the research of rapid landslide recognition and detection. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=180989346
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s12145-024-01465-6
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 5487
    Subjects:
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Databases
        Type: general
      – SubjectFull: Reference values
        Type: general
      – SubjectFull: Learning ability
        Type: general
      – SubjectFull: Generalization
        Type: general
      – SubjectFull: Landslides
        Type: general
    Titles:
      – TitleFull: A method for landslide identification and detection in high-precision aerial imagery: progressive CBAM-U-net model.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Lin, Hanjie
      – PersonEntity:
          Name:
            NameFull: Li, Li
      – PersonEntity:
          Name:
            NameFull: Qiang, Yue
      – PersonEntity:
          Name:
            NameFull: Xu, Xinlong
      – PersonEntity:
          Name:
            NameFull: Liang, Siyu
      – PersonEntity:
          Name:
            NameFull: Chen, Tao
      – PersonEntity:
          Name:
            NameFull: Yang, Wenjun
      – PersonEntity:
          Name:
            NameFull: Zhang, Yi
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Text: Dec2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 18650473
          Numbering:
            – Type: volume
              Value: 17
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Earth Science Informatics
              Type: main
ResultId 1