View in EDS HTML Full Text PDF Full Text

CAU 2 DNet: A Dual-Branch Deep Learning Network and a Dataset for Slum Recognition with Multi-Source Remote Sensing Data.

Saved in:
Bibliographic Details
Title: CAU 2 DNet: A Dual-Branch Deep Learning Network and a Dataset for Slum Recognition with Multi-Source Remote Sensing Data.
Authors: Lyu, Xi1 (AUTHOR), Zhang, Chenyu1,2 (AUTHOR), Miao, Lizhi1,2,3 (AUTHOR), Sun, Xiying3,4 (AUTHOR), Zhou, Xinxin1,2,5 (AUTHOR), Yue, Xinyi1 (AUTHOR), Sun, Zhongchang2,5 (AUTHOR), Pang, Yueyong1,2,3 (AUTHOR) pangyueyong@njupt.edu.cn
Source: Remote Sensing. Jul2025, Vol. 17 Issue 14, p2359. 28p.
Subjects: Slums, Deep learning, Remote sensing, Data integration, Geographic spatial analysis
Geographic Terms: São Paulo (Brazil : State)
Abstract: The efficient and precise identification of urban slums is a significant challenge for urban planning and sustainable development, as their morphological diversity and complex spatial distribution make it difficult to use traditional remote sensing inversion methods. Current deep learning (DL) methods mainly face challenges such as limited receptive fields and insufficient sensitivity to spatial locations when integrating multi-source remote sensing data, and high-quality datasets that integrate multi-spectral and geoscientific indicators to support them are scarce. In response to these issues, this study proposes a DL model (coordinate-attentive U2-DeepLab network [CAU2DNet]) that integrates multi-source remote sensing data. The model integrates the multi-scale feature extraction capability of U2-Net with the global receptive field advantage of DeepLabV3+ through a dual-branch architecture. Thereafter, the spatial semantic perception capability is enhanced by introducing the CoordAttention mechanism, and ConvNextV2 is adopted to optimize the backbone network of the DeepLabV3+ branch, thereby improving the modeling capability of low-resolution geoscientific features. The two branches adopt a decision-level fusion mechanism for feature fusion, which means that the results of each are weighted and summed using learnable weights to obtain the final output feature map. Furthermore, this study constructs the São Paulo slums dataset for model training due to the lack of a multi-spectral slum dataset. This dataset covers 7978 samples of 512 × 512 pixels, integrating high-resolution RGB images, Normalized Difference Vegetation Index (NDVI)/Modified Normalized Difference Water Index (MNDWI) geoscientific indicators, and POI infrastructure data, which can significantly enrich multi-source slum remote sensing data. Experiments have shown that CAU2DNet achieves an intersection over union (IoU) of 0.6372 and an F1 score of 77.97% on the São Paulo slums dataset, indicating a significant improvement in accuracy over the baseline model. The ablation experiments verify that the improvements made in this study have resulted in a 16.12% increase in precision. Moreover, CAU2DNet also achieved the best results in all metrics during the cross-domain testing on the WHU building dataset, further confirming the model's generalizability. [ABSTRACT FROM AUTHOR]
Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 186930948
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: CAU 2 DNet: A Dual-Branch Deep Learning Network and a Dataset for Slum Recognition with Multi-Source Remote Sensing Data.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Lyu%2C+Xi%22">Lyu, Xi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Chenyu%22">Zhang, Chenyu</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Miao%2C+Lizhi%22">Miao, Lizhi</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sun%2C+Xiying%22">Sun, Xiying</searchLink><relatesTo>3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhou%2C+Xinxin%22">Zhou, Xinxin</searchLink><relatesTo>1,2,5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yue%2C+Xinyi%22">Yue, Xinyi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sun%2C+Zhongchang%22">Sun, Zhongchang</searchLink><relatesTo>2,5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Pang%2C+Yueyong%22">Pang, Yueyong</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<i> pangyueyong@njupt.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Jul2025, Vol. 17 Issue 14, p2359. 28p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Slums%22">Slums</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Data+integration%22">Data integration</searchLink><br /><searchLink fieldCode="DE" term="%22Geographic+spatial+analysis%22">Geographic spatial analysis</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22São+Paulo+%28Brazil+%3A+State%29%22">São Paulo (Brazil : State)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The efficient and precise identification of urban slums is a significant challenge for urban planning and sustainable development, as their morphological diversity and complex spatial distribution make it difficult to use traditional remote sensing inversion methods. Current deep learning (DL) methods mainly face challenges such as limited receptive fields and insufficient sensitivity to spatial locations when integrating multi-source remote sensing data, and high-quality datasets that integrate multi-spectral and geoscientific indicators to support them are scarce. In response to these issues, this study proposes a DL model (coordinate-attentive U2-DeepLab network [CAU2DNet]) that integrates multi-source remote sensing data. The model integrates the multi-scale feature extraction capability of U2-Net with the global receptive field advantage of DeepLabV3+ through a dual-branch architecture. Thereafter, the spatial semantic perception capability is enhanced by introducing the CoordAttention mechanism, and ConvNextV2 is adopted to optimize the backbone network of the DeepLabV3+ branch, thereby improving the modeling capability of low-resolution geoscientific features. The two branches adopt a decision-level fusion mechanism for feature fusion, which means that the results of each are weighted and summed using learnable weights to obtain the final output feature map. Furthermore, this study constructs the São Paulo slums dataset for model training due to the lack of a multi-spectral slum dataset. This dataset covers 7978 samples of 512 × 512 pixels, integrating high-resolution RGB images, Normalized Difference Vegetation Index (NDVI)/Modified Normalized Difference Water Index (MNDWI) geoscientific indicators, and POI infrastructure data, which can significantly enrich multi-source slum remote sensing data. Experiments have shown that CAU2DNet achieves an intersection over union (IoU) of 0.6372 and an F1 score of 77.97% on the São Paulo slums dataset, indicating a significant improvement in accuracy over the baseline model. The ablation experiments verify that the improvements made in this study have resulted in a 16.12% increase in precision. Moreover, CAU2DNet also achieved the best results in all metrics during the cross-domain testing on the WHU building dataset, further confirming the model's generalizability. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=186930948
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/rs17142359
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 28
        StartPage: 2359
    Subjects:
      – SubjectFull: Slums
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Remote sensing
        Type: general
      – SubjectFull: Data integration
        Type: general
      – SubjectFull: Geographic spatial analysis
        Type: general
      – SubjectFull: São Paulo (Brazil : State)
        Type: general
    Titles:
      – TitleFull: CAU 2 DNet: A Dual-Branch Deep Learning Network and a Dataset for Slum Recognition with Multi-Source Remote Sensing Data.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Lyu, Xi
      – PersonEntity:
          Name:
            NameFull: Zhang, Chenyu
      – PersonEntity:
          Name:
            NameFull: Miao, Lizhi
      – PersonEntity:
          Name:
            NameFull: Sun, Xiying
      – PersonEntity:
          Name:
            NameFull: Zhou, Xinxin
      – PersonEntity:
          Name:
            NameFull: Yue, Xinyi
      – PersonEntity:
          Name:
            NameFull: Sun, Zhongchang
      – PersonEntity:
          Name:
            NameFull: Pang, Yueyong
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 07
              Text: Jul2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 20724292
          Numbering:
            – Type: volume
              Value: 17
            – Type: issue
              Value: 14
          Titles:
            – TitleFull: Remote Sensing
              Type: main
ResultId 1