Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 60, Issue 4, 0401002(2023)

Building Extraction from Remote Sensing Images Based on Improved U-Net

Shu Jin1, Mo Guan1、*, Yuchan Bian2, and Shulei Wang1
Author Affiliations
  • 1School of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning, China
  • 2School of Software, Shenyang University of Technology, Shenyang 110870, Liaoning, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (7)
    Equations (9)
    References (20)
    Cited By (1)
    Tools
    Paper Information
    Topics
    Figures & Tables(7)
    MA-Unet structure

    Fig. 1. MA-Unet structure

    Download full size
    Spatial attention module

    Fig. 2. Spatial attention module

    Download full size
    CBAM structure

    Fig. 3. CBAM structure

    Download full size
    Contrast effects on the Massachusetts dataset. (a) Original images; (b) label images; (c) SegNet; (d) U-Net; (e) MA-Unet

    Fig. 4. Contrast effects on the Massachusetts dataset. (a) Original images; (b) label images; (c) SegNet; (d) U-Net; (e) MA-Unet

    Download full size
    Contrast effects on the WHU dataset. (a) Original images; (b) label images; (c) SegNet; (d) U-Net; (e) MA-Unet

    Fig. 5. Contrast effects on the WHU dataset. (a) Original images; (b) label images; (c) SegNet; (d) U-Net; (e) MA-Unet

    Download full size

    • Table 1. Comparison results on Massachusetts dataset

      View table

      Table 1. Comparison results on Massachusetts dataset

      ModelAccuracy/%Precision/%IoU/%
      U-Net89.8065.2867.61
      PSPnet89.4063.9166.36
      SegNet87.7661.8465.24
      MA-Unet91.5067.3569.24

    • Table 2. Comparison results on WHU dataset

      View table

      Table 2. Comparison results on WHU dataset

      ModelAccuracy/%Precision/%IoU/%
      U-Net96.8688.9786.34
      PSPnet96.6388.3286.56
      SegNet97.1286.2785.74
      MA-Unet97.9290.4188.65
    Tools

    Get Citation

    Copy Citation Text

    Shu Jin, Mo Guan, Yuchan Bian, Shulei Wang. Building Extraction from Remote Sensing Images Based on Improved U-Net[J]. Laser & Optoelectronics Progress, 2023, 60(4): 0401002

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Atmospheric Optics and Oceanic Optics

    Received: Nov. 19, 2021

    Accepted: Dec. 21, 2021

    Published Online: Feb. 14, 2023

    The Author Email: Guan Mo (42533040@qq.com)

    DOI:10.3788/LOP213004

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology