Spacecraft Recovery & Remote Sensing, Volume. 45, Issue 3, 107(2024)

Road Extraction Method of High-Resolution Remote Sensing Images Based on Dense Blocks and Improved LinkNet

Zengyou WANG1,3, Xianhua ZHANG3, Rong LIU1,2、*, Zhigao CHEN1,2, and Wanghuang ZHU1,2
Author Affiliations
  • 1School of Surveying, Mapping and Spatial Information Engineering, East China University of Technology, Nanchang 330013, China
  • 2Key Laboratory of Mine Environmental Monitoring and Treatment in Poyang Lake Region, Ministry of Natural Resources, East China University of Technology, Nanchang 330013, China
  • 3Jiangxi College of Applied Technology, Ganzhou 341000, China
  • show less
    Figures & Tables(9)
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    • Table 1. Comparison of evaluation metrics for ablation experiment %

      View table
      View in Article

      Table 1. Comparison of evaluation metrics for ablation experiment %

      算法名称精确率平均交并比F1-score贡献率
      原始LinkNet78.6980.1777.82
      Dense Block改造后LinkNet80.4781.9479.611.77
      Dense Block改造后LinkNe+CMAM81.4582.8380.440.89
      Dense Block改造后LinkNe+ASPP81.2182.4680.070.52
      Dense Block改造后LinkNe+CMAM+ASPP82.1683.2181.661.27
    • Table 2. Different model extraction evaluation results %

      View table
      View in Article

      Table 2. Different model extraction evaluation results %

      网络模型精确率平均交并比F1-score
      U-Net77.2578.8276.53
      LinkNet78.6980.1777.82
      RoadNet81.1482.0580.33
      SegNet78.7280.4978.16
      D-LinkNet80.1381.7479.87
      本文网络82.1683.2181.66
    Tools

    Get Citation

    Copy Citation Text

    Zengyou WANG, Xianhua ZHANG, Rong LIU, Zhigao CHEN, Wanghuang ZHU. Road Extraction Method of High-Resolution Remote Sensing Images Based on Dense Blocks and Improved LinkNet[J]. Spacecraft Recovery & Remote Sensing, 2024, 45(3): 107

    Download Citation

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

    Category:

    Received: Jul. 26, 2023

    Accepted: --

    Published Online: Oct. 30, 2024

    The Author Email: Rong LIU (rliu@ecut.edu.cn)

    DOI:10.3969/j.issn.1009-8518.2024.03.011

    Topics