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. 61, Issue 4, 0428007(2024)

Remote Sensing Road Extraction Combining Contextual Information and Multi-Layer Features Fusion

Guo Chen1,2 and Likun Hu1,2、*
Author Affiliations
  • 1School of Electrical Engineering, Guangxi University, Nanning 530004, Guangxi, China
  • 2Advanced Measurement & Control & Intelligent Power Research Center, Guangxi University, Nanning 530004, Guangxi, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (15)
    Equations (17)
    References (28)
    Tools
    Paper Information
    Topics
    Figures & Tables(15)
    Structure of CMF-UNet

    Fig. 1. Structure of CMF-UNet

    Download full size
    Pyramid feature aggregation module

    Fig. 2. Pyramid feature aggregation module

    Download full size
    Channel attention module

    Fig. 3. Channel attention module

    Download full size
    Spatial attention module

    Fig. 4. Spatial attention module

    Download full size
    CBAM

    Fig. 5. CBAM

    Download full size
    Dilated convolutiona in D-LinkNet

    Fig. 6. Dilated convolutiona in D-LinkNet

    Download full size
    Multis-scale context extraction module

    Fig. 7. Multis-scale context extraction module

    Download full size
    Massachusetts Roads dataset

    Fig. 8. Massachusetts Roads dataset

    Download full size
    CHN6-CUG dataset

    Fig. 9. CHN6-CUG dataset

    Download full size
    Loss curves of the CMF-UNet training process

    Fig. 10. Loss curves of the CMF-UNet training process

    Download full size
    Segmentation results on Massachusetts Roads

    Fig. 11. Segmentation results on Massachusetts Roads

    Download full size
    Segmentation results on CHN6-CUG

    Fig. 12. Segmentation results on CHN6-CUG

    Download full size

    • Table 1. Ablation study

      View table

      Table 1. Ablation study

      BasePFAMSCEDatasetRrecall /%sF1 /%RIoU /%
      √MassachusettsRoads69.8375.5960.79
      CHN6-CUG72.0977.7363.57
      √√MassachusettsRoads70.7176.2961.67
      CHN6-CUG75.1878.5664.7
      √√MassachusettsRoads72.1376.5662.08
      CHN6-CUG74.6878.865.02
      √√√MassachusettsRoads72.5276.8762.29
      CHN6-CUG76.2779.1165.45

    • Table 2. Comparison of algorithm complexity

      View table

      Table 2. Comparison of algorithm complexity

      ModelFLOPs /109Parameter quantity /106
      PSPNet118.4546.72
      D-LinkNet67.3331.09
      DeepLabv3+166.8454.71
      U-Net451.6724.89
      CMF-UNet451.7324.93

    • Table 3. Test results on different datasets

      View table

      Table 3. Test results on different datasets

      ModelMassachusetts RoadsCHN6-CUG
      Rrecall /%sF1 /%RIoU /%Rrecall /%sF1 /%RIoU /%
      PSPNet30.0939.9524.9630.5842.7227.17
      U-Net69.8375.5960.7972.0977.7363.57
      DeepLabv3+68.7366.3749.6670.0768.6452.26
      D-LinkNet70.8675.0460.5270.6370.3958.74
      CMF-UNet75.6077.6163.4178.5679.2665.61
    Tools

    Get Citation

    Copy Citation Text

    Guo Chen, Likun Hu. Remote Sensing Road Extraction Combining Contextual Information and Multi-Layer Features Fusion[J]. Laser & Optoelectronics Progress, 2024, 61(4): 0428007

    Download Citation

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

    Category: Remote Sensing and Sensors

    Received: Apr. 3, 2023

    Accepted: Jun. 20, 2023

    Published Online: Feb. 26, 2024

    The Author Email: Hu Likun (hlk3email@163.com)

    DOI:10.3788/LOP231024

    Topics

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