Optoelectronic Technology, Volume. 40, Issue 1, 6(2020)

Research on Road Extraction Algorithm Based on Residual Neural Networks

Wei XIONG1,2,3, Laifu GUAN1, Lei TONG1, Chuansheng WANG1, Min LIU1,2, and Chunyan ZENG1,2
Author Affiliations
  • 1School of Electrical and Electronic Engineering, Hubei University of Technology, Wuhan 430068, CHN
  • 2Hubei Collaborative Innovation Center for High⁃Efficiency Utilization of Solar Energy, Hubei University of Technology, Wuhan, 430068, CHN
  • 3Department of Computer Science and Engineering, University of South Carolina, Columbia, SC 29201, USA
  • show less
    Figures & Tables(7)
    Algorithm overall framework
    Residual block
    Dilated convolution
    Dilated convolution module
    Decoder module
    The visualized results
    • Table 1. Performance comparison of different algorithms

      View table
      View in Article

      Table 1. Performance comparison of different algorithms

      精确率/(%)召回率/(%)F1值/(%)准确率/(%)
      CRF[5]40.532.235.982.5
      Minimum cost path[6]47.167.955.689.9
      FCN[17]43.568.653.290.4
      RSRCNN[12]60.672.966.292.4
      Seg Net[19]77.376.576.895.7
      Two⁃Step⁃DCNN[15]87.989.388.698.1
      Road⁃RCF[16]85.898.591.596.3
      U⁃Net(5 layer)98.898.898.897.8
      U⁃Net(7 layer)98.898.798.897.7
      Ours98.998.898.997.9
    Tools

    Get Citation

    Copy Citation Text

    Wei XIONG, Laifu GUAN, Lei TONG, Chuansheng WANG, Min LIU, Chunyan ZENG. Research on Road Extraction Algorithm Based on Residual Neural Networks[J]. Optoelectronic Technology, 2020, 40(1): 6

    Download Citation

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

    Category: Research and Trial-manufacture

    Received: Jul. 29, 2019

    Accepted: --

    Published Online: Apr. 26, 2020

    The Author Email:

    DOI:10.19453/j.cnki.1005-488x.2020.01.002

    Topics