Laser & Optoelectronics Progress, Volume. 59, Issue 16, 1610006(2022)

Road Extraction from Remote Sensing Images Based on Adaptive Morphology

Yupin Fang, Xiaopeng Wang*, and Xinna Li
Author Affiliations
  • College of Electronics and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, Gansu , China
  • show less
    Figures & Tables(8)
    Flow chart of proposed road extraction method from remote sensing image
    Shape analysis of elliptic structural elements. (a) λ1≈λ2≈0; (b) λ1≫λ2≈0; (c) λ1≈λ2≫0
    Elliptic structural elements
    Adaptive morphological top and bottom hat transformation. (a) Grayscale image; (b) result of fixed structural elements; (c) result of adaptive morphological structural elements
    Improved aspect ratio. (a) Road target area; (b) new rectangle
    Post processing of road segmentation. (a) Binary image; (b) shape feature extraction; (c) morphological filtering; (d) overlay effect image
    Road extraction simulation experiment. (a) Original image(from left to right: I1、I2、I3、I4); (b) circular structural element; (c) linear structural element; (d) watershed algorithm of morphological gradient reconstruction; (e) proposed method; (f) effect of road superimposed with original images; (g) extraction results of manual images
    • Table 1. Error comparison of road extraction

      View table

      Table 1. Error comparison of road extraction

      Remote sensing imagesCircular structural elementLinear structural elementWatershed algorithm of morphological gradient reconstructionProposed method
      I13.572.741.461.27
      I25.954.833.592.04
      I34.473.822.141.83
      I46.114.893.251.96
    Tools

    Get Citation

    Copy Citation Text

    Yupin Fang, Xiaopeng Wang, Xinna Li. Road Extraction from Remote Sensing Images Based on Adaptive Morphology[J]. Laser & Optoelectronics Progress, 2022, 59(16): 1610006

    Download Citation

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

    Category: Image Processing

    Received: May. 24, 2021

    Accepted: Jun. 27, 2021

    Published Online: Jul. 22, 2022

    The Author Email: Wang Xiaopeng (wangxp1969@sina.com)

    DOI:10.3788/LOP202259.1610006

    Topics