Journal of Natural Resources, Volume. 35, Issue 4, 963(2020)

Detection of the construction land change in fine spatial resolution remote sensing imagery coupling spatial autocorrelation

Tao ZHANG1... Hong FANG2, Yu-chun WEI2,3,4,*, Qi HU5 and Han-ze-yu XU2 |Show fewer author(s)
Author Affiliations
  • 1Nanjing Municipal Bureau of Planning and Natural Resources, Nanjing 210005, China
  • 2School of Geography, Nanjing Normal University, Nanjing 210023, China
  • 3Key Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education, Nanjing 210023, China
  • 4Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Jiangsu Provincial Key Laboratory of Geographical Environment Evolution, Nanjing 210023, China
  • 5Nnajing Underground Pipeline Data-managing Center, Nanjing 210029, China
  • show less
    Figures & Tables(19)
    The location of the study areas in Nanjing city
    True-color image and change of ground truth with 625 rows × 625 columns in the first area
    True-color image and change of ground truth with 625 rows × 625 columns in the second area
    True-color image and change of ground change truth with 1250 rows × 1250 columns in the third area
    Global Moran's I with different lags
    Global Moran's I and semivariance with different lags of change vectors in the first area
    Change distribution with the multi-scale local G statistics in the first area
    Change distribution with the multi-scale local G statistics in the second area
    Change distribution in the first area by different image feature combinations
    Change distribution in the second area by different image feature combinations
    Local autocorrelation statistics and change differences in the first and second areas
    Change distribution in the third area
    • Table 1. Confusion matrix for change detection accuracy assessment

      View table
      View in Article

      Table 1. Confusion matrix for change detection accuracy assessment

      真实情况检测结果
      正例反例
      正例TP(真正例)FN(假反例)
      反例FP(假正例)TN(真反例)
    • Table 2. Global Moran's I, normalized Z value and P value of the change vector in the first area

      View table
      View in Article

      Table 2. Global Moran's I, normalized Z value and P value of the change vector in the first area

      变化向量全局Moran's I原假设标准化ZP
      第一波段0.87随机分布872.680.001
      正态分布872.680.001
      第二波段0.85随机分布853.730.001
      正态分布853.720.001
      第三波段0.87随机分布872.440.001
      正态分布872.450.001
      第四波段0.83随机分布831.660.001
      正态分布831.660.001
    • Table 3. Multi-scale parameters configuration

      View table
      View in Article

      Table 3. Multi-scale parameters configuration

      特征组合简称特征组合简称
      Lag=1多尺度1Lag=1、2、3、4、5、6多尺度6
      Lag=1、2多尺度2Lag=1、2、3、4、5、6、7多尺度7
      Lag=1、2、3多尺度3Lag=1、2、3、4、5、6、7、8多尺度8
      Lag=1、2、3、4多尺度4Lag=1、2、3、4、5、6、7、8、9多尺度9
      Lag=1、2、3、4、5多尺度5
    • Table 4. Accuracy assessment by the multi-scale local G statistics in the first and second areas (%)

      View table
      View in Article

      Table 4. Accuracy assessment by the multi-scale local G statistics in the first and second areas (%)

      多尺度区域1区域2
      查全率查准率F1分数查全率查准率F1分数
      168.682.975.172.676.274.4
      27285.17877.678.678.1
      376.385.980.181.279.980.6
      479.4878384.181.682.9
      581.987.784.785.784.284.9
      684.287.585.886.386.786.5
      787.688.988.388.690.189.4
      88487.485.786.98887.4
      984.384.884.686.187.786.9
    • Table 5. Feature combinations and codes

      View table
      View in Article

      Table 5. Feature combinations and codes

      编号分类用的图像特征特征维度
      A图像四个光谱波段的变化向量4
      B变化向量和局部Moran's I指数32
      C变化向量和局部G指数32
      D变化向量和局部Geary's C指数32
      E变化向量、局部Moran's I指数和局部G指数60
      F变化向量、局部Moran's I指数和局部Geary's C指数60
      G变化向量、局部Geary's C指数和局部G指数60
      H变化向量和三种局部空间自相关指数88
    • Table 6. Accuracy assessment by feature combinations in the first and second areas (%)

      View table
      View in Article

      Table 6. Accuracy assessment by feature combinations in the first and second areas (%)

      编号区域1区域2
      查全率查准率F1分数查全率查准率F1分数
      A61.773.867.264.272.568.1
      B75.183.779.277.282.879.9
      C87.688.988.388.690.189.4
      D52.674.261.372.570.771.6
      E82.587.78587.288.487.8
      F64.483.772.875.479.477.3
      G79.98481.984.586.385.4
      H69.785.676.884.886.785.8
    • Table 7. Accuracy assessment of change detection in the third area (%)

      View table
      View in Article

      Table 7. Accuracy assessment of change detection in the third area (%)

      特征查全率查准率F1分数
      变化向量74.934.046.8
      变化向量及多尺度局部G指数78.467.472.5
    Tools

    Get Citation

    Copy Citation Text

    Tao ZHANG, Hong FANG, Yu-chun WEI, Qi HU, Han-ze-yu XU. Detection of the construction land change in fine spatial resolution remote sensing imagery coupling spatial autocorrelation[J]. Journal of Natural Resources, 2020, 35(4): 963

    Download Citation

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

    Category:

    Received: Feb. 27, 2019

    Accepted: --

    Published Online: Oct. 17, 2020

    The Author Email: WEI Yu-chun (weiyuchun@njnu.edu.cn)

    DOI:10.31497/zrzyxb.20200417

    Topics