• Laser & Optoelectronics Progress
  • Vol. 57, Issue 24, 241102 (2020)
Xunqiang Gong1、2、*, Xinglei Liu1、2, Tieding Lu1、2, and Dan Liu2
Author Affiliations
  • 1Fundamental Science on Radioactive Geology and Exploration Technology Laboratory, East China University of Technology, Nanchang, Jiangxi 330013, China
  • 2Faculty of Geomatics, East China University of Technology, Nanchang, Jiangxi 330013, China
  • show less
    DOI: 10.3788/LOP57.241102 Cite this Article Set citation alerts
    Xunqiang Gong, Xinglei Liu, Tieding Lu, Dan Liu. Accuracy Assessment of Object-Oriented Classification Based on Regular Verification Points[J]. Laser & Optoelectronics Progress, 2020, 57(24): 241102 Copy Citation Text show less
    Diagrams of regular verification points and random verification points. (a) Regular verification points; (b) random verification points
    Fig. 1. Diagrams of regular verification points and random verification points. (a) Regular verification points; (b) random verification points
    Fusion image of GF-2
    Fig. 2. Fusion image of GF-2
    Creation of regular verification points. (a) N=50; (b) N=100; (c) N=150; (d) N=200; (e) N=250; (f) N=300
    Fig. 3. Creation of regular verification points. (a) N=50; (b) N=100; (c) N=150; (d) N=200; (e) N=250; (f) N=300
    Comparison of classification results of three methods. (a) Overall classification accuracy; (b) Kappa coefficient
    Fig. 4. Comparison of classification results of three methods. (a) Overall classification accuracy; (b) Kappa coefficient
    Number of verification pointsOA of regular verification points /%OA of random verification points /%Kappa coefficient of regular verification pointsKappa coefficient of random verification points
    5065.1046.300.4400.205
    10077.8562.420.6420.438
    15087.1159.060.8080.395
    20087.9286.360.8100.801
    25080.5463.760.6930.462
    30083.2261.740.7340.450
    Table 1. SVM classification results under different numbers of verification points
    Number of verification pointsOA of regular verification points /%OA of random verification points /%Kappa coefficient of regular verification pointsKappa coefficient of random verification points
    5086.5861.070.7980.455
    10085.9083.220.7950.751
    15086.5883.900.8010.767
    20091.9486.580.8740.810
    25088.6081.200.8300.732
    30087.2581.810.8100.748
    Table 2. CART decision tree classification results under different numbers of verification points
    Number of verification pointsOA of regular verification points /%OA of random verification points /%Kappa coefficient of regular verification pointsKappa coefficient of random verification points
    5081.5665.600.7420.499
    10080.4183.840.7130.769
    15081.9672.000.7370.586
    20094.6386.580.9180.810
    25082.9971.200.7510.595
    30083.3381.810.7660.748
    Table 3. KNN classification results under different numbers of verification points
    Xunqiang Gong, Xinglei Liu, Tieding Lu, Dan Liu. Accuracy Assessment of Object-Oriented Classification Based on Regular Verification Points[J]. Laser & Optoelectronics Progress, 2020, 57(24): 241102
    Download Citation