Table 12 Performance Comparison of different methods for fruit tree classification.

From: Object-oriented multi-scale segmentation and multi-feature fusion-based method for identifying typical fruit trees in arid regions using Sentinel-1/2 satellite images

Indicator

Classification accuracies of different methods (in %)

OO + RF

OO + CART

OO + GBDT

OO + SVM

RF

CART

GBDT

SVM

OA (%)

94.60

92.80

92.54

80.46

92.95

90.18

88.66

80.60

KC (%)

93.74

91.67

91.35

77.09

91.88

88.71

86.92

77.48

Back to article page