Skip to main content

Table 8 Quantitative comparison of the semantic segmentation performance across five down-sampling strategies on DGCNN for the Soybean-MVS dataset

From: A comparative study on point cloud down-sampling strategies for deep learning-based crop organ segmentation

DGCNN

Semantic Segmentation (%)

Score

AveDiff (%)

Precision

Recall

F1

IoU

FPS

90.93

88.58

89.68

82.00

0

2.73

RS

91.51

91.68

91.59

84.62

12

0.68

UVS

90.95

89.03

89.93

82.36

5

2.46

VFPS

91.08

86.93

88.83

80.77

1

3.62

3DEPS

92.13

92.20

92.16

85.63

18

0.00