Deep Learning Model for Point Cloud Classification Based on Graph Convolutional Network

Table 2. Comparisons of classification accuracy on ModelNet40 and computational complexity of several models
View table
Table 2. Comparisons of classification accuracy on ModelNet40 and computational complexity of several models
Model Mean classaccuracy /% Overallaccuracy /% Forwardtime /ms
3D ShapeNets^[11] 77.3 84.7
VoxNet^[12] 83 85.9
PointNet 86 89.2 25.3
ointNet++^[13] 90.7 163.2
Kd-network^[14] 86.3
Ours 91.6 93.2 29.4

Table 3. Comparison of classification accuracy under different k values
View table
Table 3. Comparison of classification accuracy under different k values
k Mean classaccuracy /% Overallaccuracy /%
5 87.6 89.2
10 88.0 90.4
15 90.1 92.6
20 91.6 93.2
25 91.2 92.9
30 90.8 92.5
35 89.9 91.8
40 89.7 91.6

Tools

Get Citation

Copy Citation Text

Xujiao Wang, Jie Ma, Nannan Wang, Pengfei Ma, Lichaung Yang. Deep Learning Model for Point Cloud Classification Based on Graph Convolutional Network[J]. Laser & Optoelectronics Progress, 2019, 56(21): 211004

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites