Kun Zhang, Yawei Zhu, Xiaohong Wang, Liting Zhang, Ruofei Zhong. Three-Dimensional Point Cloud Semantic Segmentation Network Based on Spatial Graph Convolution Network[J]. Laser & Optoelectronics Progress, 2023, 60(2): 0228007

Search by keywords or author
- Laser & Optoelectronics Progress
- Vol. 60, Issue 2, 0228007 (2023)

Fig. 1. PCGCN problem description diagram

Fig. 2. Overall structure diagram of PCGCN

Fig. 3. EdgeConv subnet. (a) 2nd layerneighborhood aggregation; (b) 1st layer neighborhood aggregation; (c) local features graph

Fig. 4. PCGCN residual network diagram

Fig. 5. Aggregating characteristics of different layers

Fig. 6. KNN diagrams. (a) Original KNN; (b) randomly delete nodes; (c) original sampling result; (d) sampling result after improvement

Fig. 7. Comparison of training results of S3DIS.(a) Train average accuracy; (b) train accuracy; (c) train IoU

Fig. 8. Visualization of segmentation results in S3DIS

Fig. 9. Accuracy of ShapeNet test set

Fig. 10. Visualization of segmentation results in ShapeNet

Fig. 11. Robustness analysis on ShapeNet

Fig. 12. Anti noise analysis on S3DIS
|
Table 1. Parameter comparison experiment
|
Table 2. Semantic segmentation results of S3DIS
|
Table 3. Semantic Segmentation time of S3DIS
|
Table 4. Parameter sensitivity experiment
|
Table 5. Semantic segmentation results of ShapeNet

Set citation alerts for the article
Please enter your email address