Research Article
Fine-Grained Point Cloud Semantic Segmentation of Complex Railway Bridge Scenes from UAVs Using Improved DGCNN
Table 3
The percentage of different classification elements present in each of the three scenes.
| Scenes | Category (%) | Total points | Cable | Cluster | Guardrail | Mast | Protective wall | Rail | Track bed |
| (a) | 5.12 | 31.28 | 16.11 | 3.59 | 8.59 | 7.94 | 27.01 | 3253843 | (b) | 3.59 | 27.07 | 15.99 | 4.45 | 11.71 | 12.61 | 24.58 | 4179984 | (c) | 4.23 | 39.06 | 11.77 | 8.09 | 7.28 | 14.96 | 14.61 | 2720482 |
|
|