Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

GeoSLAM ZEB horizon multi-function LiDAR scanner.

More »

Fig 1 Expand

Fig 2.

Local feature integration.

More »

Fig 2 Expand

Table 1.

Pseudo-code for BN layer implementation.

More »

Table 1 Expand

Fig 3.

Building a semantic segmentation network architecture based on RandLA-Net (FC is Fully Connected Layer, LFA is Local Feature Aggregation, RS is Random Sampling, MLP is Shared Multi-Layer Perceptron, US is Upsampling, DP is Dropout Layer).

More »

Fig 3 Expand

Fig 4.

Visual interface of the system.

More »

Fig 4 Expand

Fig 5.

Point cloud data before and after preprocessing.

(a) Pre-processed point cloud data. (b) Point cloud data after pre-processing.

More »

Fig 5 Expand

Fig 6.

Before and after comparison of the final visualization results of the semantic segmentation module.

(a) Trimble Realworks manual semantic annotationTrimble Realworks. (b) Semantic segmentation results.

More »

Fig 6 Expand

Table 2.

Running effect of point cloud semantic segmentation module.

More »

Table 2 Expand

Fig 7.

Original point cloud model.

More »

Fig 7 Expand

Fig 8.

Preprocessed point cloud model.

More »

Fig 8 Expand

Fig 9.

Point cloud semantic segmentation process.

More »

Fig 9 Expand

Table 3.

Statistics of semantic segmentation results (Note: types of recognition errors in parentheses).

More »

Table 3 Expand

Table 4.

Confusion matrix for semantic segmentation results.

More »

Table 4 Expand

Fig 10.

Display of point cloud semantic segmentation results.

More »

Fig 10 Expand