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.

Overview of our proposed network architecture.

This architecture added features on centroid and neighbour relationship. The input point clouds on the left are input points, and the output is the classification result.

More »

Fig 1 Expand

Fig 2.

Overview of the ISPRS Vaihingen 3D labeling benchmark dataset.

The legend at the bottom indicates the classification labels rendered in colours.

More »

Fig 2 Expand

Table 1.

The percent of different categories in ISPRS vaihingen benchmark dataset.

More »

Table 1 Expand

Table 2.

The comparison on different loss function module.

More »

Table 2 Expand

Table 3.

The comparison of adaptive elevation.

More »

Table 3 Expand

Table 4.

The quantitative results using different features on local region.

More »

Table 4 Expand

Fig 3.

Prediction map (a) and error map (b) of our proposed method on the ISPRS benchmark dataset.

More »

Fig 3 Expand

Table 5.

Classification confusion matrix of our proposed method.

The evaluation metrics about precision, recall and F1 score of each class are reported. The numbers in the confusion matrix are normalised along each row.

More »

Table 5 Expand

Table 6.

Performance comparison between our proposed method and other state-of-art supervised models on the ISPRS Vaihingen test dataset.

The first nine columns in the table are the per-category F1 scores, and the last two columns are the OA and AvgF1.

More »

Table 6 Expand

Table 7.

Quantitative comparisons between our proposed method and other models on the GML(B) benchmark dataset.

The first four columns are the F1 scores for different classes, and the last two columns are the AvgF1 and compute time.

More »

Table 7 Expand

Fig 4.

Prediction map (a) and error map (b) of our proposed method on the GML(B) benchmark dataset.

More »

Fig 4 Expand