Figure 1.
Workflow of the building point cloud extraction.
Figure 1.
Workflow of the building point cloud extraction.
Figure 2.
Visualization flowchart of the building point cloud extraction.
Figure 2.
Visualization flowchart of the building point cloud extraction.
Figure 3.
The point cloud is divided into ground points and non-ground points using the CSF filtering algorithm (ground points are displayed in dark yellow, and non-ground points are displayed in blue).
Figure 3.
The point cloud is divided into ground points and non-ground points using the CSF filtering algorithm (ground points are displayed in dark yellow, and non-ground points are displayed in blue).
Figure 4.
Plane segmentation results using the region growing algorithm.
Figure 4.
Plane segmentation results using the region growing algorithm.
Figure 5.
(a) Ground truth; (b) coarse extraction results using the region growing algorithm, with buildings in red, trees in green, and ground points in dark yellow.
Figure 5.
(a) Ground truth; (b) coarse extraction results using the region growing algorithm, with buildings in red, trees in green, and ground points in dark yellow.
Figure 6.
Mask polygon extraction using a combination of the Alpha Shape algorithm and neighborhood expansion method.
Figure 6.
Mask polygon extraction using a combination of the Alpha Shape algorithm and neighborhood expansion method.
Figure 7.
Calculation of the center coordinates of a circle based on the distance intersection method.
Figure 7.
Calculation of the center coordinates of a circle based on the distance intersection method.
Figure 8.
Polygonal connection based on the polar angles.
Figure 8.
Polygonal connection based on the polar angles.
Figure 9.
Misclassification of building points using the CSF algorithm within the red circle, with ground points in dark yellow and non-ground points in blue.
Figure 9.
Misclassification of building points using the CSF algorithm within the red circle, with ground points in dark yellow and non-ground points in blue.
Figure 10.
Radius filtering algorithm.
Figure 10.
Radius filtering algorithm.
Figure 11.
Urban-LiDAR dataset.
Figure 11.
Urban-LiDAR dataset.
Figure 12.
Vaihingen dataset. (a) Vaihi-1 data; (b) Vaihi-2 data.
Figure 12.
Vaihingen dataset. (a) Vaihi-1 data; (b) Vaihi-2 data.
Figure 13.
Training data. Ground points are in dark yellow; the facades are in purple; the roofs are in red; and other elements are in green.
Figure 13.
Training data. Ground points are in dark yellow; the facades are in purple; the roofs are in red; and other elements are in green.
Figure 14.
Urban-LiDAR’s extraction results: ground points are in dark yellow; tree points are in green; the facades are in purple; the roofs are in red. (a) Ground truth; (b) the extraction results using the proposed method.
Figure 14.
Urban-LiDAR’s extraction results: ground points are in dark yellow; tree points are in green; the facades are in purple; the roofs are in red. (a) Ground truth; (b) the extraction results using the proposed method.
Figure 15.
Vaihi-1’s extraction results: ground points are in dark yellow; tree points are in green; the facades are in purple; the roofs are in red. (a) Ground truth; (b) the extraction results using the proposed method.
Figure 15.
Vaihi-1’s extraction results: ground points are in dark yellow; tree points are in green; the facades are in purple; the roofs are in red. (a) Ground truth; (b) the extraction results using the proposed method.
Figure 16.
Vaihi-2’s extraction results: ground points are in dark yellow; the facades are in purple; the roofs are in red. (a) Ground truth; (b) the extraction results using the proposed method.
Figure 16.
Vaihi-2’s extraction results: ground points are in dark yellow; the facades are in purple; the roofs are in red. (a) Ground truth; (b) the extraction results using the proposed method.
Figure 17.
(a) Facade points within mask polygons in the original points; (b) the facade points within mask polygons in the non-ground points; (c) the overlay of (a,b).
Figure 17.
(a) Facade points within mask polygons in the original points; (b) the facade points within mask polygons in the non-ground points; (c) the overlay of (a,b).
Figure 18.
Extraction of buildings results in complex scenes: (a) original data; (b) label data; (c) the extraction results of the building using the proposed method.
Figure 18.
Extraction of buildings results in complex scenes: (a) original data; (b) label data; (c) the extraction results of the building using the proposed method.
Figure 19.
Extraction of the buildings with low cloud density: (a) original point cloud; (b) manually delineated reference building points. The integration of texture information into data collected by unmanned aerial vehicles (UAVs) may introduce errors, as exemplified by the points highlighted in blue in the figure, which should ideally be categorized as building points; (c) the extracted building points using the proposed method.
Figure 19.
Extraction of the buildings with low cloud density: (a) original point cloud; (b) manually delineated reference building points. The integration of texture information into data collected by unmanned aerial vehicles (UAVs) may introduce errors, as exemplified by the points highlighted in blue in the figure, which should ideally be categorized as building points; (c) the extracted building points using the proposed method.
Figure 20.
Vaihi-1 data. (a) Label of Vaihi-1; (b) Vaihi-1’s extraction results using the proposed method.
Figure 20.
Vaihi-1 data. (a) Label of Vaihi-1; (b) Vaihi-1’s extraction results using the proposed method.
Figure 21.
Vaihi-2 data. (a) Label of Vaihi-2; (b) Vaihi-2’s extraction results using the proposed method.
Figure 21.
Vaihi-2 data. (a) Label of Vaihi-2; (b) Vaihi-2’s extraction results using the proposed method.
Table 1.
Parameter settings of some important algorithms.
Table 1.
Parameter settings of some important algorithms.
Algorithm | Parameter | Urban-LiDAR | Vaihi-1 | Vaihi-2 |
---|
CSF algorithm | cloth_resolution | 1.0 | 0.3 | 1.0 |
max_iterations | 500 | 500 | 500 |
classification_thresold | 2.0 | 1.5 | 2.2 |
Region growing algorithm | theta_threshold | 5 | 30 | 10 |
curvature_threshold | 0.05 | 0.05 | 0.03 |
neighbor_number | 20 | 15 | 30 |
min_pts_per_cluster | 100 | 40 | 50 |
max_pts_per_cluster | 10,000 | 10,000 | 10,000 |
European clustering algorithm | tolerance | 0.58 | 1.5 | 1.25 |
min_cluster_size | 80 | 180 | 180 |
max_cluster_size | 100,000 | 10,000 | 15,000 |
Table 2.
Accuracy assessment of Urban-LiDAR’s extraction (%).
Table 2.
Accuracy assessment of Urban-LiDAR’s extraction (%).
| Precision | Recall | F1 Score |
---|
Roof | 98.74 | 98.47 | 98.60 |
Façade | 97.98 | 70.94 | 82.30 |
Table 3.
Accuracy assessment of Urban-LiDAR’s roof extraction (%).
Table 3.
Accuracy assessment of Urban-LiDAR’s roof extraction (%).
ID | Precision | Recall | F1 Score |
---|
0 | 99.54 | 99.77 | 99.66 |
1 | 98.25 | 98.92 | 98.58 |
2 | 99.80 | 98.42 | 99.11 |
3 | 96.05 | 98.00 | 97.02 |
4 | 97.19 | 98.56 | 97.87 |
5 | 95.22 | 95.62 | 95.42 |
6 | 99.85 | 99.80 | 99.82 |
7 | 100 | 98.14 | 99.06 |
8 | 84.08 | 91.31 | 87.55 |
9 | 98.72 | 98.88 | 98.80 |
10 | 98.68 | 97.35 | 98.01 |
11 | 98.82 | 98.38 | 98.60 |
12 | 98.00 | 98.52 | 98.26 |
13 | 99.50 | 97.70 | 98.59 |
14 | 100 | 100 | 100 |
15 | 99.12 | 96.64 | 97.86 |
16 | 98.79 | 97.65 | 98.22 |
17 | 99.94 | 99.32 | 99.63 |
18 | 96.67 | 98.28 | 97.47 |
19 | 88.47 | 93.46 | 90.90 |
20 | 93.29 | 96.37 | 94.80 |
21 | 99.87 | 97.78 | 98.81 |
22 | 99.62 | 99.17 | 99.39 |
23 | 97.69 | 97.96 | 97.82 |
24 | 99.41 | 92.02 | 95.57 |
25 | 97.46 | 92.42 | 94.87 |
26 | 96.18 | 98.06 | 97.11 |
27 | 98.91 | 98.68 | 98.79 |
28 | 79.57 | 89.13 | 84.08 |
29 | 100 | 100 | 100 |
30 | 92.76 | 95.66 | 94.19 |
Table 4.
Accuracy assessment of Vaihingen’s extraction (%).
Table 4.
Accuracy assessment of Vaihingen’s extraction (%).
Algorithm | Indicator | Roof | Facade |
---|
PointNet | Precision | 73.0 (↑20.73) | 10.7 (↑49.63) |
Recall | 82.2 | 0.1 |
F1 score | 77.6 | 5.4 |
PointNet++ | Precision | 92.8 | 43.8 (↑16.53) |
Recall | 81.0 | 38.3 |
F1 score | 86.9 | 41.0 |
HDL-JME-GGO | Precision | 92.8 | 64.2 (↓3.87) |
Recall | 89.3 | 24.2 |
F1 score | 91.1 (↓0.28) | 44.2 |
The Proposed Method | Precision | 93.73 | 60.33 |
Recall | 88.08 | 27.33 |
F1 score | 90.82 | 37.62 |
Table 5.
Accuracy assessment of Vaihi-1 and Vaihi-2’s extraction (%).
Table 5.
Accuracy assessment of Vaihi-1 and Vaihi-2’s extraction (%).
| Precision | Recall | F1 Score |
---|
Vaih-1 | Vaih-2 | Vaih-1 | Vaih-2 | Vaih-1 | Vaih-2 |
---|
Roof | 91.49 | 96.27 | 92.32 | 83.93 | 91.90 | 89.68 |
Facade | 58.33 | 61.45 | 17.77 | 38.36 | 27.24 | 47.23 |
Table 6.
Accuracy assessment of Vaihi-1 and Vaihi-2’s roof extraction (%).
Table 6.
Accuracy assessment of Vaihi-1 and Vaihi-2’s roof extraction (%).
ID | Precision | Recall | F1 Score |
---|
Roof | Vaih-1 | Vaih-2 | Vaih-1 | Vaih-2 | Vaih-1 | Vaih-2 |
---|
0 | 100 | 86.80 | 100 | 91.83 | 100 | 89.24 |
1 | 88.94 | 98.04 | 93.87 | 90.77 | 91.34 | 94.27 |
2 | 100 | 92.65 | 99.80 | 92.45 | 99.90 | 92.55 |
3 | 97.83 | 97.91 | 99.77 | 95.02 | 98.79 | 96.44 |
4 | 99.45 | 99.90 | 99.73 | 94.43 | 99.59 | 97.09 |
5 | 97.75 | 99.88 | 97.61 | 78.13 | 97.68 | 87.68 |
6 | 99.39 | 94.78 | 95.46 | 84.80 | 97.39 | 89.51 |
7 | 100 | 99.88 | 95.58 | 55.14 | 97.74 | 71.05 |
8 | 99.02 | 99.41 | 99.18 | 68.67 | 99.10 | 81.23 |
9 | 71.91 | 99.72 | 81.51 | 94.67 | 76.41 | 97.13 |
10 | 98.52 | 99.29 | 98.89 | 94.40 | 98.70 | 96.78 |
11 | 100 | 97.21 | 100 | 93.43 | 100 | 95.28 |
12 | 98.14 | 99.70 | 86.17 | 98.38 | 91.77 | 99.04 |
13 | 98.18 | 96.57 | 96.83 | 97.70 | 97.50 | 97.13 |
14 | 98.96 | 99.55 | 95.65 | 98.31 | 97.28 | 98.93 |
15 | 99.43 | 99.84 | 99.15 | 87.41 | 99.29 | 93.21 |
16 | 100 | 99.07 | 99.76 | 98.05 | 99.88 | 98.56 |
17 | 99.29 | 99.23 | 99.29 | 90.44 | 99.29 | 94.63 |
18 | 100 | 99.16 | 89.25 | 98.39 | 94.32 | 98.77 |
19 | 96.92 | 97.68 | 98.43 | 91.75 | 97.67 | 94.62 |
20 | 97.35 | 96.92 | 96.89 | 97.55 | 97.12 | 97.23 |