OpenDroneMap / ODMSemantic3D

An open photogrammetry dataset of classified 3D point clouds for automated semantic segmentation. CC BY-SA 4.0
Other
15 stars 7 forks source link

Added toledo point cloud #16

Closed HeDo88TH closed 1 year ago

u4gbot commented 1 year ago
Comparison for brighton_beach_small (Differences) Accuracy: 94.11% vs 95.19% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 28.09% | 47.06% | 41.06% | 0.44 | | | -38.86% | -48.00% | -28.30% | -0.36 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 40.35% | 40.85% | 97.10% | 0.58 | | | -4.99% | -43.14% | 47.46% | -0.05 | | | | | | | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 24.26% | 47.59% | 33.11% | 0.39 | | | 9.63% | -51.97% | 18.46% | 0.14 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 95.43% | 97.48% | 97.84% | 0.98 | | | 1.37% | 3.37% | -2.09% | 0.01 | | | | | | |
Comparison for sheffield_park_small (Differences) Accuracy: 97.85% vs 31.59% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 20.43% | 99.95% | 20.43% | 0.34 | | | -75.41% | 1.86% | -77.22% | -0.64 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 0.12% | 0.12% | 13.83% | 0.00 | | | -34.64% | -94.23% | -21.67% | -0.51 | | | | | | | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 50.24% | 67.65% | 66.12% | 0.67 | | | -42.23% | -26.35% | -32.14% | -0.29 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 11.68% | 11.74% | 96.00% | 0.21 | | | -86.35% | -86.59% | -3.70% | -0.78 | | | | | | |

Average (2 datasets)

Accuracy: 95.98% vs 63.39%

Label Accuracy Recall Precision F1
81.40% 96.58% 83.51% 0.89
low_vegetation 24.26% 73.51% 30.75% 0.39
-57.14% -23.07% -52.76% -0.50
40.06% 89.17% 42.57% 0.57
human_made_object 20.24% 20.48% 55.47% 0.29
-19.82% -68.68% 12.90% -0.28
53.55% 96.78% 56.46% 0.61
building 37.25% 57.62% 49.62% 0.53
-16.30% -39.16% -6.84% -0.08
96.05% 96.22% 99.82% 0.98
ground 53.56% 54.61% 96.92% 0.59
-42.49% -41.61% -2.90% -0.39