issues
search
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 dataset
#15
Closed
HeDo88TH
closed
1 year ago
u4gbot
commented
1 year ago
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 96.31% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 17.49% | 29.75% | 29.79% | 0.30 | | | 2.85% | -69.81% | 15.14% | 0.04 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 96.52% | 98.73% | 97.74% | 0.98 | | | 2.46% | 4.61% | -2.20% | 0.01 | | | | | | | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 36.22% | 47.95% | 59.69% | 0.53 | | | -30.73% | -47.12% | -9.67% | -0.27 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 42.92% | 44.54% | 92.21% | 0.60 | | | -2.43% | -39.45% | 42.57% | -0.02 | | | | | | |
Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 27.39% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 28.93% | 37.60% | 55.64% | 0.45 | | | -63.53% | -56.40% | -42.63% | -0.51 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 9.36% | 9.74% | 70.39% | 0.17 | | | -88.68% | -88.58% | -29.31% | -0.82 | | | | | | | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 20.16% | 99.95% | 20.16% | 0.34 | | | -75.68% | 1.85% | -77.50% | -0.64 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 5.14% | 10.92% | 8.85% | 0.10 | | | -29.62% | -83.42% | -26.65% | -0.42 | | | | | | |
Average (2 datasets)
Accuracy: 95.98% vs 61.85%
Label
Accuracy
Recall
Precision
F1
53.55%
96.78%
56.46%
0.61
building
23.21%
33.68%
42.71%
0.37
-30.34%
-63.10%
-13.75%
-0.23
96.05%
96.22%
99.82%
0.98
ground
52.94%
54.24%
84.06%
0.58
-43.11%
-41.99%
-15.76%
-0.40
81.40%
96.58%
83.51%
0.89
low_vegetation
28.19%
73.95%
39.93%
0.43
-53.21%
-22.63%
-43.58%
-0.46
40.06%
89.17%
42.57%
0.57
human_made_object
24.03%
27.73%
50.53%
0.35
-16.02%
-61.44%
7.96%
-0.22
HeDo88TH
commented
1 year ago
!skip
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 96.31% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 17.49% | 29.75% | 29.79% | 0.30 | | | 2.85% | -69.81% | 15.14% | 0.04 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 96.52% | 98.73% | 97.74% | 0.98 | | | 2.46% | 4.61% | -2.20% | 0.01 | | | | | | | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 36.22% | 47.95% | 59.69% | 0.53 | | | -30.73% | -47.12% | -9.67% | -0.27 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 42.92% | 44.54% | 92.21% | 0.60 | | | -2.43% | -39.45% | 42.57% | -0.02 | | | | | | |Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 27.39% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 28.93% | 37.60% | 55.64% | 0.45 | | | -63.53% | -56.40% | -42.63% | -0.51 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 9.36% | 9.74% | 70.39% | 0.17 | | | -88.68% | -88.58% | -29.31% | -0.82 | | | | | | | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 20.16% | 99.95% | 20.16% | 0.34 | | | -75.68% | 1.85% | -77.50% | -0.64 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 5.14% | 10.92% | 8.85% | 0.10 | | | -29.62% | -83.42% | -26.65% | -0.42 | | | | | | |Average (2 datasets)
Accuracy: 95.98% vs 61.85%