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
#26
Closed
HeDo88TH
closed
1 year ago
u4gbot
commented
1 year ago
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 94.36% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 94.59% | 96.41% | 98.05% | 0.97 | | | 0.53% | 2.29% | -1.89% | 0.00 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 42.94% | 43.28% | 98.21% | 0.60 | | | -2.40% | -40.70% | 48.57% | -0.02 | | | | | | | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 24.87% | 50.16% | 33.04% | 0.40 | | | -42.08% | -44.91% | -36.32% | -0.40 | | | | | | | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 30.82% | 60.28% | 38.67% | 0.47 | | | 16.18% | -39.28% | 24.03% | 0.22 | | | | | | |
Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 24.52% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 7.94% | 8.36% | 61.17% | 0.15 | | | -90.10% | -89.97% | -38.54% | -0.84 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 0.09% | 0.09% | 10.99% | 0.00 | | | -34.67% | -94.25% | -24.51% | -0.51 | | | | | | | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 19.37% | 99.98% | 19.37% | 0.32 | | | -76.47% | 1.88% | -78.29% | -0.65 | | | | | | | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 15.08% | 18.80% | 43.25% | 0.26 | | | -77.38% | -75.19% | -55.01% | -0.70 | | | | | | |
Average (2 datasets)
Accuracy: 95.98% vs 59.44%
Label
Accuracy
Recall
Precision
F1
96.05%
96.22%
99.82%
0.98
ground
51.26%
52.38%
79.61%
0.56
-44.79%
-43.84%
-20.21%
-0.42
40.06%
89.17%
42.57%
0.57
human_made_object
21.52%
21.69%
54.60%
0.30
-18.54%
-67.48%
12.03%
-0.27
81.40%
96.58%
83.51%
0.89
low_vegetation
22.12%
75.07%
26.20%
0.36
-59.28%
-21.51%
-57.31%
-0.53
53.55%
96.78%
56.46%
0.61
building
22.95%
39.54%
40.96%
0.37
-30.60%
-57.24%
-15.49%
-0.24
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 94.36% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 94.59% | 96.41% | 98.05% | 0.97 | | | 0.53% | 2.29% | -1.89% | 0.00 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 42.94% | 43.28% | 98.21% | 0.60 | | | -2.40% | -40.70% | 48.57% | -0.02 | | | | | | | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 24.87% | 50.16% | 33.04% | 0.40 | | | -42.08% | -44.91% | -36.32% | -0.40 | | | | | | | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 30.82% | 60.28% | 38.67% | 0.47 | | | 16.18% | -39.28% | 24.03% | 0.22 | | | | | | |Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 24.52% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 7.94% | 8.36% | 61.17% | 0.15 | | | -90.10% | -89.97% | -38.54% | -0.84 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 0.09% | 0.09% | 10.99% | 0.00 | | | -34.67% | -94.25% | -24.51% | -0.51 | | | | | | | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 19.37% | 99.98% | 19.37% | 0.32 | | | -76.47% | 1.88% | -78.29% | -0.65 | | | | | | | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 15.08% | 18.80% | 43.25% | 0.26 | | | -77.38% | -75.19% | -55.01% | -0.70 | | | | | | |Average (2 datasets)
Accuracy: 95.98% vs 59.44%