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
#20
Closed
HeDo88TH
closed
1 year ago
u4gbot
commented
1 year ago
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 95.03% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 33.53% | 62.17% | 42.13% | 0.50 | | | -33.42% | -32.90% | -27.23% | -0.30 | | | | | | | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 26.15% | 57.45% | 32.43% | 0.41 | | | 11.51% | -42.11% | 17.78% | 0.16 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 41.62% | 41.74% | 99.32% | 0.59 | | | -3.73% | -42.24% | 49.68% | -0.04 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 95.26% | 96.76% | 98.40% | 0.98 | | | 1.20% | 2.64% | -1.53% | 0.01 | | | | | | |
Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 29.08% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 19.82% | 99.97% | 19.82% | 0.33 | | | -76.03% | 1.87% | -77.84% | -0.65 | | | | | | | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 50.16% | 67.32% | 66.31% | 0.67 | | | -42.30% | -26.68% | -31.95% | -0.29 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 0.95% | 0.97% | 25.43% | 0.02 | | | -33.82% | -93.38% | -10.07% | -0.50 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 8.30% | 8.34% | 94.70% | 0.15 | | | -89.74% | -89.99% | -5.01% | -0.84 | | | | | | |
Average (2 datasets)
Accuracy: 95.98% vs 62.06%
Label
Accuracy
Recall
Precision
F1
81.40%
96.58%
83.51%
0.89
low_vegetation
26.67%
81.07%
30.97%
0.42
-54.72%
-15.51%
-52.54%
-0.47
53.55%
96.78%
56.46%
0.61
building
38.16%
62.38%
49.37%
0.54
-15.39%
-34.39%
-7.09%
-0.07
40.06%
89.17%
42.57%
0.57
human_made_object
21.28%
21.36%
62.38%
0.30
-18.77%
-67.81%
19.80%
-0.27
96.05%
96.22%
99.82%
0.98
ground
51.78%
52.55%
96.55%
0.56
-44.27%
-43.67%
-3.27%
-0.42
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 95.03% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 33.53% | 62.17% | 42.13% | 0.50 | | | -33.42% | -32.90% | -27.23% | -0.30 | | | | | | | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 26.15% | 57.45% | 32.43% | 0.41 | | | 11.51% | -42.11% | 17.78% | 0.16 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 41.62% | 41.74% | 99.32% | 0.59 | | | -3.73% | -42.24% | 49.68% | -0.04 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 95.26% | 96.76% | 98.40% | 0.98 | | | 1.20% | 2.64% | -1.53% | 0.01 | | | | | | |Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 29.08% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 19.82% | 99.97% | 19.82% | 0.33 | | | -76.03% | 1.87% | -77.84% | -0.65 | | | | | | | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 50.16% | 67.32% | 66.31% | 0.67 | | | -42.30% | -26.68% | -31.95% | -0.29 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 0.95% | 0.97% | 25.43% | 0.02 | | | -33.82% | -93.38% | -10.07% | -0.50 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 8.30% | 8.34% | 94.70% | 0.15 | | | -89.74% | -89.99% | -5.01% | -0.84 | | | | | | |Average (2 datasets)
Accuracy: 95.98% vs 62.06%