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
#28
Closed
HeDo88TH
closed
1 year ago
u4gbot
commented
1 year ago
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 95.76% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 96.07% | 98.65% | 97.36% | 0.98 | | | 2.01% | 4.53% | -2.58% | 0.01 | | | | | | | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 22.14% | 53.03% | 27.53% | 0.36 | | | 7.50% | -46.52% | 12.89% | 0.11 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 36.89% | 37.05% | 98.85% | 0.54 | | | -8.46% | -46.94% | 49.21% | -0.09 | | | | | | | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 23.78% | 29.40% | 55.45% | 0.38 | | | -43.17% | -65.67% | -13.91% | -0.42 | | | | | | |
Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 23.63% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 0.44% | 0.44% | 86.19% | 0.01 | | | -97.60% | -97.88% | -13.51% | -0.98 | | | | | | | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 51.70% | 70.70% | 65.80% | 0.68 | | | -40.76% | -23.29% | -32.46% | -0.28 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 1.43% | 1.50% | 21.78% | 0.03 | | | -33.34% | -92.85% | -13.72% | -0.49 | | | | | | | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 18.60% | 99.98% | 18.60% | 0.31 | | | -77.24% | 1.88% | -79.06% | -0.67 | | | | | | |
Average (2 datasets)
Accuracy: 95.98% vs 59.70%
Label
Accuracy
Recall
Precision
F1
96.05%
96.22%
99.82%
0.98
ground
48.26%
49.54%
91.77%
0.49
-47.79%
-46.68%
-8.04%
-0.49
53.55%
96.78%
56.46%
0.61
building
36.92%
61.87%
46.67%
0.52
-16.63%
-34.91%
-9.79%
-0.09
40.06%
89.17%
42.57%
0.57
human_made_object
19.16%
19.28%
60.32%
0.28
-20.90%
-69.89%
17.75%
-0.29
81.40%
96.58%
83.51%
0.89
low_vegetation
21.19%
64.69%
37.02%
0.35
-60.21%
-31.90%
-46.49%
-0.54
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 95.76% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 96.07% | 98.65% | 97.36% | 0.98 | | | 2.01% | 4.53% | -2.58% | 0.01 | | | | | | | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 22.14% | 53.03% | 27.53% | 0.36 | | | 7.50% | -46.52% | 12.89% | 0.11 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 36.89% | 37.05% | 98.85% | 0.54 | | | -8.46% | -46.94% | 49.21% | -0.09 | | | | | | | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 23.78% | 29.40% | 55.45% | 0.38 | | | -43.17% | -65.67% | -13.91% | -0.42 | | | | | | |Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 23.63% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 0.44% | 0.44% | 86.19% | 0.01 | | | -97.60% | -97.88% | -13.51% | -0.98 | | | | | | | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 51.70% | 70.70% | 65.80% | 0.68 | | | -40.76% | -23.29% | -32.46% | -0.28 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 1.43% | 1.50% | 21.78% | 0.03 | | | -33.34% | -92.85% | -13.72% | -0.49 | | | | | | | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 18.60% | 99.98% | 18.60% | 0.31 | | | -77.24% | 1.88% | -79.06% | -0.67 | | | | | | |Average (2 datasets)
Accuracy: 95.98% vs 59.70%