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
#22
Closed
HeDo88TH
closed
1 year ago
u4gbot
commented
1 year ago
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 96.08% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 18.60% | 40.68% | 25.52% | 0.31 | | | 3.96% | -58.88% | 10.87% | 0.06 | | | | | | | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 34.36% | 45.06% | 59.12% | 0.51 | | | -32.59% | -50.00% | -10.24% | -0.29 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 96.37% | 98.53% | 97.77% | 0.98 | | | 2.31% | 4.41% | -2.16% | 0.01 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 40.48% | 40.92% | 97.44% | 0.58 | | | -4.87% | -43.07% | 47.80% | -0.05 | | | | | | |
Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 26.21% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 36.34% | 58.02% | 49.31% | 0.53 | | | -56.12% | -35.97% | -48.95% | -0.43 | | | | | | | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 19.77% | 99.98% | 19.77% | 0.33 | | | -76.08% | 1.88% | -77.89% | -0.65 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 5.57% | 5.62% | 87.49% | 0.11 | | | -92.46% | -92.71% | -12.22% | -0.88 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 0.27% | 0.28% | 5.66% | 0.01 | | | -34.49% | -94.07% | -29.84% | -0.51 | | | | | | |
Average (2 datasets)
Accuracy: 95.98% vs 61.15%
Label
Accuracy
Recall
Precision
F1
53.55%
96.78%
56.46%
0.61
building
27.47%
49.35%
37.42%
0.42
-26.08%
-47.43%
-19.04%
-0.18
81.40%
96.58%
83.51%
0.89
low_vegetation
27.06%
72.52%
39.44%
0.42
-54.34%
-24.06%
-44.07%
-0.47
96.05%
96.22%
99.82%
0.98
ground
50.97%
52.07%
92.63%
0.54
-45.08%
-44.15%
-7.19%
-0.44
40.06%
89.17%
42.57%
0.57
human_made_object
20.38%
20.60%
51.55%
0.29
-19.68%
-68.57%
8.98%
-0.28
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 96.08% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 18.60% | 40.68% | 25.52% | 0.31 | | | 3.96% | -58.88% | 10.87% | 0.06 | | | | | | | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 34.36% | 45.06% | 59.12% | 0.51 | | | -32.59% | -50.00% | -10.24% | -0.29 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 96.37% | 98.53% | 97.77% | 0.98 | | | 2.31% | 4.41% | -2.16% | 0.01 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 40.48% | 40.92% | 97.44% | 0.58 | | | -4.87% | -43.07% | 47.80% | -0.05 | | | | | | |Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 26.21% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 36.34% | 58.02% | 49.31% | 0.53 | | | -56.12% | -35.97% | -48.95% | -0.43 | | | | | | | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 19.77% | 99.98% | 19.77% | 0.33 | | | -76.08% | 1.88% | -77.89% | -0.65 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 5.57% | 5.62% | 87.49% | 0.11 | | | -92.46% | -92.71% | -12.22% | -0.88 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 0.27% | 0.28% | 5.66% | 0.01 | | | -34.49% | -94.07% | -29.84% | -0.51 | | | | | | |Average (2 datasets)
Accuracy: 95.98% vs 61.15%