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
Add toledo dataset
#21
Closed
HeDo88TH
closed
1 year ago
u4gbot
commented
1 year ago
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 87.44% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 27.74% | 75.76% | 30.45% | 0.43 | | | 13.11% | -23.80% | 15.80% | 0.18 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 39.17% | 39.27% | 99.37% | 0.56 | | | -6.18% | -44.72% | 49.73% | -0.06 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 87.44% | 88.54% | 98.61% | 0.93 | | | -6.62% | -5.58% | -1.33% | -0.04 | | | | | | | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 15.60% | 66.83% | 16.91% | 0.27 | | | -51.35% | -28.24% | -52.46% | -0.53 | | | | | | |
Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 32.10% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 49.16% | 64.11% | 67.83% | 0.66 | | | -43.30% | -29.88% | -30.43% | -0.30 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 1.98% | 2.32% | 12.18% | 0.04 | | | -32.78% | -92.03% | -23.33% | -0.48 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 12.71% | 12.86% | 91.76% | 0.23 | | | -85.32% | -85.46% | -7.94% | -0.76 | | | | | | | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 20.61% | 99.95% | 20.62% | 0.34 | | | -75.23% | 1.85% | -77.04% | -0.64 | | | | | | |
Average (2 datasets)
Accuracy: 95.98% vs 59.77%
Label
Accuracy
Recall
Precision
F1
53.55%
96.78%
56.46%
0.61
building
38.45%
69.94%
49.14%
0.55
-15.10%
-26.84%
-7.32%
-0.06
40.06%
89.17%
42.57%
0.57
human_made_object
20.58%
20.79%
55.77%
0.30
-19.48%
-68.37%
13.20%
-0.27
96.05%
96.22%
99.82%
0.98
ground
50.08%
50.70%
95.18%
0.58
-45.97%
-45.52%
-4.64%
-0.40
81.40%
96.58%
83.51%
0.89
low_vegetation
18.11%
83.39%
18.76%
0.31
-63.29%
-13.19%
-64.75%
-0.58
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 87.44% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 27.74% | 75.76% | 30.45% | 0.43 | | | 13.11% | -23.80% | 15.80% | 0.18 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 39.17% | 39.27% | 99.37% | 0.56 | | | -6.18% | -44.72% | 49.73% | -0.06 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 87.44% | 88.54% | 98.61% | 0.93 | | | -6.62% | -5.58% | -1.33% | -0.04 | | | | | | | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 15.60% | 66.83% | 16.91% | 0.27 | | | -51.35% | -28.24% | -52.46% | -0.53 | | | | | | |Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 32.10% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 49.16% | 64.11% | 67.83% | 0.66 | | | -43.30% | -29.88% | -30.43% | -0.30 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 1.98% | 2.32% | 12.18% | 0.04 | | | -32.78% | -92.03% | -23.33% | -0.48 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 12.71% | 12.86% | 91.76% | 0.23 | | | -85.32% | -85.46% | -7.94% | -0.76 | | | | | | | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 20.61% | 99.95% | 20.62% | 0.34 | | | -75.23% | 1.85% | -77.04% | -0.64 | | | | | | |Average (2 datasets)
Accuracy: 95.98% vs 59.77%