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
#19
Closed
HeDo88TH
closed
1 year ago
u4gbot
commented
1 year ago
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 94.08% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 31.38% | 54.62% | 42.45% | 0.48 | | | -35.57% | -40.45% | -26.91% | -0.32 | | | | | | | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 18.83% | 73.78% | 20.18% | 0.32 | | | 4.19% | -25.78% | 5.53% | 0.06 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 94.28% | 95.89% | 98.24% | 0.97 | | | 0.21% | 1.78% | -1.69% | 0.00 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 41.08% | 41.17% | 99.48% | 0.58 | | | -4.27% | -42.82% | 49.84% | -0.04 | | | | | | |
Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 29.11% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 21.57% | 99.84% | 21.58% | 0.35 | | | -74.27% | 1.75% | -76.08% | -0.62 | | | | | | | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 17.92% | 23.37% | 43.42% | 0.30 | | | -74.54% | -70.62% | -54.84% | -0.66 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 13.18% | 13.97% | 70.07% | 0.23 | | | -84.85% | -84.35% | -29.63% | -0.76 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 1.70% | 8.55% | 2.08% | 0.03 | | | -33.06% | -85.80% | -33.42% | -0.48 | | | | | | |
Average (2 datasets)
Accuracy: 95.98% vs 61.59%
Label
Accuracy
Recall
Precision
F1
81.40%
96.58%
83.51%
0.89
low_vegetation
26.48%
77.23%
32.01%
0.42
-54.92%
-19.35%
-51.50%
-0.47
53.55%
96.78%
56.46%
0.61
building
18.37%
48.57%
31.80%
0.31
-35.18%
-48.20%
-24.65%
-0.30
96.05%
96.22%
99.82%
0.98
ground
53.73%
54.93%
84.16%
0.60
-42.32%
-41.29%
-15.66%
-0.38
40.06%
89.17%
42.57%
0.57
human_made_object
21.39%
24.86%
50.78%
0.31
-18.66%
-64.31%
8.21%
-0.26
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 94.08% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 31.38% | 54.62% | 42.45% | 0.48 | | | -35.57% | -40.45% | -26.91% | -0.32 | | | | | | | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 18.83% | 73.78% | 20.18% | 0.32 | | | 4.19% | -25.78% | 5.53% | 0.06 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 94.28% | 95.89% | 98.24% | 0.97 | | | 0.21% | 1.78% | -1.69% | 0.00 | | | | | | | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 41.08% | 41.17% | 99.48% | 0.58 | | | -4.27% | -42.82% | 49.84% | -0.04 | | | | | | |Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 29.11% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 21.57% | 99.84% | 21.58% | 0.35 | | | -74.27% | 1.75% | -76.08% | -0.62 | | | | | | | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 17.92% | 23.37% | 43.42% | 0.30 | | | -74.54% | -70.62% | -54.84% | -0.66 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 13.18% | 13.97% | 70.07% | 0.23 | | | -84.85% | -84.35% | -29.63% | -0.76 | | | | | | | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 1.70% | 8.55% | 2.08% | 0.03 | | | -33.06% | -85.80% | -33.42% | -0.48 | | | | | | |Average (2 datasets)
Accuracy: 95.98% vs 61.59%