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
#24
Closed
HeDo88TH
closed
1 year ago
u4gbot
commented
1 year ago
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 96.27% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 39.38% | 40.27% | 94.69% | 0.57 | | | -5.96% | -43.71% | 45.05% | -0.06 | | | | | | | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 33.16% | 40.98% | 63.48% | 0.50 | | | -33.79% | -54.09% | -5.88% | -0.30 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 96.52% | 98.78% | 97.68% | 0.98 | | | 2.46% | 4.66% | -2.25% | 0.01 | | | | | | | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 24.99% | 52.45% | 32.31% | 0.40 | | | 10.35% | -47.11% | 17.66% | 0.14 | | | | | | |
Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 25.68% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 1.06% | 1.08% | 34.55% | 0.02 | | | -33.71% | -93.27% | -0.96% | -0.50 | | | | | | | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 18.98% | 99.99% | 18.98% | 0.32 | | | -76.86% | 1.89% | -78.68% | -0.66 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 3.57% | 3.57% | 98.35% | 0.07 | | | -94.47% | -94.75% | -1.35% | -0.92 | | | | | | | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 50.80% | 68.19% | 66.58% | 0.67 | | | -41.66% | -25.81% | -31.69% | -0.29 | | | | | | |
Average (2 datasets)
Accuracy: 95.98% vs 60.98%
Label
Accuracy
Recall
Precision
F1
40.06%
89.17%
42.57%
0.57
human_made_object
20.22%
20.67%
64.62%
0.29
-19.84%
-68.49%
22.05%
-0.28
81.40%
96.58%
83.51%
0.89
low_vegetation
26.07%
70.48%
41.23%
0.41
-55.33%
-26.10%
-42.28%
-0.48
96.05%
96.22%
99.82%
0.98
ground
50.05%
51.18%
98.02%
0.53
-46.00%
-45.04%
-1.80%
-0.45
53.55%
96.78%
56.46%
0.61
building
37.89%
60.32%
49.44%
0.54
-15.66%
-36.46%
-7.02%
-0.07
HeDo88TH
commented
1 year ago
!skip
Comparison for brighton_beach_small (Differences)
Accuracy: 94.11% vs 96.27% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 45.35% | 83.98% | 49.64% | 0.62 | | human_made_object | 39.38% | 40.27% | 94.69% | 0.57 | | | -5.96% | -43.71% | 45.05% | -0.06 | | | | | | | | | 66.95% | 95.07% | 69.36% | 0.80 | | low_vegetation | 33.16% | 40.98% | 63.48% | 0.50 | | | -33.79% | -54.09% | -5.88% | -0.30 | | | | | | | | | 94.06% | 94.12% | 99.93% | 0.97 | | ground | 96.52% | 98.78% | 97.68% | 0.98 | | | 2.46% | 4.66% | -2.25% | 0.01 | | | | | | | | | 14.64% | 99.56% | 14.65% | 0.26 | | building | 24.99% | 52.45% | 32.31% | 0.40 | | | 10.35% | -47.11% | 17.66% | 0.14 | | | | | | |Comparison for sheffield_park_small (Differences)
Accuracy: 97.85% vs 25.68% | Label | Accuracy | Recall | Precision | F1 | | -------------------- | ---------- | ---------- | ---------- | ---------- | | | 34.76% | 94.35% | 35.50% | 0.52 | | human_made_object | 1.06% | 1.08% | 34.55% | 0.02 | | | -33.71% | -93.27% | -0.96% | -0.50 | | | | | | | | | 95.84% | 98.10% | 97.66% | 0.98 | | low_vegetation | 18.98% | 99.99% | 18.98% | 0.32 | | | -76.86% | 1.89% | -78.68% | -0.66 | | | | | | | | | 98.04% | 98.33% | 99.70% | 0.99 | | ground | 3.57% | 3.57% | 98.35% | 0.07 | | | -94.47% | -94.75% | -1.35% | -0.92 | | | | | | | | | 92.46% | 94.00% | 98.27% | 0.96 | | building | 50.80% | 68.19% | 66.58% | 0.67 | | | -41.66% | -25.81% | -31.69% | -0.29 | | | | | | |Average (2 datasets)
Accuracy: 95.98% vs 60.98%