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
Fix classification codes
#43
Closed
HeDo88TH
closed
1 year ago
u4gbot
commented
1 year ago
sheffield_park_small
Overall accuracy from 91.37% to 79.35% | ground | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 91.62% | 92.53% | 98.94% | 0.96 | | After | 85.57% | 85.83% | 99.65% | 0.92 | | Diff | -6.05% | -6.69% | 0.70% | -0.03 | | low_vegetation | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 80.03% | 94.96% | 83.58% | 0.89 | | After | 80.33% | 91.98% | 86.38% | 0.89 | | Diff | 0.30% | -2.98% | 2.80% | 0.00 | | human_made_object | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 12.76% | 86.17% | 13.03% | 0.23 | | After | 4.02% | 93.17% | 4.03% | 0.08 | | Diff | -8.74% | 7.00% | -9.00% | -0.15 | | building | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 75.33% | 76.46% | 98.08% | 0.86 | | After | 5.43% | 5.45% | 95.69% | 0.10 | | Diff | -69.89% | -71.01% | -2.38% | -0.76 |
brighton_beach_small
Overall accuracy from 63.73% to 74.45% | ground | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 63.73% | 64.12% | 99.06% | 0.78 | | After | 74.27% | 74.51% | 99.57% | 0.85 | | Diff | 10.55% | 10.40% | 0.51% | 0.07 | | low_vegetation | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 55.99% | 58.07% | 94.01% | 0.72 | | After | 69.99% | 73.71% | 93.26% | 0.82 | | Diff | 13.99% | 15.65% | -0.74% | 0.11 | | human_made_object | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 0.00% | 0.00% | N/A | N/A | | After | 22.56% | 82.01% | 23.73% | 0.37 | | Diff | N/A | N/A | N/A | N/A | | building | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 1.87% | 99.96% | 1.87% | 0.04 | | After | 1.75% | 61.60% | 1.76% | 0.03 | | Diff | -0.12% | -38.36% | -0.10% | -0.00 |
Average (2 datasets)
Overall accuracy from 77.55% to 76.90%
ground
Accuracy
Recall
Precision
F1
Before
77.67%
78.32%
99.00%
0.87
After
79.92%
80.17%
99.61%
0.89
Diff
2.25%
1.85%
0.61%
0.02
low_vegetation
Accuracy
Recall
Precision
F1
Before
68.01%
76.51%
88.79%
0.80
After
75.16%
82.85%
89.82%
0.86
Diff
7.15%
6.33%
1.03%
0.05
human_made_object
Accuracy
Recall
Precision
F1
Before
6.38%
43.08%
6.51%
0.11
After
13.29%
87.59%
13.88%
0.22
Diff
6.91%
44.51%
7.37%
0.11
building
Accuracy
Recall
Precision
F1
Before
38.60%
88.21%
49.97%
0.45
After
3.59%
33.53%
48.73%
0.07
Diff
-35.01%
-54.68%
-1.24%
-0.38
sheffield_park_small
Overall accuracy from 91.37% to 79.35% | ground | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 91.62% | 92.53% | 98.94% | 0.96 | | After | 85.57% | 85.83% | 99.65% | 0.92 | | Diff | -6.05% | -6.69% | 0.70% | -0.03 | | low_vegetation | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 80.03% | 94.96% | 83.58% | 0.89 | | After | 80.33% | 91.98% | 86.38% | 0.89 | | Diff | 0.30% | -2.98% | 2.80% | 0.00 | | human_made_object | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 12.76% | 86.17% | 13.03% | 0.23 | | After | 4.02% | 93.17% | 4.03% | 0.08 | | Diff | -8.74% | 7.00% | -9.00% | -0.15 | | building | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 75.33% | 76.46% | 98.08% | 0.86 | | After | 5.43% | 5.45% | 95.69% | 0.10 | | Diff | -69.89% | -71.01% | -2.38% | -0.76 |brighton_beach_small
Overall accuracy from 63.73% to 74.45% | ground | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 63.73% | 64.12% | 99.06% | 0.78 | | After | 74.27% | 74.51% | 99.57% | 0.85 | | Diff | 10.55% | 10.40% | 0.51% | 0.07 | | low_vegetation | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 55.99% | 58.07% | 94.01% | 0.72 | | After | 69.99% | 73.71% | 93.26% | 0.82 | | Diff | 13.99% | 15.65% | -0.74% | 0.11 | | human_made_object | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 0.00% | 0.00% | N/A | N/A | | After | 22.56% | 82.01% | 23.73% | 0.37 | | Diff | N/A | N/A | N/A | N/A | | building | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 1.87% | 99.96% | 1.87% | 0.04 | | After | 1.75% | 61.60% | 1.76% | 0.03 | | Diff | -0.12% | -38.36% | -0.10% | -0.00 |Average (2 datasets)
Overall accuracy from 77.55% to 76.90%