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 waterbury point cloud and mappings files #40

Closed HeDo88TH closed 1 year ago

HeDo88TH commented 1 year ago
u4gbot commented 1 year ago
brighton_beach_small Overall accuracy from 63.73% to 82.28% | low_vegetation | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 55.99% | 58.07% | 94.01% | 0.72 | | After | 49.65% | 50.29% | 97.51% | 0.66 | | Diff | -6.35% | -7.78% | 3.50% | -0.05 | | building | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 1.87% | 99.96% | 1.87% | 0.04 | | After | 2.07% | 49.06% | 2.11% | 0.04 | | Diff | 0.20% | -50.90% | 0.25% | 0.00 | | ground | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 63.73% | 64.12% | 99.06% | 0.78 | | After | 82.46% | 83.57% | 98.42% | 0.90 | | Diff | 18.73% | 19.45% | -0.64% | 0.13 | | human_made_object | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 0.00% | 0.00% | N/A | N/A | | After | 32.97% | 80.54% | 35.82% | 0.50 | | Diff | N/A | N/A | N/A | N/A |
sheffield_park_small Overall accuracy from 91.37% to 74.52% | low_vegetation | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 80.03% | 94.96% | 83.58% | 0.89 | | After | 74.06% | 97.38% | 75.56% | 0.85 | | Diff | -5.97% | 2.42% | -8.02% | -0.04 | | building | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 75.33% | 76.46% | 98.08% | 0.86 | | After | 6.54% | 6.54% | 98.13% | 0.12 | | Diff | -68.79% | -69.91% | 0.06% | -0.74 | | ground | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 91.62% | 92.53% | 98.94% | 0.96 | | After | 77.16% | 77.84% | 98.88% | 0.87 | | Diff | -14.46% | -14.68% | -0.07% | -0.09 | | human_made_object | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 12.76% | 86.17% | 13.03% | 0.23 | | After | 3.75% | 94.19% | 3.76% | 0.07 | | Diff | -9.02% | 8.02% | -9.27% | -0.15 |

Average (2 datasets)

Overall accuracy from 77.55% to 78.40%

low_vegetation Accuracy Recall Precision F1
Before 68.01% 76.51% 88.79% 0.80
After 61.85% 73.83% 86.54% 0.76
Diff -6.16% -2.68% -2.26% -0.05
building Accuracy Recall Precision F1
Before 38.60% 88.21% 49.97% 0.45
After 4.30% 27.80% 50.12% 0.08
Diff -34.29% -60.41% 0.15% -0.37
ground Accuracy Recall Precision F1
Before 77.67% 78.32% 99.00% 0.87
After 79.81% 80.70% 98.65% 0.89
Diff 2.13% 2.38% -0.35% 0.02
human_made_object Accuracy Recall Precision F1
Before 6.38% 43.08% 6.51% 0.11
After 18.36% 87.37% 19.79% 0.28
Diff 11.98% 44.28% 13.28% 0.17