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 walter.laz #35

Closed pierotofy closed 1 year ago

u4gbot commented 1 year ago
brighton_beach_small Overall accuracy from 95.76% to 82.98% | ground | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 96.07% | 98.65% | 97.36% | 0.98 | | After | 83.10% | 83.10% | 99.99% | 0.91 | | Diff | -12.98% | -15.54% | 2.64% | -0.07 | | human_made_object | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 36.89% | 37.05% | 98.85% | 0.54 | | After | 0.00% | 0.00% | N/A | N/A | | Diff | -36.89% | -37.05% | N/A | N/A | | building | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 22.14% | 53.03% | 27.53% | 0.36 | | After | 7.20% | 99.49% | 7.20% | 0.13 | | Diff | -14.94% | 46.45% | -20.34% | -0.23 | | low_vegetation | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 23.78% | 29.40% | 55.45% | 0.38 | | After | 25.52% | 94.05% | 25.94% | 0.41 | | Diff | 1.74% | 64.65% | -29.51% | 0.02 |
sheffield_park_small Overall accuracy from 23.63% to 79.27% | ground | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 0.44% | 0.44% | 86.19% | 0.01 | | After | 90.87% | 91.87% | 98.81% | 0.95 | | Diff | 90.43% | 91.43% | 12.62% | 0.94 | | human_made_object | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 1.43% | 1.50% | 21.78% | 0.03 | | After | 4.20% | 75.23% | 4.26% | 0.08 | | Diff | 2.78% | 73.73% | -17.52% | 0.05 | | building | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 51.70% | 70.70% | 65.80% | 0.68 | | After | 0.01% | 0.01% | 63.64% | 0.00 | | Diff | -51.70% | -70.70% | -2.17% | -0.68 | | low_vegetation | Accuracy | Recall | Precision | F1 | | -------------------- | -------- | -------- | --------- | -------- | | Before | 18.60% | 99.98% | 18.60% | 0.31 | | After | 50.22% | 68.94% | 64.91% | 0.67 | | Diff | 31.62% | -31.04% | 46.31% | 0.35 |

Average (2 datasets)

Overall accuracy from 59.70% to 81.12%

ground Accuracy Recall Precision F1
Before 48.26% 49.54% 91.77% 0.49
After 86.98% 87.49% 99.40% 0.93
Diff 38.73% 37.94% 7.63% 0.44
human_made_object Accuracy Recall Precision F1
Before 19.16% 19.28% 60.32% 0.28
After 2.10% 37.62% 2.13% 0.04
Diff -17.06% 18.34% -58.19% -0.24
building Accuracy Recall Precision F1
Before 36.92% 61.87% 46.67% 0.52
After 3.60% 49.75% 35.42% 0.07
Diff -33.32% -12.12% -11.25% -0.45
low_vegetation Accuracy Recall Precision F1
Before 21.19% 64.69% 37.02% 0.35
After 37.87% 81.49% 45.42% 0.54
Diff 16.68% 16.81% 8.40% 0.19