Table 9 Metrics for each pathology type (YOLOv10l-seg)
From: Deep learning-driven pathology detection and analysis in historic masonry buildings of Suzhou
Class | Images | Instances | Box | Mask | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
Precision | Recall | mAP50 | mAP50-95 | Precision | Recall | mAP50 | mAP50-95 | |||
all | 174 | 1963 | 0.572 | 0.509 | 0.526 | 0.303 | 0.572 | 0.473 | 0.478 | 0.267 |
ML | 3 | 23 | 0.793 | 0.696 | 0.803 | 0.406 | 0.833 | 0.651 | 0.763 | 0.463 |
DD | 148 | 1001 | 0.537 | 0.461 | 0.486 | 0.333 | 0.541 | 0.437 | 0.465 | 0.297 |
CR | 59 | 144 | 0.482 | 0.479 | 0.471 | 0.261 | 0.453 | 0.438 | 0.406 | 0.146 |
SS | 137 | 746 | 0.538 | 0.521 | 0.52 | 0.358 | 0.544 | 0.511 | 0.516 | 0.336 |
BI | 20 | 49 | 0.511 | 0.388 | 0.352 | 0.157 | 0.487 | 0.327 | 0.241 | 0.0929 |