Harden detection model asset selection

2026-07-08 04:03:50 +02:00
parent 48ffcd0991
commit 0ed71c6f1e
7 changed files with 153 additions and 9 deletions
@@ -416,7 +416,8 @@ This file now starts with the current implementation status. Older preparation/b
 - [x] Add operator-only tile-level YOLO dataset export with overlapping windows and deterministic negative tile retention.
 - [x] Run tile-level training on Tower and accept/reject the resulting local model through the persisted QA/QC matrix.
 - [x] Train/evaluate a YOLOv8s hard-negative local building-detector candidate on Tower and keep it inactive because hard-negative false positives remain.
- [ ] Add an operator-facing local model catalog/activation workflow with SHA256, active model status and explicit threshold guidance.
- [ ] Add threshold calibration UX so detection runs do not silently rely on an unsafe default confidence.
+- [x] Add an operator-facing local model catalog/activation workflow with SHA256, active model status and explicit threshold guidance.
+- [x] Block silent local model asset auto-selection in Detection Lab.
+- [ ] Add full threshold calibration comparison UX so detection runs can compare candidate thresholds before promotion.
 - [ ] Add more AOIs after the tile-level baseline so the next local model attempt is not limited to Geel/Mol/Turnhout.
 - [ ] Add negative/background AOIs so the next tile dataset is not all positive tiles.