Add multi-sample detection quality calibration

backend/README.md

@@ -374,6 +374,17 @@ manifests generated for AI handoff include source CRS metadata so pixel-space
 model outputs can be transformed to WGS84 GeoJSON coordinates. Current V1 upload
 support is limited to GeoTIFF-style rasters and GeoJSON/JSON reference vectors.
 
+To prepare the documented Geel/Mol/Turnhout operator sample pairs inside the
+all-in-one runtime container, run:
+
+```bash
+docker exec -it geointel python /app/scripts/prepare_operator_real_data_samples.py --samples geel,mol,turnhout
+```
+
+The helper writes GeoTIFF orthophotos, GRB GBG building GeoJSON files and
+`operator_samples_manifest.json` under `/app/storage/operator-data`. These are
+runtime artifacts only and are not committed to Git.
+
 For model-quality calibration, run the confidence sweep wrapper:
 
 ```bash
@@ -409,6 +420,21 @@ and false-positive/false-negative counts. It ranks `best_by_score`,
 `best_by_recall` and `best_by_precision`. It does not download weights, create
 fake detections, fetch live providers or change backend API behavior.
 
+To aggregate the same matrix over every prepared operator sample, run:
+
+```bash
+OPERATOR_SAMPLE_MANIFEST_PATH=storage/operator-data/operator_samples_manifest.json \
+QUALITY_MODEL_ASSET_IDS="yolov8n-building-segmentation-pt yolov8n-pt" \
+QUALITY_TILE_SIZES="512 640" \
+QUALITY_TILE_OVERLAPS="64" \
+QUALITY_THRESHOLDS="0.50 0.15" \
+bash scripts/run_multi_sample_detection_quality_matrix.sh http://192.168.10.150:1202
+```
+
+The combined `multi_sample_quality_summary.json` reports per-sample and overall
+best configurations. It is an operator benchmarking command, not a backend API
+or provider import path.
+
 To inspect the evidence behind a calibration run, export the persisted QA
 evidence bundle: