Filter low variance YOLO negative tiles

backend/tests/test_sprint130_operator_yolo_tile_dataset.py

@@ -5,6 +5,8 @@ from pathlib import Path
 import subprocess
 import sys
 
+import numpy as np
+
 
 ROOT = Path(__file__).resolve().parents[2]
 
@@ -39,6 +41,8 @@ def test_operator_yolo_tile_dataset_export_script_contract() -> None:
     assert "stride" in script
     assert "negative_keep_ratio" in script
     assert "min_label_visible_ratio" in script
+    assert "drop_low_variance_negatives" in script
+    assert "skipped_low_variance_negative_tile_count" in script
     assert "positive_tile_count" in script
     assert "negative_tile_count" in script
     assert "skipped_negative_tile_count" in script
@@ -67,6 +71,8 @@ def test_operator_yolo_tile_dataset_export_help_does_not_require_gis_dependencie
     assert "--negative-keep-ratio" in result.stdout
     assert "--min-label-visible-ratio" in result.stdout
     assert "--background-negative-repeat" in result.stdout
+    assert "--drop-low-variance-negatives" in result.stdout
+    assert "--blank-range-threshold" in result.stdout
 
 
 def test_iter_tile_windows_covers_edges_without_duplicates() -> None:
@@ -171,3 +177,86 @@ def test_background_category_is_derived_for_legacy_operator_manifests() -> None:
     assert module.background_category_for_sample(pure_empty_sample) == "pure_empty_negative"
     assert module.background_category_for_sample(sparse_context_sample) == "sparse_building_context"
     assert module.background_category_for_sample(reference_sample) == "reference_aoi"
+
+
+def test_export_can_skip_low_variance_negative_tiles(tmp_path: Path, monkeypatch) -> None:
+    module = load_tile_exporter()
+    raster_path = tmp_path / "sample.tif"
+    reference_path = tmp_path / "reference.geojson"
+    raster_path.write_bytes(b"fake-raster")
+    reference_path.write_text('{"type": "FeatureCollection", "features": []}', encoding="utf-8")
+
+    class FakeDataset:
+        width = 256
+        height = 128
+        crs = "EPSG:31370"
+
+        def __enter__(self):
+            return self
+
+        def __exit__(self, exc_type, exc, traceback):
+            return False
+
+    class FakeRasterio:
+        @staticmethod
+        def open(path):
+            assert Path(path) == raster_path
+            return FakeDataset()
+
+    class FakeImageObject:
+        def __init__(self, array):
+            self.array = array
+
+        def save(self, path):
+            Path(path).write_bytes(b"png")
+
+    class FakeImage:
+        @staticmethod
+        def fromarray(array):
+            return FakeImageObject(array)
+
+    def fake_image_array_from_raster_window(dataset, tile_window):
+        if tile_window.col_off == 0:
+            return np.full((128, 128, 3), 255, dtype=np.uint8)
+        image = np.zeros((128, 128, 3), dtype=np.uint8)
+        image[:, 64:, :] = 80
+        return image
+
+    monkeypatch.setattr(module, "rasterio", FakeRasterio)
+    monkeypatch.setattr(module, "Image", FakeImage)
+    monkeypatch.setattr(module, "load_reference_pixel_boxes", lambda reference_path, dataset, min_label_px: [])
+    monkeypatch.setattr(module, "image_array_from_raster_window", fake_image_array_from_raster_window)
+
+    records = module.export_sample_tiles(
+        sample={
+            "sample_slug": "blank_negative",
+            "sample_role": "background_candidate",
+            "background_category": "pure_empty_negative",
+            "raster_path": str(raster_path),
+            "reference_path": str(reference_path),
+        },
+        manifest_path=tmp_path / "operator_samples_manifest.json",
+        output_dir=tmp_path / "dataset",
+        val_slugs=set(),
+        tile_size=128,
+        stride=128,
+        negative_keep_ratio=1.0,
+        min_label_px=4,
+        min_label_visible_ratio=0.0,
+        background_negative_repeat=1,
+        drop_low_variance_negatives=True,
+        blank_range_threshold=3,
+    )
+
+    skipped = [record for record in records if not record["kept"]]
+    kept = [record for record in records if record["kept"]]
+
+    assert len(skipped) == 1
+    assert skipped[0]["skip_reason"] == "low_visual_variance_negative"
+    assert skipped[0]["low_visual_variance"] is True
+    assert skipped[0]["is_negative"] is True
+    assert skipped[0]["tile_index"] == 0
+    assert len(kept) == 1
+    assert kept[0]["tile_index"] == 1
+    assert kept[0]["low_visual_variance"] is False
+    assert Path(kept[0]["image_path"]).exists()