Merge remote-tracking branch 'origin/feature/no-altitude' into dev

Made-with: Cursor

_docs/00_problem/acceptance_criteria.md

@@ -5,7 +5,7 @@
 - Detections with confidence below `probability_threshold` (default: 0.25) are filtered out.
 - Overlapping detections with containment ratio > `tracking_intersection_threshold` (default: 0.6) are deduplicated, keeping the higher-confidence detection.
 - Tile duplicate detections are identified when all bounding box coordinates differ by less than 0.01 (TILE_DUPLICATE_CONFIDENCE_THRESHOLD).
-- Physical size filtering: detections exceeding `max_object_size_meters` for their class (defined in classes.json, range 2–20 meters) are removed.
+- Physical size filtering: detections exceeding `max_object_size_meters` for their class (defined in classes.json, range 2–20 meters) are removed when ground sampling distance can be computed from camera settings.
 
 ## Video Processing
 
@@ -17,7 +17,7 @@
 
 - Images ≤ 1.5× model dimensions (1280×1280): processed as single frame.
 - Larger images: tiled based on ground sampling distance. Tile physical size: 25 meters (METERS_IN_TILE). Tile overlap: `big_image_tile_overlap_percent` (default: 20%).
-- GSD calculation: `sensor_width * altitude / (focal_length * image_width)`.
+- GSD calculation: `sensor_width * altitude / (focal_length * image_width)` when `altitude` is provided.
 
 ## API
 

_docs/00_problem/input_data/data_parameters.md

@@ -36,7 +36,7 @@ Media path is resolved from the Annotations service via `GET /api/media/{media_i
 | tracking_intersection_threshold | float | 0.6 | Overlap ratio for NMS deduplication |
 | model_batch_size | int | 8 | Inference batch size |
 | big_image_tile_overlap_percent | int | 20 | Tile overlap for large images (0-100%) |
-| altitude | float | 400 | Camera altitude in meters |
+| altitude | float | optional | Camera altitude in meters. When omitted, GSD-based size filtering and image tiling are skipped. |
 | focal_length | float | 24 | Camera focal length in mm |
 | sensor_width | float | 23.5 | Camera sensor width in mm |
 

_docs/02_document/modules/ai_config.md

@@ -20,7 +20,7 @@ Data class holding all AI recognition configuration parameters, with factory met
 | `tracking_intersection_threshold` | double | 0.6 | IoU threshold for overlapping detection removal |
 | `model_batch_size` | int | 1 | Batch size for inference |
 | `big_image_tile_overlap_percent` | int | 20 | Tile overlap percentage for large image splitting |
-| `altitude` | double | 400 | Camera altitude in meters |
+| `altitude` | double? | optional | Camera altitude in meters. When missing, GSD-based filtering is disabled |
 | `focal_length` | double | 24 | Camera focal length in mm |
 | `sensor_width` | double | 23.5 | Camera sensor width in mm |
 
@@ -51,7 +51,7 @@ Data class holding all AI recognition configuration parameters, with factory met
 
 ## Configuration
 
-Camera/altitude parameters (`altitude`, `focal_length`, `sensor_width`) are used for ground sampling distance calculation in aerial image processing.
+Camera/altitude parameters (`altitude`, `focal_length`, `sensor_width`) are used for ground sampling distance calculation in aerial image processing. If `altitude` is missing, the service skips GSD-based size filtering and does not tile large images by physical size.
 
 ## External Integrations
 

src/ai_config.pxd

@@ -12,6 +12,7 @@ cdef class AIRecognitionConfig:
 
     cdef public int model_batch_size
 
+    cdef public bint has_altitude
     cdef public double altitude
     cdef public double focal_length
     cdef public double sensor_width

src/ai_config.pyx

@@ -25,7 +25,8 @@ cdef class AIRecognitionConfig:
 
         self.big_image_tile_overlap_percent = big_image_tile_overlap_percent
 
-        self.altitude = altitude
+        self.has_altitude = altitude is not None
+        self.altitude = 0.0 if altitude is None else float(altitude)
         self.focal_length = focal_length
         self.sensor_width = sensor_width
 
@@ -36,7 +37,7 @@ cdef class AIRecognitionConfig:
                 f'frame_period_recognition : {self.frame_period_recognition}, '
                 f'big_image_tile_overlap_percent: {self.big_image_tile_overlap_percent}, '
                 f'model_batch_size: {self.model_batch_size}, '
-                f'altitude: {self.altitude}, '
+                f'altitude: {self.altitude if self.has_altitude else None}, '
                 f'focal_length: {self.focal_length}, '
                 f'sensor_width: {self.sensor_width}'
                 )
@@ -56,7 +57,7 @@ cdef class AIRecognitionConfig:
 
             data.get("big_image_tile_overlap_percent", 20),
 
-            data.get("altitude", 400),
+            data.get("altitude", None),
             data.get("focal_length", 24),
             data.get("sensor_width", 23.5)
         )

src/inference.pyx

@@ -311,13 +311,22 @@ cdef class Inference:
         cdef double ground_sampling_distance
         cdef int model_h, model_w
         cdef int img_h, img_w
+        cdef bint has_gsd
         model_h, model_w = self.engine.get_input_shape()
         img_h, img_w, _ = frame.shape
+        has_gsd = ai_config.has_altitude and ai_config.focal_length > 0 and ai_config.sensor_width > 0 and img_w > 0
+        ground_sampling_distance = 0.0
+        if has_gsd:
             ground_sampling_distance = ai_config.sensor_width * ai_config.altitude / (ai_config.focal_length * img_w)
             constants_inf.log(<str>f'ground sampling distance: {ground_sampling_distance}')
+        else:
+            constants_inf.log(<str>'ground sampling distance: skipped (altitude unavailable)')
         if img_h <= 1.5 * model_h and img_w <= 1.5 * model_w:
             all_frame_data.append((frame, original_media_name, f'{original_media_name}_000000', ground_sampling_distance))
         else:
+            if not has_gsd:
+                all_frame_data.append((frame, original_media_name, f'{original_media_name}_000000', ground_sampling_distance))
+                return
             tile_size = int(constants_inf.METERS_IN_TILE / ground_sampling_distance)
             constants_inf.log(<str> f'calc tile size: {tile_size}')
             res = self.split_to_tiles(frame, original_media_name, tile_size, ai_config.big_image_tile_overlap_percent)
@@ -410,6 +419,12 @@ cdef class Inference:
         if annotation.detections:
             constants_inf.log(<str> f'Initial ann: {annotation}')
 
+        if ground_sampling_distance <= 0:
+            if not annotation.detections:
+                return <bint>False
+            constants_inf.log(<str>'Skipping physical-size filtering (ground sampling distance unavailable)')
+            return <bint>True
+
         cdef list[Detection] valid_detections = []
         for det in annotation.detections:
             m_w = det.w * img_w * ground_sampling_distance

src/main.py

@@ -163,7 +163,7 @@ class AIConfigDto(BaseModel):
     tracking_intersection_threshold: float = 0.6
     model_batch_size: int = 8
     big_image_tile_overlap_percent: int = 20
-    altitude: float = 400
+    altitude: Optional[float] = None
     focal_length: float = 24
     sensor_width: float = 23.5
 

tests/test_ai_config_from_dict.py

@@ -5,6 +5,15 @@ def test_ai_config_from_dict_defaults():
     assert cfg.model_batch_size == 8
     assert cfg.frame_period_recognition == 4
     assert cfg.frame_recognition_seconds == 2
+    assert cfg.has_altitude is False
+
+
+def test_ai_config_from_dict_altitude_override_sets_flag():
+    from inference import ai_config_from_dict
+
+    cfg = ai_config_from_dict({"altitude": 400})
+    assert cfg.has_altitude is True
+    assert cfg.altitude == 400
 
 
 def test_ai_config_from_dict_overrides():

tests/test_az174_db_driven_config.py

@@ -118,6 +118,23 @@ def test_resolve_media_for_detect_override_wins():
     assert "paths" not in cfg
 
 
+def test_resolve_media_for_detect_omits_altitude_when_not_provided():
+    # Arrange
+    import main
+
+    tm = main.TokenManager(_access_jwt(), "")
+    mock_ann = MagicMock()
+    mock_ann.fetch_user_ai_settings.return_value = {"probabilityThreshold": 0.2}
+    mock_ann.fetch_media_path.return_value = "/m/v.mp4"
+    with patch("main.annotations_client", mock_ann):
+        # Act
+        cfg, path = main._resolve_media_for_detect("vid-2", tm, None)
+    # Assert
+    assert "altitude" not in cfg
+    assert cfg["probability_threshold"] == 0.2
+    assert path == "/m/v.mp4"
+
+
 def test_resolve_media_for_detect_raises_when_no_media_path():
     # Arrange
     import main