Suppression éclairage solaire, GPU accéléré, --file multi, tests unitaires

- Suppression de generate_solar (éclairage solaire) des visualisations
- Accélération GPU de hillshade, slope, aspect, curvature, depressions,
  anomalies, roughness, texture GLCM, flow (sink filling)
- Nettoyage mémoire GPU entre visualisations (gpu_cleanup)
- Correction OOM texture GLCM: calcul entropie bin par bin au lieu d'un
  tableau 3D massif sur GPU
- Correction bug: xp_minimum_filter manquant dans imports visualizations
- Option --file accepte plusieurs noms complets sans extension
- run.sh affiche l'aide si appelé sans arguments
- Option --test pour exécuter les tests unitaires dans Docker
- Filtre ReturnNumber>=1 intégré dans le pipeline PDAL (plus d'erreur SMRF)
- 60 tests unitaires: GPU, visualisations, rendering, DTM, pipeline, CLI
- Ajout pytest au Dockerfile

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

lidar_pipeline/dtm.py

@@ -23,6 +23,9 @@ logger = logging.getLogger("lidar")
 def create_smrf_pipeline(input_laz, output_las):
     """Create a PDAL pipeline JSON for SMRF ground classification.
 
+    Includes a filter for ReturnNumber/NumberOfReturns >= 1 to handle
+    LiDAR HD files that may contain points with invalid return numbers.
+
     Args:
         input_laz: Path to input LAZ/LAS file.
         output_las: Path to output classified LAS file.
@@ -33,6 +36,10 @@ def create_smrf_pipeline(input_laz, output_las):
     pipeline = {
         "pipeline": [
             str(input_laz),
+            {
+                "type": "filters.range",
+                "limits": "ReturnNumber[1:],NumberOfReturns[1:]"
+            },
             {
                 "type": "filters.smrf",
                 "ignore": "Classification[7:7]",
@@ -87,36 +94,7 @@ def classify_ground(laz_file, temp_dir):
         logger.info("  ✓ Classification sol terminée")
         return output_las
     except subprocess.CalledProcessError as e:
-        error_msg = e.stderr.decode()
-        logger.error(f"  ✗ Erreur PDAL: {error_msg}")
-
-        # If error is about ReturnNumber=0, try filtering those points
-        if "ReturnNumber" in error_msg and "NumberOfReturns" in error_msg:
-            logger.info("  → Tentative de filtrage des points ReturnNumber=0...")
-
-            filtered_pipeline = [
-                {"type": "readers.las", "filename": str(laz_file)},
-                {"type": "filters.range", "limits": "ReturnNumber[1:],NumberOfReturns[1:]"},
-                {"type": "filters.smrf", "scalar": 1.25},
-                {"type": "filters.range", "limits": "Classification[2:2]"},
-                {"type": "writers.las", "filename": str(output_las), "extra_dims": "all"}
-            ]
-
-            filtered_json = json.dumps(filtered_pipeline)
-            with open(pipeline_file, 'w') as f:
-                f.write(filtered_json)
-
-            try:
-                subprocess.run(
-                    ["pdal", "pipeline", str(pipeline_file)],
-                    capture_output=True, check=True
-                )
-                logger.info("  ✓ Classification sol terminée (points filtrés)")
-                return output_las
-            except subprocess.CalledProcessError as e2:
-                logger.error(f"  ✗ Erreur même avec filtrage: {e2.stderr.decode()}")
-                return None
-
+        logger.error(f"  ✗ Erreur classification PDAL: {e.stderr.decode()}")
         return None