update the morphology for corn

sorghum_pipeline/features/morphology.py

@@ -56,6 +56,7 @@ class MorphologyExtractor:
             
             # Calculate height for each plant (skip background label 0)
             plant_heights = {}
+            plant_areas = {}
             for plant_idx in range(1, num_labels):
                 area = stats[plant_idx, cv2.CC_STAT_AREA]
                 # Filter out very small components (noise)
@@ -69,17 +70,21 @@ class MorphologyExtractor:
                     height_px = int(rows.max() - rows.min() + 1)
                     height_cm = float(height_px * self.pixel_to_cm)
                     plant_heights[f'plant_{plant_idx}'] = height_cm
+                    plant_areas[f'plant_{plant_idx}'] = area
+            
+            # Keep only the largest plant (main plant) for single-plant datasets
+            if len(plant_heights) > 1:
+                # Find the largest plant by area
+                largest_plant = max(plant_areas.items(), key=lambda x: x[1])[0]
+                plant_heights = {largest_plant: plant_heights[largest_plant]}
             
             # Store individual plant heights
             features['traits']['plant_heights'] = plant_heights
-            features['traits']['num_plants'] = len(plant_heights)
+            features['traits']['num_plants'] = 1 if len(plant_heights) > 0 else 0
             
-            # For backward compatibility, store total height if single plant
+            # Store single plant height
             if len(plant_heights) == 1:
                 features['traits']['plant_height_cm'] = list(plant_heights.values())[0]
-            elif len(plant_heights) > 1:
-                # Store max height as overall height
-                features['traits']['plant_height_cm'] = max(plant_heights.values())
             else:
                 features['traits']['plant_height_cm'] = 0.0
 
@@ -160,30 +165,31 @@ class MorphologyExtractor:
         return arr
     
     def _simple_size_visual(self, rgb: np.ndarray, mask: np.ndarray) -> np.ndarray:
-        """Draw contours and bbox for each plant on RGB image."""
+        """Draw contours and bbox for the largest plant on RGB image."""
         vis = rgb.copy()
         
         # Find connected components to identify individual plants
         num_labels, labels, stats, _ = cv2.connectedComponentsWithStats(mask, connectivity=8)
         
-        # Use different colors for different plants
-        colors = [(255, 0, 0), (0, 255, 0), (0, 0, 255), (255, 255, 0), (255, 0, 255), (0, 255, 255)]
-        
-        plant_count = 0
-        for plant_idx in range(1, num_labels):  # Skip background (0)
+        # Find the largest plant (skip background 0)
+        largest_idx = -1
+        largest_area = 0
+        for plant_idx in range(1, num_labels):
             area = stats[plant_idx, cv2.CC_STAT_AREA]
-            # Filter out very small components (noise)
-            if area < 100:
-                continue
-            
-            # Get individual plant mask
-            plant_mask = ((labels == plant_idx).astype(np.uint8) * 255)
+            if area > largest_area and area >= 100:  # Filter noise
+                largest_area = area
+                largest_idx = plant_idx
+        
+        # Draw only the largest plant
+        if largest_idx > 0:
+            # Get mask for largest plant
+            plant_mask = ((labels == largest_idx).astype(np.uint8) * 255)
             
-            # Find contours for this plant
+            # Find contours
             contours, _ = cv2.findContours(plant_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
             
-            # Pick color for this plant
-            color = colors[plant_count % len(colors)]
+            # Use blue color for main plant
+            color = (255, 0, 0)
             
             # Draw contours
             cv2.drawContours(vis, contours, -1, color, 2)
@@ -191,13 +197,11 @@ class MorphologyExtractor:
             # Draw bounding box
             if contours:
                 x, y, w, h = cv2.boundingRect(contours[0])
-                cv2.rectangle(vis, (x, y), (x + w, y + h), color, 2)
+                cv2.rectangle(vis, (x, y), (x + w, y + h), (0, 255, 0), 2)
                 
-                # Add plant number label
-                cv2.putText(vis, f"P{plant_idx}", (x, y - 5), 
+                # Add "Plant 1" label
+                cv2.putText(vis, "Plant 1", (x, y - 5), 
                            cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2, cv2.LINE_AA)
-            
-            plant_count += 1
         
         return vis
     

wrapper.py

@@ -106,30 +106,24 @@ def _collect_outputs(work: Path, plants: Dict[str, Any]) -> Dict[str, str]:
                 st = entry.get('statistics', {}) if isinstance(entry, dict) else {}
                 if st:
                     stats_lines.append(f"{name}: mean={st.get('mean', 0):.3f}, std={st.get('std', 0):.3f}")
-            # Morphology stats (height for multiple plants)
+            # Morphology stats (height - always show as single plant)
             morph = pdata.get('morphology_features', {}) if isinstance(pdata, dict) else {}
             traits = morph.get('traits', {}) if isinstance(morph, dict) else {}
             
-            # Check if we have multiple plants
+            # Get plant height (system now filters to largest plant only)
             plant_heights = traits.get('plant_heights', {})
             num_plants = traits.get('num_plants', 0)
             
-            if isinstance(plant_heights, dict) and len(plant_heights) > 1:
-                # Multiple plants detected
-                stats_lines.append(f"Number of plants: {num_plants}")
-                # Sort by plant index for consistent display
-                sorted_plants = sorted(plant_heights.items(), key=lambda x: int(x[0].split('_')[1]))
-                for plant_name, height_cm in sorted_plants:
-                    plant_num = plant_name.split('_')[1]
-                    stats_lines.append(f"  Plant {plant_num}: {height_cm:.2f} cm")
-            elif isinstance(plant_heights, dict) and len(plant_heights) == 1:
-                # Single plant
+            # Always show as single plant (largest component)
+            if num_plants > 0 and isinstance(plant_heights, dict) and len(plant_heights) >= 1:
                 height_cm = list(plant_heights.values())[0]
+                stats_lines.append(f"Number of plants: 1")
                 stats_lines.append(f"Plant height: {height_cm:.2f} cm")
             else:
                 # Fallback to old single height field
                 height_cm = traits.get('plant_height_cm')
                 if isinstance(height_cm, (int, float)) and height_cm > 0:
+                    stats_lines.append(f"Number of plants: 1")
                     stats_lines.append(f"Plant height: {height_cm:.2f} cm")
             if stats_lines:
                 outputs['StatsText'] = "\n".join(stats_lines)