Update services/plantation/plant_health.py

services/plantation/plant_health.py

@@ -1,85 +1,77 @@
 import cv2
 import numpy as np
-from ultralytics import YOLO
-import os
 import logging
-from typing import Tuple, List, Dict, Any
+from typing import List, Dict, Tuple
 
-# Configure logging
+# Setup logging
 logging.basicConfig(
     filename="app.log",
     level=logging.INFO,
     format="%(asctime)s - %(levelname)s - %(message)s"
 )
 
-# Define base directory and model path
-BASE_DIR = os.path.dirname(os.path.abspath(__file__))
-MODEL_PATH = os.path.abspath(os.path.join(BASE_DIR, "../../models/yolov8n.pt"))
-
-# Initialize YOLO model
-try:
-    model = YOLO(MODEL_PATH)
-    logging.info("Loaded YOLOv8n model for plant health detection.")
-    logging.info(f"Model class names: {model.names}")
-except Exception as e:
-    logging.error(f"Failed to load YOLOv8n model: {str(e)}")
-    model = None
-
-def process_plant_health(frame: np.ndarray) -> Tuple[List[Dict[str, Any]], np.ndarray]:
-    # Validate input frame
-    if not isinstance(frame, np.ndarray) or frame.size == 0:
-        logging.error("Invalid input frame provided to plant_health.")
-        return [], frame
-
-    # Check if model is loaded
-    if model is None:
-        logging.error("YOLO model not loaded. Skipping plant health detection.")
-        return [], frame
-
+def process_plant_health(frame: np.ndarray) -> Tuple[List[Dict], np.ndarray]:
+    """
+    Process a frame to assess plant health based on color.
+    Args:
+        frame: Input frame (BGR numpy array)
+    Returns:
+        Tuple: (List of detection dictionaries with health status, annotated frame)
+    """
     try:
-        # Perform YOLO inference
-        results = model(frame, verbose=False)
-        logging.debug("Completed YOLO inference for plant health detection.")
-    except Exception as e:
-        logging.error(f"Error during YOLO inference: {str(e)}")
-        return [], frame
+        # Convert frame to HSV
+        hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
 
-    detections: List[Dict[str, Any]] = []
-    line_counter = 1
+        # Define range for green (healthy) and yellow/brown (unhealthy)
+        lower_green = np.array([35, 40, 40])
+        upper_green = np.array([85, 255, 255])
+        green_mask = cv2.inRange(hsv, lower_green, upper_green)
 
-    for r in results:
-        for box in r.boxes:
-            conf = float(box.conf[0])
-            if conf < 0.3:
-                continue
-            cls = int(box.cls[0])
-            label = model.names[cls]
-            if label != "unhealthy_plant":
+        # Define range for yellow/brown (unhealthy)
+        lower_unhealthy = np.array([20, 40, 40])
+        upper_unhealthy = np.array([35, 255, 255])
+        unhealthy_mask = cv2.inRange(hsv, lower_unhealthy, upper_unhealthy)
+
+        detections = []
+        # Process green regions (healthy plants)
+        contours, _ = cv2.findContours(green_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+        for idx, contour in enumerate(contours):
+            area = cv2.contourArea(contour)
+            if area < 300:
                 continue
-            xyxy = box.xyxy[0].cpu().numpy().astype(int)
-            x_min, y_min, x_max, y_max = xyxy
+            x, y, w, h = cv2.boundingRect(contour)
+            x_min, y_min, x_max, y_max = x, y, x + w, y + h
+            detections.append({
+                "type": "plant",
+                "label": f"Plant {idx + 1} - Healthy",
+                "box": [x_min, y_min, x_max, y_max],
+                "health": "Healthy"
+            })
+            cv2.rectangle(frame, (x_min, y_min), (x_max, y_max), (0, 255, 0), 2)
+            cv2.putText(frame, "Healthy", (x_min, y_min - 10),
+                        cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
 
-            detection_label = f"Line {line_counter} - Unhealthy Plant (Conf: {conf:.2f})"
+        # Process unhealthy regions
+        contours, _ = cv2.findContours(unhealthy_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+        for idx, contour in enumerate(contours):
+            area = cv2.contourArea(contour)
+            if area < 300:
+                continue
+            x, y, w, h = cv2.boundingRect(contour)
+            x_min, y_min, x_max, y_max = x, y, x + w, y + h
             detections.append({
-                "type": "unhealthy_plant",
-                "label": detection_label,
-                "confidence": conf,
-                "coordinates": [x_min, y_min, x_max, y_max]
+                "type": "plant",
+                "label": f"Plant {idx + 1} - Unhealthy",
+                "box": [x_min, y_min, x_max, y_max],
+                "health": "Unhealthy"
             })
+            cv2.rectangle(frame, (x_min, y_min), (x_max, y_max), (255, 0, 0), 2)
+            cv2.putText(frame, "Unhealthy", (x_min, y_min - 10),
+                        cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 0), 2)
 
-            color = (0, 255, 0)  # Green for unhealthy plants
-            cv2.rectangle(frame, (x_min, y_min), (x_max, y_max), color, 2)
-            cv2.putText(
-                frame,
-                detection_label,
-                (x_min, y_min - 10),
-                cv2.FONT_HERSHEY_SIMPLEX,
-                0.6,
-                color,
-                2
-            )
-            
-            line_counter += 1
+        logging.info(f"Assessed health of {len(detections)} plants in frame.")
+        return detections, frame
 
-    logging.info(f"Detected {len(detections)} unhealthy plants in plantation.")
-    return detections, frame
+    except Exception as e:
+        logging.error(f"Error in plant health assessment: {str(e)}")
+        return [], frame