Update app.py

app.py

@@ -78,7 +78,7 @@ def custom_nms(preds, iou_threshold=0.3):
 def process_image(job_id, image_path, object_type, multiplier):
     try:
         jobs[job_id]['progress'] = 10
-        # Load the original image freshly
+        # Load a fresh copy of the original image
         image = cv2.imread(image_path)
         if image is None:
             jobs[job_id]['progress'] = 100
@@ -87,7 +87,7 @@ def process_image(job_id, image_path, object_type, multiplier):
 
         jobs[job_id]['progress'] = 20
         img_height, img_width = image.shape[:2]
-        # Compute a dynamic thickness based on image size and multiplier.
+        # Compute dynamic thickness based on image size and multiplier.
         thickness = max(2, int(min(img_width, img_height) / 300)) * multiplier
         detection_info = []
 
@@ -97,7 +97,7 @@ def process_image(job_id, image_path, object_type, multiplier):
                 jobs[job_id]['result'] = {"error": "Roboflow model not available."}
                 return
 
-            # Upscale the image if it's small (to help detect small boxes)
+            # Upscale the image if it is small to help detect small boxes.
             scale_factor = 1
             if img_width < 1000 or img_height < 1000:
                 scale_factor = 2
@@ -106,11 +106,10 @@ def process_image(job_id, image_path, object_type, multiplier):
                 upscaled_image = cv2.resize(image, None, fx=scale_factor, fy=scale_factor, interpolation=cv2.INTER_LINEAR)
                 temp_path = "upscaled.jpg"
                 cv2.imwrite(temp_path, upscaled_image)
-                # Lower the confidence threshold to 30 and overlap to 20 for better sensitivity
                 results = box_model.predict(temp_path, confidence=30, overlap=20).json()
             else:
                 results = box_model.predict(image_path, confidence=30, overlap=20).json()
-            
+
             predictions = results.get("predictions", [])
             processed_preds = []
             for prediction in predictions:
@@ -142,24 +141,30 @@ def process_image(job_id, image_path, object_type, multiplier):
                 except Exception as e:
                     continue
 
-            # Increase NMS IoU threshold to 0.7 to prevent suppression of valid, close boxes.
+            # Use a higher NMS threshold to prevent merging valid nearby detections.
             box_detections = custom_nms(processed_preds, iou_threshold=0.7)
             jobs[job_id]['progress'] = 60
 
-            # ArUco Marker Detection for measurement:
-            # Here we assume the marker is printed at 5cm x 5cm.
-            marker_real_width_cm = 5.0  
+            # --- ArUco Marker Detection for Measurement ---
+            # We assume the marker is printed at 5cm x 5cm.
+            marker_real_width_cm = 5.0
             try:
-                # Use a fresh copy of the image (without drawn overlays) for detection.
+                # Create a fresh copy for ArUco detection to avoid drawn overlays
                 aruco_image = image.copy()
                 gray = cv2.cvtColor(aruco_image, cv2.COLOR_BGR2GRAY)
-                # Use the DICT_6X6_250 dictionary. (You can change to DICT_4X4_50 if desired.)
+                # Use DICT_6X6_250 – ensure your printed marker is generated with this dictionary.
                 aruco_dict = cv2.aruco.getPredefinedDictionary(cv2.aruco.DICT_6X6_250)
+                # Create and adjust detector parameters for small markers
                 aruco_params = cv2.aruco.DetectorParameters_create()
-                # Optionally tweak parameters, e.g., aruco_params.minMarkerPerimeterRate = 0.03
-                corners, ids, _ = cv2.aruco.detectMarkers(gray, aruco_dict, parameters=aruco_params)
+                aruco_params.adaptiveThreshWinSizeMin = 3
+                aruco_params.adaptiveThreshWinSizeMax = 23
+                aruco_params.adaptiveThreshWinSizeStep = 10
+                aruco_params.minMarkerPerimeterRate = 0.03
+                aruco_params.cornerRefinementMethod = cv2.aruco.CORNER_REFINE_SUBPIX
+
+                corners, ids, rejected = cv2.aruco.detectMarkers(gray, aruco_dict, parameters=aruco_params)
+                print("DEBUG: Detected ArUco ids:", ids)
                 if ids is not None and len(corners) > 0:
-                    # Use the first detected marker as reference.
                     marker_corners = corners[0].reshape((4, 2))
                     cv2.aruco.drawDetectedMarkers(image, corners, ids)
                     side_lengths = []
@@ -169,9 +174,12 @@ def process_image(job_id, image_path, object_type, multiplier):
                         side_lengths.append(np.linalg.norm(pt1 - pt2))
                     avg_side_length = np.mean(side_lengths)
                     conversion_factor = marker_real_width_cm / avg_side_length
+                    print("DEBUG: Marker conversion factor:", conversion_factor)
                 else:
+                    print("DEBUG: No ArUco marker detected.")
                     conversion_factor = None
             except Exception as e:
+                print("DEBUG: Exception in ArUco detection:", e)
                 conversion_factor = None
 
             for pred in box_detections: