Update app.py

app.py

@@ -19,30 +19,30 @@ def classify_action(detections):
     objects = [d[0] for d in detections]
     confidences = [d[1] for d in detections]
 
-    has_person = 'person' in objects
-    has_valuable = any(obj in objects for obj in ['backpack', 'handbag', 'laptop', 'cash', 'mobile', 'refrigerator', 'microwave'])
-    low_conf = max(confidences) < 0.55 if confidences else True
-    few_objects = len(set(objects)) <= 2
-    mostly_person = objects.count('person') > len(objects) * 0.6
-
-    if has_person:
-        # Stealing logic
+    num_persons = objects.count('person')
+    total_objects = len(objects)
+    avg_conf = np.mean(confidences) if confidences else 0.0
+
+    has_valuable = any(obj in objects for obj in ['backpack', 'handbag', 'laptop', 'cash', 'microwave', 'refrigerator'])
+
+    if num_persons >= 1:
+        # Stealing
         if has_valuable:
             action_scores['Stealing'] += 0.7
             if 'handbag' in objects or 'laptop' in objects:
                 action_scores['Stealing'] += 0.2
 
-        # Sneaking logic
-        if low_conf and not has_valuable:
-            action_scores['Sneaking'] += 0.8
+        # Sneaking - enhanced logic
+        if (total_objects <= 2 and avg_conf < 0.5 and not has_valuable):
+            action_scores['Sneaking'] += 0.9
 
-        # Peaking logic
-        elif few_objects and mostly_person:
+        # Peaking
+        elif (total_objects <= 3 and num_persons == 1 and avg_conf >= 0.5):
             action_scores['Peaking'] += 0.7
 
-        # Normal behavior fallback
+        # Normal fallback
         else:
-            action_scores['Normal'] += 0.5
+            action_scores['Normal'] += 0.6
     else:
         action_scores['Normal'] += 1.0
 
@@ -54,6 +54,7 @@ def classify_action(detections):
 
     return action_scores
 
+
 # ------------------ Detection Function ------------------
 def detect_action(image_path):
     results = model.predict(source=image_path, conf=0.4, iou=0.5, save=False, verbose=False)