Update app.py

app.py

@@ -3,54 +3,56 @@ from PIL import Image
 import numpy as np
 from ultralytics import YOLO
 
+# Streamlit configuration
 st.set_page_config(page_title="Suspicious Activity Detection", layout="centered")
 
-# Load the YOLOv11 model
+# Load YOLOv11 model
 @st.cache_resource
 def load_model():
-    return YOLO("yolo11l.pt")  # Ensure your model file is present in the root directory
+    return YOLO("yolo11l (1).pt")  # Match the uploaded filename
 
 model = load_model()
 
-# ------------------ Intelligent Action Classification Logic ------------------
+# ------------------ Action Classification Logic ------------------
 def classify_action(detections):
     """
-    Classifies the activity based on detected object types and confidence scores.
-    Adjusted to better separate 'Sneaking' from 'Peaking'.
+    Classify action using object types and confidence.
+    Sneaking: person detected with low confidence, alone, and few objects.
     """
-    action_scores = {'Stealing': 0, 'Sneaking': 0, 'Peaking': 0, 'Normal': 0}
+    action_scores = {
+        'Stealing': 0,
+        'Sneaking': 0,
+        'Peaking': 0,
+        'Normal': 0
+    }
+
     objects = [d[0] for d in detections]
     confidences = [d[1] for d in detections]
-
     has_person = 'person' in objects
-    has_bag = any(obj in objects for obj in ['backpack', 'handbag'])
-    low_conf = max(confidences) < 0.6 if confidences else True
-    few_objects = len(set(objects)) <= 2
-    mostly_person = objects.count('person') >= len(objects) * 0.6
+    num_objects = len(objects)
 
     if has_person:
-        if has_bag:
+        if ('handbag' in objects or 'backpack' in objects) and num_objects > 2:
             action_scores['Stealing'] += 0.7
-        if low_conf and few_objects:
-            action_scores['Sneaking'] += 0.9
-        elif mostly_person and few_objects:
+        if max(confidences) < 0.55 and num_objects <= 2:
+            action_scores['Sneaking'] += 0.8
+        if num_objects <= 2 and max(confidences) > 0.55:
             action_scores['Peaking'] += 0.6
-        else:
-            action_scores['Normal'] += 0.8
+        if action_scores['Stealing'] == 0 and action_scores['Sneaking'] == 0 and action_scores['Peaking'] == 0:
+            action_scores['Normal'] = 1.0
     else:
-        action_scores['Normal'] += 1.0
+        action_scores['Normal'] = 1.0
 
-    # Normalize scores
     total = sum(action_scores.values())
     if total > 0:
-        for k in action_scores:
-            action_scores[k] /= total
+        for key in action_scores:
+            action_scores[key] /= total
 
     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)
+    results = model.predict(source=image_path, conf=0.3, iou=0.5, save=False, verbose=False)
     result = results[0]
 
     detections = [
@@ -64,10 +66,10 @@ def detect_action(image_path):
     return annotated_image, action_scores
 
 # ------------------ Streamlit UI ------------------
-st.title("🛡️ Suspicious Activity Detection")
-st.markdown("Upload an image to detect if someone is **Stealing**, **Sneaking**, **Peaking**, or acting **Normal**.")
+st.title("🔍 Suspicious Activity Detection")
+st.markdown("Upload an image to detect if someone is **Stealing**, **Sneaking**, **Peaking**, or just acting **Normal**.")
 
-uploaded_file = st.file_uploader("📸 Upload an image", type=["jpg", "jpeg", "png"])
+uploaded_file = st.file_uploader("📤 Upload an image", type=["jpg", "jpeg", "png"])
 
 if uploaded_file:
     image = Image.open(uploaded_file).convert("RGB")
@@ -76,14 +78,14 @@ if uploaded_file:
     temp_path = "/tmp/uploaded.jpg"
     image.save(temp_path)
 
-    with st.spinner("🔍 Detecting suspicious activity..."):
+    with st.spinner("🕵️ Detecting suspicious activity..."):
         detected_image, action_scores = detect_action(temp_path)
 
-    st.image(detected_image, caption="🔍 Detection Results", use_column_width=True)
+    st.image(detected_image, caption="🔍 Detected Image", use_column_width=True)
 
     st.subheader("📊 Action Confidence Scores")
     for action, score in action_scores.items():
         st.write(f"**{action}**: {score:.2%}")
 
-    top_action = max(action_scores.items(), key=lambda x: x[1])
-    st.success(f"🎯 **Predicted Action:** {top_action[0]} ({top_action[1]:.2%} confidence)")
+    most_likely_action = max(action_scores.items(), key=lambda x: x[1])
+    st.success(f"🎯 **Predicted Action**: {most_likely_action[0]} ({most_likely_action[1]:.2%} confidence)")