Update app.py

app.py

@@ -1,32 +1,63 @@
-import cv2
 import gradio as gr
-from transformers import pipeline
+import cv2
+import numpy as np
+from tensorflow.keras.models import load_model
+from sklearn.preprocessing import StandardScaler
+from ultralytics import YOLO
 
-# Load YOLOv8 model and suspicious activity classification model
-pose_detection = pipeline("object-detection", model="yolov8-pose")  # Correct path if it's inside same folder.
-suspicious_activity_detection = pipeline("text-classification", model="suspicious_activity_model")
+# Load models
+lstm_model = load_model('suspicious_activity_model.h5')
+yolo_model = YOLO('yolov8n-pose.pt')  # Ensure this model supports keypoint detection
+scaler = StandardScaler()
 
+# Function to extract keypoints from a frame
+def extract_keypoints(frame):
+    results = yolo_model(frame, verbose=False)
+    for r in results:
+        if r.keypoints is not None and len(r.keypoints) > 0:
+            keypoints = r.keypoints.xyn.tolist()[0]  # Use the first person's keypoints
+            flattened_keypoints = [kp for keypoint in keypoints for kp in keypoint[:2]]  # Flatten x, y values
+            return flattened_keypoints
+    return None  # Return None if no keypoints are detected
+
+# Function to process each frame
 def process_frame(frame):
-    results = pose_detection(frame)
+    results = yolo_model(frame, verbose=False)
+
+    for box in results[0].boxes:
+        cls = int(box.cls[0])  # Class ID
+        confidence = float(box.conf[0])
 
-    for person in results:
-        if person['label'] == 'person':
-            x1, y1, x2, y2 = map(int, person['box'].values())
-            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
-            cv2.putText(frame, 'Detected', (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
+        if cls == 0 and confidence > 0.5:  # Detect persons only
+            x1, y1, x2, y2 = map(int, box.xyxy[0])  # Bounding box coordinates
+
+            # Extract ROI for classification
+            roi = frame[y1:y2, x1:x2]
+            if roi.size > 0:
+                keypoints = extract_keypoints(roi)
+                if keypoints is not None and len(keypoints) > 0:
+                    keypoints_scaled = scaler.fit_transform([keypoints])
+                    keypoints_reshaped = keypoints_scaled.reshape((1, 1, len(keypoints)))
+
+                    prediction = (lstm_model.predict(keypoints_reshaped) > 0.5).astype(int)[0][0]
+
+                    color = (0, 0, 255) if prediction == 1 else (0, 255, 0)
+                    label = 'Suspicious' if prediction == 1 else 'Normal'
+                    cv2.rectangle(frame, (x1, y1), (x2, y2), color, 2)
+                    cv2.putText(frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
     return frame
 
-def live_detection(frame):
-    frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+# Gradio video streaming function
+def video_processing(video_frame):
+    frame = cv2.cvtColor(video_frame, cv2.COLOR_BGR2RGB)  # Convert to RGB
     processed_frame = process_frame(frame)
     return processed_frame
 
-interface = gr.Interface(
-    fn=live_detection,
-    inputs=gr.Image(source="webcam", tool="editor", type="numpy"),
-    outputs=gr.Image(type="numpy"),
-    live=True
-)
-
-if __name__ == "__main__":
-    interface.launch(server_name="0.0.0.0", server_port=7860)
+# Launch Gradio app
+gr.Interface(
+    fn=video_processing,
+    inputs=gr.Video(source="webcam", streaming=True),
+    outputs="video",
+    live=True,
+    title="Suspicious Activity Detection"
+).launch(debug=True)