Update app.py

app.py

@@ -3,9 +3,8 @@ import cv2
 import joblib
 import mediapipe as mp
 import numpy as np
-from streamlit_webrtc import webrtc_streamer, VideoTransformerBase
 
-# Load the trained model and label encoder
+# Load trained model and label encoder
 model = joblib.load("pose_classifier.joblib")
 label_encoder = joblib.load("label_encoder.joblib")
 
@@ -13,34 +12,49 @@ label_encoder = joblib.load("label_encoder.joblib")
 mp_pose = mp.solutions.pose
 pose = mp_pose.Pose()
 
-class PoseTransformer(VideoTransformerBase):
-    def transform(self, frame):
-        img = frame.to_ndarray(format="bgr24")  # Convert to BGR format
-        img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+# Streamlit UI
+st.title("Live Pose Classification")
+st.write("Real-time pose detection using OpenCV and MediaPipe.")
 
-        # Process frame with MediaPipe Pose
-        results = pose.process(img_rgb)
+# OpenCV Video Capture
+cap = cv2.VideoCapture(0)
 
-        if results.pose_landmarks:
-            landmarks = results.pose_landmarks.landmark
-            pose_data = [j.x for j in landmarks] + [j.y for j in landmarks] + \
-                        [j.z for j in landmarks] + [j.visibility for j in landmarks]
+# Streamlit Image Display
+frame_placeholder = st.empty()
 
-            pose_data = np.array(pose_data).reshape(1, -1)
+while cap.isOpened():
+    ret, frame = cap.read()
+    if not ret:
+        st.warning("Failed to capture video. Check your camera.")
+        break
 
-            # Predict pose
-            y_pred = model.predict(pose_data)
-            predicted_label = label_encoder.inverse_transform(y_pred)[0]
+    # Convert frame to RGB
+    img_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
 
-            # Display predicted label
-            cv2.putText(img, f"Pose: {predicted_label}", (20, 50),
-                        cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 3)
+    # Process frame with MediaPipe Pose
+    results = pose.process(img_rgb)
 
-        return cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
+    if results.pose_landmarks:
+        landmarks = results.pose_landmarks.landmark
+        pose_data = [j.x for j in landmarks] + [j.y for j in landmarks] + \
+                    [j.z for j in landmarks] + [j.visibility for j in landmarks]
 
-# Streamlit UI
-st.title("Live Pose Classification")
-st.write("This application detects human poses in real-time.")
+        pose_data = np.array(pose_data).reshape(1, -1)
+
+        # Predict pose
+        y_pred = model.predict(pose_data)
+        predicted_label = label_encoder.inverse_transform(y_pred)[0]
+
+        # Display predicted label
+        cv2.putText(frame, f"Pose: {predicted_label}", (20, 50),
+                    cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 3)
+
+    # Display frame in Streamlit
+    frame_placeholder.image(frame, channels="BGR")
+
+    # Break loop if user stops execution
+    if st.button("Stop Camera"):
+        break
 
-# Start WebRTC Stream
-webrtc_streamer(key="pose-detection", video_transformer_factory=PoseTransformer)
+cap.release()
+cv2.destroyAllWindows()