Update src/streamlit_app.py

src/streamlit_app.py

@@ -7,6 +7,8 @@ import mediapipe as mp
 import time
 import os
 from mediapipe.python.solutions import hands
+from streamlit_webrtc import webrtc_streamer, VideoTransformerBase
+
 
 st.set_page_config(page_title="🖐️ Hand Tracking Demo", layout="wide")
 
@@ -54,52 +56,93 @@ st.title("🖐️ Hand Tracking Demo")
 stop_button = st.button("Stop")
 frame_placeholder = st.empty()
 finger_count_text = st.empty()
-# Initialize webcam
-cap = cv2.VideoCapture(0)
-# Initialize finger count
-current_finger_count = 0
-
-# Initialize MediaPipe Hands
-with hands.Hands(
-    max_num_hands=2, min_detection_confidence=0.5, min_tracking_confidence=0.5
-) as hands_model:
-    while not stop_button:
-        ret, frame = cap.read()
-        if not ret:
-            st.error("Failed to capture video from webcam")
-            break
-        frame = cv2.flip(frame, 1)
-        frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+
+
+class VideoProcessor(VideoTransformerBase):
+    def __init__(self):
+        self.finger_count = 0
+
+    def transform(self, frame):
+        img = frame.to_ndarray(format="bgr24")
+        frame_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
         mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=frame_rgb)
         result = landmarker.detect(mp_image)
-        # Reset finger count for each frame
-        current_finger_count = 0
+
+        self.finger_count = 0
         if result.hand_landmarks:
             for hand_landmarks in result.hand_landmarks:
-                # Draw landmarks & connections
-                draw_hand_landmarks(frame, hand_landmarks)
-                # Calculate finger count for this hand
+                draw_hand_landmarks(img, hand_landmarks)
                 hand_finger_count = 0
-                if hand_landmarks[4].y < hand_landmarks[3].y:  # Thumb
+                if hand_landmarks[4].y < hand_landmarks[3].y:
                     hand_finger_count += 1
-                for i in [8, 12, 16, 20]:  # Index, middle, ring, pinky
+                for i in [8, 12, 16, 20]:
                     if hand_landmarks[i].y < hand_landmarks[i - 2].y:
                         hand_finger_count += 1
-                # Add this hand's fingers to the total count
-                current_finger_count += hand_finger_count
-        # Display finger count
-        finger_count_text.markdown(f"### Fingers detected: {current_finger_count}")
-        # Convert BGR to RGB for displaying in Streamlit
-        frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-        frame_placeholder.image(frame_rgb, channels="RGB")
-        # Add a small delay to simulate real-time processing
-        time.sleep(0.05)
-        # Rerun to check if stop button was pressed
-        if stop_button:
-            break
-# Release resources
-cap.release()
-st.success("Camera released. Application stopped.")
+                self.finger_count += hand_finger_count
+
+        return img
+
+# Start webcam capture
+ctx = webrtc_streamer(
+    key="hand-tracker",
+    video_processor_factory=VideoProcessor,
+    media_stream_constraints={"video": True, "audio": False},
+    async_processing=True,
+)
+
+# Display finger count
+if ctx.state.playing:
+    st.markdown("### Live tracking active...")
+    while ctx.video_processor:
+        finger_count_text.markdown(f"### Fingers detected: {ctx.video_processor.finger_count}")
+        time.sleep(0.1)
+else:
+    st.info("Click 'Start' to begin camera tracking.")
+
+# Initialize finger count
+# current_finger_count = 0
+
+# # Initialize MediaPipe Hands
+# with hands.Hands(
+#     max_num_hands=2, min_detection_confidence=0.5, min_tracking_confidence=0.5
+# ) as hands_model:
+#     while not stop_button:
+#         ret, frame = cap.read()
+#         if not ret:
+#             st.error("Failed to capture video from webcam")
+#             break
+#         frame = cv2.flip(frame, 1)
+#         frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+#         mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=frame_rgb)
+#         result = landmarker.detect(mp_image)
+#         # Reset finger count for each frame
+#         current_finger_count = 0
+#         if result.hand_landmarks:
+#             for hand_landmarks in result.hand_landmarks:
+#                 # Draw landmarks & connections
+#                 draw_hand_landmarks(frame, hand_landmarks)
+#                 # Calculate finger count for this hand
+#                 hand_finger_count = 0
+#                 if hand_landmarks[4].y < hand_landmarks[3].y:  # Thumb
+#                     hand_finger_count += 1
+#                 for i in [8, 12, 16, 20]:  # Index, middle, ring, pinky
+#                     if hand_landmarks[i].y < hand_landmarks[i - 2].y:
+#                         hand_finger_count += 1
+#                 # Add this hand's fingers to the total count
+#                 current_finger_count += hand_finger_count
+#         # Display finger count
+#         finger_count_text.markdown(f"### Fingers detected: {current_finger_count}")
+#         # Convert BGR to RGB for displaying in Streamlit
+#         frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+#         frame_placeholder.image(frame_rgb, channels="RGB")
+#         # Add a small delay to simulate real-time processing
+#         time.sleep(0.05)
+#         # Rerun to check if stop button was pressed
+#         if stop_button:
+#             break
+# # Release resources
+# cap.release()
+# st.success("Camera released. Application stopped.")
 
 
 # """