Update

app.py

@@ -3,7 +3,7 @@ import mediapipe as mp
 import numpy as np
 import gradio as gr
 
-# Initialize MediaPipe Pose.
+# Initialize MediaPipe Pose
 mp_pose = mp.solutions.pose
 pose = mp_pose.Pose(
     static_image_mode=False,
@@ -13,7 +13,7 @@ pose = mp_pose.Pose(
     min_tracking_confidence=0.5
 )
 
-# Initialize MediaPipe Face Mesh.
+# Initialize MediaPipe Face Mesh
 mp_face_mesh = mp.solutions.face_mesh
 face_mesh = mp_face_mesh.FaceMesh(
     static_image_mode=False,
@@ -25,96 +25,80 @@ face_mesh = mp_face_mesh.FaceMesh(
 
 def process_frame(image):
     """
-    Processes an input image (from the webcam) by:
-      1. Converting from RGB (Gradio default) to BGR for OpenCV.
+    Processes a frame by:
+      1. Converting RGB to BGR for OpenCV.
       2. Flipping the frame for a mirror view.
       3. Creating a black background.
-      4. Using MediaPipe Pose to draw body landmarks (excluding facial parts) and compute the shoulder center.
-      5. Using MediaPipe Face Mesh to draw the full facial mesh and extract the chin point.
-      6. Drawing a neck line from the shoulder center to the chin.
-      7. Converting the result back to RGB for display.
+      4. Drawing body landmarks and computing shoulder center.
+      5. Drawing facial mesh and extracting chin point.
+      6. Drawing a neck line from shoulder center to chin.
+      7. Converting the result back to RGB.
     """
-    # Convert the input image from RGB (Gradio default) to BGR.
     frame = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
-    
-    # Flip the frame horizontally for a mirror view.
     frame = cv2.flip(frame, 1)
-    
-    # Create a black background image of the same size.
     output = np.zeros_like(frame)
-    
-    # Convert frame to RGB for MediaPipe processing.
     rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-    
-    # --- Body Posture Analysis using MediaPipe Pose ---
+
+    # --- Body Posture Analysis ---
     pose_results = pose.process(rgb_frame)
     shoulder_center = None
     if pose_results.pose_landmarks:
         h, w, _ = frame.shape
         landmarks = [(int(lm.x * w), int(lm.y * h)) for lm in pose_results.pose_landmarks.landmark]
-        
-        # Draw body skeleton (only drawing non-facial landmarks, i.e. indices 11 and above).
+
         for connection in mp_pose.POSE_CONNECTIONS:
             start_idx, end_idx = connection
             if start_idx >= 11 and end_idx >= 11:
                 if start_idx < len(landmarks) and end_idx < len(landmarks):
                     cv2.line(output, landmarks[start_idx], landmarks[end_idx], (255, 255, 0), 2)
-        
-        # Draw landmarks as yellow circles.
+
         for i, pt in enumerate(landmarks):
             if i >= 11:
                 cv2.circle(output, pt, 3, (255, 255, 0), -1)
-        
-        # Calculate shoulder center using landmarks 11 (left shoulder) and 12 (right shoulder).
+
         if len(landmarks) > 12:
-            left_shoulder = landmarks[11]
-            right_shoulder = landmarks[12]
+            left_shoulder, right_shoulder = landmarks[11], landmarks[12]
             shoulder_center = ((left_shoulder[0] + right_shoulder[0]) // 2,
                                (left_shoulder[1] + right_shoulder[1]) // 2)
             cv2.circle(output, shoulder_center, 4, (0, 255, 255), -1)
-    
-    # --- Facemesh Analysis using MediaPipe Face Mesh ---
+
+    # --- Facial Mesh Analysis ---
     chin_point = None
     fm_results = face_mesh.process(rgb_frame)
     if fm_results.multi_face_landmarks:
         for face_landmarks in fm_results.multi_face_landmarks:
             h, w, _ = frame.shape
             fm_points = [(int(lm.x * w), int(lm.y * h)) for lm in face_landmarks.landmark]
-            
-            # Draw red lines connecting facial landmarks.
+
             for connection in mp_face_mesh.FACEMESH_TESSELATION:
                 start_idx, end_idx = connection
                 if start_idx < len(fm_points) and end_idx < len(fm_points):
                     cv2.line(output, fm_points[start_idx], fm_points[end_idx], (0, 0, 255), 1)
-            
-            # Draw green dots for each facial landmark.
+
             for pt in fm_points:
                 cv2.circle(output, pt, 2, (0, 255, 0), -1)
-            
-            # Extract the chin point (landmark 152 is generally at the bottom of the chin).
+
             if len(face_landmarks.landmark) > 152:
                 lm = face_landmarks.landmark[152]
                 chin_point = (int(lm.x * w), int(lm.y * h))
                 cv2.circle(output, chin_point, 4, (0, 0, 255), -1)
             break  # Process only the first detected face.
-    
-    # --- Draw the Neck Line ---
+
+    # --- Draw Neck Line ---
     if shoulder_center and chin_point:
         cv2.line(output, shoulder_center, chin_point, (0, 255, 255), 2)
-    
-    # Convert the processed image back to RGB for display.
-    output_rgb = cv2.cvtColor(output, cv2.COLOR_BGR2RGB)
-    return output_rgb
 
-# Create the Gradio interface.
+    return cv2.cvtColor(output, cv2.COLOR_BGR2RGB)
+
+
+# --- Gradio Interface for Live Webcam Inference ---
 iface = gr.Interface(
     fn=process_frame,
-    inputs=gr.Image(source="webcam", type="numpy", label="Webcam"),
+    inputs=gr.Image(sources=["webcam"], streaming=True, label="Webcam Input"),  # Live webcam stream
     outputs=gr.Image(type="numpy", label="Processed Output"),
     live=True,
-    title="Body Posture & Neck Analysis (No Face Pose)",
-    description="Webcam-based analysis using MediaPipe Pose and Face Mesh."
+    title="Live Body Posture & Neck Analysis (No Face Pose)",
+    description="Real-time webcam analysis using MediaPipe Pose and Face Mesh with live inference."
 )
 
-# Launch the Gradio app.
 iface.launch()