Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 import cv2
 import mediapipe as mp
-import numpy as np
+import tempfile
 
 # Initialize MediaPipe once
 mp_hands = mp.solutions.hands
@@ -23,62 +23,58 @@ pose = mp_pose.Pose(
     min_tracking_confidence=0.5
 )
 
-def process_frame(frame, target_width=640, return_original_size=False):
-    """
-    frame: RGB image from webcam
-    target_width: width to resize before processing
-    return_original_size: upscale output back to original size
-    """
-    if frame is None:
-        return None
+def process_video(video_path, target_width=640):
+    cap = cv2.VideoCapture(video_path)
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    temp_output = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4")
+    out = None
 
-    h0, w0 = frame.shape[:2]
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
 
-    # Compute resize keeping aspect ratio
-    target_width = max(160, int(target_width))
-    scale = target_width / float(w0)
-    target_height = int(round(h0 * scale))
+        h0, w0 = frame.shape[:2]
+        # Resize frame keeping aspect ratio
+        scale = target_width / float(w0)
+        target_height = int(round(h0 * scale))
+        frame_small = cv2.resize(frame, (target_width, target_height), interpolation=cv2.INTER_AREA)
 
-    # Resize for processing
-    rgb_small = cv2.resize(frame, (target_width, target_height), interpolation=cv2.INTER_AREA)
+        # Convert BGR to RGB
+        rgb_small = cv2.cvtColor(frame_small, cv2.COLOR_BGR2RGB)
 
-    # Process with MediaPipe
-    hand_results = hands.process(rgb_small)
-    pose_results = pose.process(rgb_small)
+        # Hand detection
+        hand_results = hands.process(rgb_small)
+        if hand_results.multi_hand_landmarks:
+            for hand_landmarks in hand_results.multi_hand_landmarks:
+                mp_drawing.draw_landmarks(frame_small, hand_landmarks, mp_hands.HAND_CONNECTIONS)
 
-    # Convert to BGR for drawing
-    bgr_draw = cv2.cvtColor(rgb_small, cv2.COLOR_RGB2BGR)
+        # Pose detection
+        pose_results = pose.process(rgb_small)
+        if pose_results.pose_landmarks:
+            mp_drawing.draw_landmarks(frame_small, pose_results.pose_landmarks, mp_pose.POSE_CONNECTIONS)
 
-    # Draw hands
-    if hand_results.multi_hand_landmarks:
-        for hand_landmarks in hand_results.multi_hand_landmarks:
-            mp_drawing.draw_landmarks(bgr_draw, hand_landmarks, mp_hands.HAND_CONNECTIONS)
+        # Initialize video writer
+        if out is None:
+            out = cv2.VideoWriter(temp_output.name, fourcc, cap.get(cv2.CAP_PROP_FPS), (frame_small.shape[1], frame_small.shape[0]))
 
-    # Draw pose
-    if pose_results.pose_landmarks:
-        mp_drawing.draw_landmarks(bgr_draw, pose_results.pose_landmarks, mp_pose.POSE_CONNECTIONS)
+        out.write(frame_small)
 
-    # Convert back to RGB for Gradio
-    rgb_out_small = cv2.cvtColor(bgr_draw, cv2.COLOR_BGR2RGB)
+    cap.release()
+    if out:
+        out.release()
 
-    if return_original_size:
-        rgb_out = cv2.resize(rgb_out_small, (w0, h0), interpolation=cv2.INTER_LINEAR)
-        return rgb_out
-    else:
-        return rgb_out_small
+    return temp_output.name
 
-# Gradio Interface
 iface = gr.Interface(
-    fn=process_frame,
+    fn=process_video,
     inputs=[
-        gr.inputs.Image(shape=(640,480), webcam=True, label="Webcam Input"),
-        gr.inputs.Slider(minimum=160, maximum=1280, default=640, step=20, label="Processing width"),
-        gr.inputs.Checkbox(default=False, label="Return at original webcam resolution")
+        gr.Video(label="Upload a video"),
+        gr.Slider(minimum=160, maximum=1280, value=640, step=20, label="Processing width")
     ],
-    outputs=gr.outputs.Image(label="Processed Output"),
-    live=True,
-    title="Live Hand & Body Pose Detection",
-    description="Real-time MediaPipe Hand and Body Pose detection from webcam."
+    outputs=gr.Video(label="Processed video"),
+    title="Hand & Body Pose Detection from Video",
+    description="Upload a video and see MediaPipe detect hands and body pose."
 )
 
 if __name__ == "__main__":