Update app.py

app.py

@@ -2,11 +2,9 @@ import cv2
 import mediapipe as mp
 import numpy as np
 import gradio as gr
-import tempfile
 
-# Load model
+# MediaPipe setup
 MODEL_PATH = "hand_landmarker.task"
-
 BaseOptions = mp.tasks.BaseOptions
 HandLandmarker = mp.tasks.vision.HandLandmarker
 HandLandmarkerOptions = mp.tasks.vision.HandLandmarkerOptions
@@ -46,61 +44,42 @@ def get_finger_color(start_idx):
     else:
         return FINGER_COLORS['palm']
 
-def process_video(video_path):
-    cap = cv2.VideoCapture(video_path)
-
-    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
-    tmp_out = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
-    out_path = tmp_out.name
-
-    fps = cap.get(cv2.CAP_PROP_FPS)
-    w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-    h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-    out = cv2.VideoWriter(out_path, fourcc, fps, (w, h))
-
-    options = HandLandmarkerOptions(
-        base_options=BaseOptions(model_asset_path=MODEL_PATH),
-        running_mode=VisionRunningMode.IMAGE,
-        num_hands=2,
-        min_hand_detection_confidence=0.5,
-        min_hand_presence_confidence=0.5,
-        min_tracking_confidence=0.5
-    )
-
-    with HandLandmarker.create_from_options(options) as landmarker:
-        while cap.isOpened():
-            ret, frame = cap.read()
-            if not ret:
-                break
-
-            rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-            mp_img = mp_image(image_format=mp_format.SRGB, data=rgb_frame)
-            results = landmarker.detect(mp_img)
-
-            if results.hand_landmarks:
-                for hand_landmarks in results.hand_landmarks:
-                    points = [(int(lm.x * w), int(lm.y * h)) for lm in hand_landmarks]
-
-                    for start, end in HAND_CONNECTIONS:
-                        color = get_finger_color(start)
-                        cv2.line(frame, points[start], points[end], color, 2)
-
-                    for i, (x, y) in enumerate(points):
-                        cv2.circle(frame, (x, y), 4, (0, 255, 255), -1)
-
-            out.write(frame)
-
-    cap.release()
-    out.release()
-    return out_path
-
-# Gradio interface
-demo = gr.Interface(
-    fn=process_video,
-    inputs=gr.Video(label="Upload Video or Use Webcam"),
-    outputs=gr.Video(label="Hand Landmark Annotated Video"),
-    title="Hand Detection ",
-    description="Upload a video or use webcam to detect hands."
+# Load model only once
+options = HandLandmarkerOptions(
+    base_options=BaseOptions(model_asset_path=MODEL_PATH),
+    running_mode=VisionRunningMode.IMAGE,
+    num_hands=2,
+    min_hand_detection_confidence=0.5,
+    min_hand_presence_confidence=0.5,
+    min_tracking_confidence=0.5
 )
-
-demo.launch()
+landmarker = HandLandmarker.create_from_options(options)
+
+# Main processing function
+def detect_hand(frame):
+    rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+    mp_img = mp_image(image_format=mp_format.SRGB, data=rgb_frame)
+    results = landmarker.detect(mp_img)
+
+    h, w, _ = frame.shape
+    if results.hand_landmarks:
+        for hand_landmarks in results.hand_landmarks:
+            points = [(int(lm.x * w), int(lm.y * h)) for lm in hand_landmarks]
+
+            for start, end in HAND_CONNECTIONS:
+                color = get_finger_color(start)
+                cv2.line(frame, points[start], points[end], color, 2)
+
+            for (x, y) in points:
+                cv2.circle(frame, (x, y), 4, (0, 255, 255), -1)
+
+    return frame
+
+# Gradio UI
+gr.Interface(
+    fn=detect_hand,
+    inputs=gr.Image(source="webcam", streaming=True, label="Webcam Input"),
+    outputs=gr.Image(label="Annotated Frame"),
+    title="Real-time Hand Detection with MediaPipe",
+    live=True
+).launch()