Update app.py

app.py

@@ -1,68 +1,72 @@
 import gradio as gr
 import cv2
-import mediapipe as mp
+from huggingface_hub import hf_hub_download
+from gradio_webrtc import WebRTC
+from twilio.rest import Client
+import os
+from inference import YOLOv10
 
-# 初始化 MediaPipe Hands
-mp_hands = mp.solutions.hands
-mp_drawing = mp.solutions.drawing_utils
-hands = mp_hands.Hands(min_detection_confidence=0.3, min_tracking_confidence=0.3)
+model_file = hf_hub_download(
+    repo_id="onnx-community/yolov10n", filename="onnx/model.onnx"
+)
 
-# 手势检测函数
-def detection(image, conf_threshold=0.5):
-    """
-    使用 MediaPipe Hands 进行手势检测。
-    """
-    # 将图像从 BGR 转换为 RGB（MediaPipe 需要 RGB 格式）
-    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+model = YOLOv10(model_file)
 
-    # 将图像大小缩小到一个较小的尺寸，降低计算负担
-    image = cv2.resize(image, (640, 480))
+account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
+auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
 
-    # 使用 MediaPipe Hands 处理图像
-    results = hands.process(image_rgb)
+if account_sid and auth_token:
+    client = Client(account_sid, auth_token)
+
+    token = client.tokens.create()
+
+    rtc_configuration = {
+        "iceServers": token.ice_servers,
+        "iceTransportPolicy": "relay",
+    }
+else:
+    rtc_configuration = None
 
-    # 如果检测到手，绘制手部关键点
-    if results.multi_hand_landmarks:
-        for hand_landmarks in results.multi_hand_landmarks:
-            mp_drawing.draw_landmarks(
-                image, hand_landmarks, mp_hands.HAND_CONNECTIONS
-            )
 
-    # 返回带注释的图像
-    return image
+def detection(image, conf_threshold=0.3):
+    image = cv2.resize(image, (model.input_width, model.input_height))
+    new_image = model.detect_objects(image, conf_threshold)
+    return cv2.resize(new_image, (500, 500))
+
 
-# Gradio 界面
 css = """.my-group {max-width: 600px !important; max-height: 600 !important;}
-         .my-column {display: flex !important; justify-content: center !important; align-items: center !important;}"""
+                      .my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
+
 
 with gr.Blocks(css=css) as demo:
     gr.HTML(
         """
-        <h1 style='text-align: center'>
-        Hand Gesture Detection with MediaPipe
-        </h1>
-        """
+    <h1 style='text-align: center'>
+    YOLOv10 Webcam Stream (Powered by WebRTC ⚡️)
+    </h1>
+    """
     )
     gr.HTML(
         """
         <h3 style='text-align: center'>
-        <a href='https://mediapipe.dev/'>MediaPipe Hands</a>
+        <a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
         </h3>
         """
     )
     with gr.Column(elem_classes=["my-column"]):
         with gr.Group(elem_classes=["my-group"]):
-            image = gr.Image(label="Upload Image")  # 使用图像上传代替 WebRTC 流
+            image = WebRTC(label="Stream", rtc_configuration=rtc_configuration)
             conf_threshold = gr.Slider(
                 label="Confidence Threshold",
                 minimum=0.0,
                 maximum=1.0,
                 step=0.05,
-                value=0.5,
+                value=0.30,
             )
 
-        # 使用队列（queue=True）和时间限制来优化处理
-        image.stream(fn=detection, inputs=[image, conf_threshold], outputs=[image], time_limit=10)
+        image.stream(
+            fn=detection, inputs=[image, conf_threshold], outputs=[image], time_limit=10
+        )
 
 if __name__ == "__main__":
     demo.launch()