Initial commit: Video detection platform with YOLO models

Features:
- Fire detection (YOLOv10)
- Helmet detection (YOLOv8)
- Crowd detection (YOLOv8)
- Smoking detection (YOLOv8)
- Loitering detection (YOLOv8)

Tech Stack:
- Frontend: Vue 3 + Vite + Element Plus
- Backend: FastAPI + WebSocket
- Monorepo: pnpm workspace + Turbo
- Docker support included

apps/web/src/api/detection.js

@@ -0,0 +1,20 @@
+import axios from 'axios'
+
+const api = axios.create({
+  baseURL: '/api',
+  timeout: 30000
+})
+
+export const detectionApi = {
+  getModels() {
+    return api.get('/models')
+  },
+  
+  detectImage(formData) {
+    return api.post('/detect/image', formData, {
+      headers: {
+        'Content-Type': 'multipart/form-data'
+      }
+    })
+  }
+}