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

docker/docker-compose.yml

@@ -0,0 +1,26 @@
+version: '3.8'
+
+services:
+  backend:
+    build:
+      context: ../apps/server
+      dockerfile: ../../docker/Dockerfile.server
+    ports:
+      - "8000:8000"
+    volumes:
+      - ../models:/app/models:ro
+      - ../apps/server/static:/app/static
+    environment:
+      - MODEL_PATH=/app/models
+      - STATIC_PATH=/app/static
+    restart: unless-stopped
+
+  frontend:
+    build:
+      context: ../apps/web
+      dockerfile: ../../docker/Dockerfile.web
+    ports:
+      - "80:80"
+    depends_on:
+      - backend
+    restart: unless-stopped