{"id":32693023,"url":"https://github.com/brumaombra/microw8","last_synced_at":"2026-04-16T10:02:38.374Z","repository":{"id":318133463,"uuid":"1069766334","full_name":"brumaombra/microw8","owner":"brumaombra","description":"🍜 MicroW8 - Smart microwave queue monitoring with AI! 🤖 Uses YOLO11n \u0026 ESP32-CAM modules for real-time person detection 📊. Privacy-first dashboard 🛡️ runs on Raspberry Pi. Perfect for universities \u0026 busy facilities! 🚀","archived":false,"fork":false,"pushed_at":"2025-10-05T09:16:17.000Z","size":968,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-05T11:31:32.579Z","etag":null,"topics":["apexcharts","esp32-cam","nodejs","nuxt3","python3","raspberry-pi","tailwind-css","yolo11"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/brumaombra.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-10-04T15:26:35.000Z","updated_at":"2025-10-05T09:16:21.000Z","dependencies_parsed_at":"2025-10-05T11:31:50.277Z","dependency_job_id":"ffeb960f-4f79-4b2c-8739-a823e795c077","html_url":"https://github.com/brumaombra/microw8","commit_stats":null,"previous_names":["brumaombra/microw8"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/brumaombra/microw8","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brumaombra%2Fmicrow8","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brumaombra%2Fmicrow8/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brumaombra%2Fmicrow8/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brumaombra%2Fmicrow8/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/brumaombra","download_url":"https://codeload.github.com/brumaombra/microw8/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/brumaombra%2Fmicrow8/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31880884,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-16T09:23:21.276Z","status":"ssl_error","status_checked_at":"2026-04-16T09:23:15.028Z","response_time":69,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["apexcharts","esp32-cam","nodejs","nuxt3","python3","raspberry-pi","tailwind-css","yolo11"],"created_at":"2025-11-01T16:02:42.092Z","updated_at":"2026-04-16T10:02:38.368Z","avatar_url":"https://github.com/brumaombra.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🍜 MicroW8 - Smart Microwave Queue Analytics\n\n\u003cdiv align=\"center\"\u003e\n\n![Nuxt 3](https://img.shields.io/badge/Nuxt-3.17.6-00DC82?style=flat-square\u0026logo=nuxt.js)\n![Python](https://img.shields.io/badge/Python-3.12+-3776AB?style=flat-square\u0026logo=python)\n![YOLO](https://img.shields.io/badge/YOLO-11n-FF6B35?style=flat-square\u0026logo=yolo)\n![MySQL](https://img.shields.io/badge/MySQL-8.0+-4479A1?style=flat-square\u0026logo=mysql)\n![License](https://img.shields.io/badge/License-MIT-green?style=flat-square)\n\n\u003c/div\u003e\n\n---\n\n## 🎯 What is MicroW8?\n\nMicroW8 is an intelligent **microwave queue monitoring system** designed for university campuses and busy facilities. Using cutting-edge **computer vision** and **real-time analytics**, it automatically counts people waiting at microwave stations and provides comprehensive insights through a beautiful web dashboard.\n\n### 🌟 Key Highlights\n\n- 🤖 **AI-Powered Detection**: Uses YOLO11n for accurate person detection\n- 📊 **Real-Time Analytics**: Live queue monitoring with historical trends\n- 🎨 **Modern Dashboard**: Sleek Nuxt 3 interface with interactive charts\n- 📱 **Responsive Design**: Works perfectly on desktop and mobile\n- 🔄 **Automated Polling**: Continuous monitoring with configurable intervals\n- 📈 **Rich Analytics**: Daily usage patterns, queue statistics, and performance metrics\n- 🛡️ **Privacy-First**: Runs entirely on Raspberry Pi for complete data control and privacy\n\n---\n\n## 📸 Screenshots\n\n\u003cdiv align=\"center\"\u003e\n\n### 📱 Dashboard Screenshot\n![Dashboard Screenshot](docs/images/page-screenshot.png)\n\n### 🤖 AI Queue Detection Examples\n\n\u003ctable\u003e\n\t\u003ctr\u003e\n\t\t\u003ctd align=\"center\"\u003e\n\t\t\t\u003cimg src=\"docs/images/detected-microwave-queue-1.jpeg\" alt=\"AI Detection Example 1\" width=\"200\"/\u003e\n\t\t\t\u003cbr\u003e\u003cem\u003eExample 1\u003c/em\u003e\n\t\t\u003c/td\u003e\n\t\t\u003ctd align=\"center\"\u003e\n\t\t\t\u003cimg src=\"docs/images/detected-microwave-queue-2.jpeg\" alt=\"AI Detection Example 2\" width=\"200\"/\u003e\n\t\t\t\u003cbr\u003e\u003cem\u003eExample 2\u003c/em\u003e\n\t\t\u003c/td\u003e\n\t\u003c/tr\u003e\n\t\u003ctr\u003e\n\t\t\u003ctd align=\"center\"\u003e\n\t\t\t\u003cimg src=\"docs/images/detected-microwave-queue-3.jpeg\" alt=\"AI Detection Example 3\" width=\"200\"/\u003e\n\t\t\t\u003cbr\u003e\u003cem\u003eExample 3\u003c/em\u003e\n\t\t\u003c/td\u003e\n\t\t\u003ctd align=\"center\"\u003e\n\t\t\t\u003cimg src=\"docs/images/detected-microwave-queue-4.jpeg\" alt=\"AI Detection Example 4\" width=\"200\"/\u003e\n\t\t\t\u003cbr\u003e\u003cem\u003eExample 4\u003c/em\u003e\n\t\t\u003c/td\u003e\n\t\u003c/tr\u003e\n\u003c/table\u003e\n\n\u003c/div\u003e\n\n---\n\n## 🏗️ Architecture\n\nMicroW8 consists of four main components:\n\n### 📹 Cameras (ESP32-CAM)\n- IoT camera modules for on-demand image capture\n- Triggered via HTTP requests to capture JPEG images\n\n### 🐍 Inference Server (FastAPI)\n- Python-based AI service using YOLO11n for person detection\n- Processes images and returns queue count data\n\n### 🗄️ Database (MySQL)\n- Relational database for storing queue analytics and historical data\n- Uses Knex.js for SQL query building\n\n### 🎨 Dashboard (Nuxt 3)\n- Full-stack Vue.js web application\n- Real-time analytics and visualization interface\n\n### 🔄 Data Flow\n\n1. **📹 Camera Capture**: ESP32-CAM modules capture images on-demand via HTTP requests\n2. **🔍 Image Processing**: Nuxt server processes JPEG images from camera responses\n3. **🤖 AI Detection**: Images sent to Python inference server for person counting\n4. **💾 Data Storage**: Queue counts stored in MySQL with timestamps\n5. **📊 Visualization**: Real-time dashboard displays analytics and trends\n\n---\n\n## 🛠️ Tech Stack\n\n### 🎨 Frontend (Dashboard)\n- **Nuxt 3** - Full-stack Vue.js framework\n- **Vue 3** - Progressive JavaScript framework\n- **Tailwind CSS** - Utility-first CSS framework\n- **ApexCharts** - Interactive charting library\n- **FontAwesome** - Icon library\n- **Jimp** - Image processing library\n\n### 🐍 Backend (Inference)\n- **FastAPI** - Modern Python web framework\n- **Ultralytics YOLO** - State-of-the-art object detection\n- **OpenCV** - Computer vision library\n- **Uvicorn** - ASGI web server\n\n### 🗄️ Database\n- **MySQL** - Relational database\n- **Knex.js** - SQL query builder\n\n### 🔧 Infrastructure\n- **PM2** - Process manager for Node.js/Python apps\n- **ESP32-CAM** - IoT camera modules for on-demand image capture\n\n---\n\n## 📋 Features\n\n### 🎯 Core Functionality\n- ✅ **Real-time Queue Monitoring** - Live person counting at microwave stations\n- ✅ **Automated Data Collection** - Periodic image capture from camera modules\n- ✅ **Historical Analytics** - 30+ days of queue data analysis\n- ✅ **Multi-Microwave Support** - Monitor multiple microwave locations\n- ✅ **Configurable Detection** - Adjustable confidence thresholds\n\n### 📊 Analytics \u0026 Insights\n- 📈 **Queue History Charts** - Time-series visualization of queue trends\n- 📊 **Daily Usage Patterns** - Hourly averages from 6AM to 9PM\n- 📋 **Queue Statistics** - Average, maximum, and total queue metrics\n- ⏱️ **Wait Time Estimation** - Calculated wait times based on queue length\n- 🎨 **Color-coded Status** - Visual indicators for queue severity\n\n### 🎨 User Experience\n- 🌙 **Responsive Design** - Optimized for all screen sizes\n- 🎭 **Smooth Animations** - AOS (Animate On Scroll) integration\n- 🎨 **Modern UI** - Clean, professional interface\n- 📱 **Mobile Friendly** - Touch-optimized controls\n- 🔄 **Real-time Updates** - Live data refresh\n\n---\n\n## 🚀 Quick Start\n\n### 📋 Prerequisites\n\n- �️ **Local MySQL**\n- 🐍 **Python 3.12+**\n- 🟢 **Node.js 18+**\n- 📹 **ESP32-CAM modules**\n\n### 🥧 Raspberry Pi Deployment\n\nFor enhanced **privacy and data control**, the entire system can run on a **Raspberry Pi**:\n\n- 🔒 **Complete Data Sovereignty**: All processing happens locally on your device\n- ☁️ **No Cloud Dependencies**: No external services or data transmission\n- 💰 **Cost Effective**: Low-power, always-on monitoring solution\n- ⚡ **Easy Setup**: Simple deployment on Raspberry Pi 4/5\n\n**Recommended Setup**: Raspberry Pi 4 with 4GB RAM + ESP32-CAM modules\n\n### 🔧 Configuration\n\n#### Frontend (.env)\n```env\n# Application Environment\nNUXT_ENVIRONMENT=development  # Environment mode (development/production)\n\n# Inference Server Configuration\nINFERENCE_SERVER_URL=http://localhost:3002  # URL where the Python inference server is running\n\n# Camera Polling\nPOLLING_INTERVAL=60  # How often to poll cameras for new images (in seconds)\n\n# Camera Configuration (JSON array of camera objects)\nCAMERAS=[{\"microwaveId\":\"550e8400-e29b-41d4-a716-446655440001\",\"url\":\"http://192.168.21.112\"}]\n\n# MySQL Database Configuration\nMYSQL_IP=127.0.0.1      # MySQL server IP address\nMYSQL_PORT=3306         # MySQL server port\nMYSQL_USER=root         # MySQL username\nMYSQL_PASSWORD=password # MySQL password\nMYSQL_DATABASE=microw8  # MySQL database name\n```\n\n#### Inference Server\nThe Python inference server uses hardcoded configuration values and does not require environment variables. It automatically loads the YOLO model from `models/yolo11n.pt` and uses a default confidence threshold of 0.25.\n\n#### ESP32-CAM Configuration\nThe ESP32-CAM modules use a configuration file stored in the SPIFFS filesystem. Edit the `esp-cam/data/config.txt` file with your WiFi credentials and settings:\n\n```plaintext\nSSID=Your_WiFi_Network_Name\nPASSWORD=Your_WiFi_Password\nSERIAL=true\n```\n\n- **SSID**: Your WiFi network name\n- **PASSWORD**: Your WiFi network password\n- **SERIAL**: Enable/disable serial debugging (true/false)\n\nNote that you need to manually create and upload the SPIFFS filesystem image before uploading the firmware.\n\n## 🎯 Usage\n\n### 👀 Monitoring Dashboard\n\n1. **Current Status** - View live queue counts for all microwaves\n2. **Analytics Overview** - Check today's statistics and trends\n3. **Daily Patterns** - Analyze usage patterns throughout the day\n4. **Historical Data** - Review past performance and queue trends\n\n### 🤖 AI Detection\n\nThe system automatically:\n- 📹 Triggers image capture from ESP32-CAM modules via HTTP requests\n- 🔍 Detects people using YOLO object detection\n- 📊 Counts queue lengths in real-time\n- 💾 Stores data for analytics and reporting\n\n### 📊 Analytics Insights\n\n- **Queue Statistics**: Average, maximum, and total daily queues\n- **Wait Time Estimation**: Calculated based on queue length\n- **Usage Patterns**: Hourly averages showing peak times\n- **Trend Analysis**: Historical queue data visualization\n\n---\n\n## 📄 License\n\nThis project is licensed under the **MIT License** - see the [LICENSE](LICENSE) file for details.\n\n---\n\n## 🙏 Acknowledgments\n\n- 🎯 **Ultralytics** for the amazing YOLO implementation\n- 🎨 **Nuxt Team** for the fantastic framework\n- 📊 **ApexCharts** for beautiful data visualization\n- 🤖 **FastAPI** for the lightning-fast Python API","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrumaombra%2Fmicrow8","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbrumaombra%2Fmicrow8","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbrumaombra%2Fmicrow8/lists"}