mmScribe 🎯

mmScribe: Streaming End-to-End Aerial Handwriting Text Translation via mmWave Radar

🌟 Overview

mmScribe is an innovative Aerial Handwriting system that enables contactless human-computer interaction through millimeter-wave radar technology. The system accurately captures user gestures and converts them into text input, providing a novel approach to human-computer interaction.

✨ Key Features

• 🎯 Streaming Aerial Handwriting Recognition
• 📱 Cross-platform compatibility (Android, Windows, Raspberry Pi)
• ⚡ Real-time response with low latency
• 🔒 Privacy-preserving interaction
• 🛠️ Easy integration with existing systems
• 📊 Comprehensive data analysis tools

🎬 Demos

Android Demo	Laptop Demo	Raspberry Pi Demo
demo_Android.mp4	demo_laptop.mp4	demo_RPI4B.mp4
🌟🌟🌟New! Window GUI Demo🌟🌟🌟 cc_raw.mp4

📱 Runtime Support

mmScribe supports multiple platforms through our runtime system:

Android ✅ Released

Windows ✅|🚧 Source Code and Libs

Raspberry Pi ✅|🚧 Source Code and Libs

Hardware Requirements

• ESP32-BGT60TR13 Radar Module
  • 58-63GHz mmWave Radar
  • USB/UART Interface
  • 5V Power Supply

Quick Installation

# Android APK
wget https://github.com/Tkwer/mmScribe/releases/latest/download/mmScribe.apk

For detailed installation instructions and platform-specific guides, see our Runtime Documentation.

📊 Dataset

We provide a comprehensive dataset for aerial handwriting recognition using millimeter-wave radar. The dataset includes:

• 🧑‍🤝‍🧑 12 participants (6 males, 6 females)
• 📝 15,488 total samples
• 📊 Rich feature set including micro-Doppler and range-time data
• 🎯 Ground truth data from Leap Motion controller

Dataset Structure

dataset/
├── datas1/    # Reserved dataset
├── datas2/    # Participant 001 (1212 samples)
├── datas3/    # Participant 002 (1202 samples)
...
└── datas14/   # Participant 013 (1192 samples)

For detailed information about the dataset, including collection methodology, data format, and usage guidelines, please visit our Dataset Documentation.

Data Collection System Setup

🚀 Quick Start

Prerequisites

• Python 3.8 or higher
• CUDA-compatible GPU (optional, for faster processing)
• Compatible radar hardware

Installation

# Clone the repository
git clone https://github.com/yourusername/mmScribe.git

# Navigate to project directory
cd mmScribe

# Install dependencies
pip install -r requirements.txt

Basic Usage

1. Select Dataset
2. Run the main program:

python main.py

3. Training ...

📚 Documentation

For detailed documentation, please visit our Wiki.

🤝 Contributing

We welcome contributions! Please see our Contributing Guidelines for details.

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

📮 Contact

• Maintainer: [Your Name]
• Email: [your.email@example.com]
• Project Link: GitHub Repository

⭐ Show Your Support

If you find this project useful, please consider giving it a star on GitHub!