VisionCommand

A Hybrid Gesture and Voice Control System for Your OS

VisionCommand empowers you to control your operating system using real-time hand gestures and voice commands. By leveraging your webcam and microphone, it offers a unique and intuitive way to interact with your computer.

Core Features

• Real-Time Hand Tracking: Utilizes the MediaPipe Hand Landmarker to detect and track 21 key hand landmarks with high precision.
• Gesture-Based Control:
  • Cursor Movement: Point with your index finger to move the cursor across the screen.
  • Scrolling: Extend two fingers to scroll vertically (up or down).
  • Wave Gesture: Wave with an open palm to trigger a friendly "BYE!!" feedback message.
• Voice-Activated Commands:
  • "left": Simulates a left mouse click.
  • "right": Simulates a right mouse click.
  • "go" / "confirm": Simulates pressing the Enter key.
• Customizable Configuration: Easily tweak camera settings, hand tracking parameters, and gesture definitions through simple JSON files.
• Audible Feedback: Provides speech confirmation for executed commands.

Getting Started

Prerequisites

• Python 3.8 or higher
• A connected webcam

Installation

1. Clone the Repository:

   git clone https://github.com/nomadrai/VisionCommand.git
   cd VisionCommand

2. Set Up a Virtual Environment:

   • Windows:

     python -m venv venv
     .\venv\Scripts\activate

   • macOS / Linux:

     python3 -m venv venv
     source venv/bin/activate

3. Install Dependencies:

   pip install -r requirements.txt

Usage

To start the application, run the main.py script from the root of the project directory:

python src/main.py

Configuration

The config/ directory contains JSON files that allow you to customize the application's behavior:

• settings.json: Main application settings.
• gestures.json: Definitions for hand gestures.