360 VisionVox

Control YouTube 360 videos with head movements and voice commands.

Click here to watch the demo

Table of Contents

• About
• Features
• Technologies Used
• Installation
• Usage
• Contributing
• License

About

360 VisionVox enhances the experience of watching YouTube 360-degree videos by enabling control through AI-powered voice commands and head movements. It utilizes TensorFlow.js for pose estimation and speech recognition, providing seamless interaction with the video player.

Features

• Voice Commands: Control video playback with voice commands such as Play, Pause, Stop, Next, and Back.
• Head Movement Controls: Navigate 360-degree videos by moving your head in different directions (Up, Down, Left, Right).

Technologies Used

• TensorFlow.js: Utilized for both pose estimation (head movement tracking) and speech recognition (audio classifier model).
• GitHub Actions: Used for automated workflows, including deployment tasks.
• HTML5/CSS3/JavaScript: Front-end development technologies for building the user interface and interaction logic.

Installation

1. Clone the repository:

   git clone https://github.com/lucianoayres/360-visionvox.git
   

2. Run the application:

   Open index.html in a web browser or set up a local server.

Usage

1. Open index.html in a web browser.
2. Ensure your browser has access to the microphone and camera.
3. Say (Play, Pause, Stop, Next, Back) to control video playback.
4. Enable head movements to navigate 360-degree videos:
   • Look Up/Down to adjust vertical viewing angle.
   • Look Left/Right to pan horizontally.
5. Enjoy an immersive experience with navigating the 360-degree videos in the playlist.

Contributing

Contributions are welcome! Here's how you can contribute:

1. Fork the repository.
2. Create a new branch (git checkout -b feature/improvement).
3. Make your changes.
4. Commit your changes (git commit -am 'Add feature/improvement').
5. Push to the branch (git push origin feature/improvement).
6. Create a new Pull Request.

License

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