daniel-alvarenga / barium

Gesture-controlled computer interactions using hand tracking

English | Рortuguês | Español| 한국어

Barium (HMI)

An innovative software that utilizes neural networks, machine learning, and deep learning for tracking body movements, such as hands, enabling advanced interactions with the operating system, including predefined actions and a virtual mouse. Additionally, the project employs 4D neural network training techniques, where time is one of the dimensions, opening up revolutionary possibilities in various technology fields

How To Use

Prerequisites

• Python 3.11

Clone this repository

git clone https://github.com/VitorCarvalho67/Barium.git

Navigate to the project directory

cd Barium

Create a virtual environment (venv) for the project

python -m venv venv

Activate the virtual environment. On Windows:

.\venv\Scripts\activate

On macOS and Linux:

source venv/bin/activate

Install the project's dependencies from requirements.txt.

pip install -r requirements.txt

Running the Software

Make sure your webcam is connected and functional. In your virtual environment, run the main software script.

cd src
python main.py

The software should now be active, and you can interact with your computer using hand gestures.

Warning

Remember that you need a camera to use this software.

Develop

In the development process, we start with the creation of a data collection software to build our custom dataset. Next, we move on to developing a neural network, utilizing deep learning and convolutional neural networks (CNN). Finally, we create software that employs this network to recognize real-time movements and execute corresponding actions For more detailed information on developing Barium, please read the Developer Guide

Dataset

Technology

Contribute

Alvaro Richard - Daniel Alvarenga - Vitor Carvalho