Skip to content

ahere84/Vistra-Smart-Mirror

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Vistra-Smart-Mirror

Vistra_Logo Vistra Smart Mirror brings the power to the eyes of the user. With our advanced hands-free technology, anyone can interact with our smart mirror regardless of physical abilities. The smart mirror is equipped to detect subtle head and eye movements, allowing users to select and interact with applications effortlessly.

https://devpost.com/software/vistra-the-mirror-for-everyone

Features

  1. Operate the smart mirror without physical touch, using only subtle head and eye movements.
  2. Utilizes torchvision library from PyTorch to detect directional gazes such as top left (TL), top right (TR), bottom left (BL), and bottom right (BR).
  3. Designed to be used by individuals with varying levels of mobility, enhancing accessibility and ease of use
  4. control interface with gaze control

Installation

The Vistra Smart Mirror software has been developed and tested on Ubuntu 22.04. Follow the steps below to set up the software on a similar environment:

Clone the repository:

git clone https://github.com/yourgithub/Vistra-Smart-Mirror

Contributing

Data Contributions

We are actively seeking to expand the EyeMovementDataset to enhance the eye-tracking capabilities of Vistra Smart Mirror. More diverse training data can significantly improve the accuracy and responsiveness of our technology. If you are interested in contributing data or improving the dataset, please see the guidelines in CONTRIBUTING.md or contact us directly at aheredi7@montgomerycollege.edu.

Technology

The eye movement detection in Vistra Smart Mirror is powered by a machine learning model trained on a dataset of eye movements. Currently, the dataset requires further expansion to enhance detection accuracy across diverse conditions. We welcome contributions of training data, especially from environments and demographics currently underrepresented in our dataset.

About

No description, website, or topics provided.

Resources

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors