fanton-dev / traffic-brain

Traffic Brain is an open-source traffic light embedded system taking use of a machine learning classification model for decision making automation.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Traffic Brain

Traffic Brain is an open-source traffic light control system. Using a classifier, information about the current road situation is collected and automated light switch decision is made based on it.

Project Banner

Classification CI Server CI status Embedded CI status Client CI status

Hit count badge Open issues status badge Closed issues status badge Contributions welcome badge License badge

Get started

Project Architecture

The project consists of 4 main components:

  • Object recognition for traffic detection (located in "/classification")
  • Main server controlling all the traffic light nodes (located in "/server")
  • Embedded server and traffic light schematics (located in "/embedded")
  • Front-end client for communicating with the server (still incomplete; located in "/client")

For each of the components' directories there is a coresponding README.md with instructions on how to get started.

Authors

  • Angel Penchev (@angel-penchev) - Object detection neural network, Embedded traffic light
  • Bogdan Mironov (@bogdanmironov) - Main controlling server
  • Simeon Georgiev (@simo1209) - Thank you for helping me out to complete the embedded <3

Contributions

  1. Fork it (https://github.com/braind3d/traffic-brain/fork)
  2. Create your feature branch (git checkout -b feature/fooBar)
  3. Commit your changes (git commit -a)
  4. Push to the branch (git push origin feature/fooBar)
  5. Create a new Pull Request
  6. Upon review it will be merged.

License

Distributed under the MIT license. See LICENSE for more information.

About

Traffic Brain is an open-source traffic light embedded system taking use of a machine learning classification model for decision making automation.

License:MIT License


Languages

Language:Jupyter Notebook 92.2%Language:Python 3.6%Language:HTML 2.8%Language:TypeScript 0.9%Language:JavaScript 0.4%Language:Dockerfile 0.1%Language:Shell 0.0%Language:CSS 0.0%