## Inspiration

We wanted to use the Google Cloud AI API, especially the Cloud Vision. We also wanted to make a program that actually matters and benefits others.

## What it does

Captures images by the camera every second and analyzes it. The program looks for any distracting objects in the object as well as checks if the driver has their eyes open and is focused on the road. If the program detects any distraction, such as the driver looking elsewhere or the driver dosing off, it plays the siren sound. If the driver continues their behavior, the sirens multiply and get louder

## How we built it

We have multiple Python modules for detecting images, database, calculations for determining how closed the eyes are as well as a custom trained machine, who can identify genders based on the face alone. We used lots of Python modules, the whole list can be found below on the "Built with" section. For the web page, we used a combination of the flask library from Python along with JavaScript and HTML to power the application.

## Challenges we ran into

  • Getting the live stream image on the web page (we never ended up doing so but it helped us figure out what we really wanted to do with the program)
  • Working with the different APIs and their credentials as well as .json files

## Accomplishments that we're proud of

  • Getting the code to recognize the person, their age and gender. In addition, the program also detects objects and facial expressions

## What we learned

We have learned Flask, a tool for web development with Python. We also learned about the Google Cloud service and learned how to use it in a real project.

## What's next for RoastMyDriving.com

  • Dash camera and phone app supports
  • Better GUI
  • Comparisons of users to others around their demographics

Built With

Share this project: