Somnolence

Inspiration

Every year, many people get into potentially fatal car accidents due to drowsy driving. We want to reduce this number to as little as possible.

What it does

Our app is a drowsiness detection model that will detect if the driver is sleepy. A user can log in to the page so that they can see all the previous times that they were drowsy

How we built it

We built it using an AI model that would connect to our Flutter application. The video from the live Flutter app would feed into the AI model which would then give results.

Challenges we ran into

We ran into many challenges, the biggest one being that none of our devices could handle the training of the AI data and so, it took a big portion of our time. Additionally, our sound was not working in flutter, which meant that we lost a big portion of our project.

Accomplishments that we're proud of

We are proud of the login system that we were able to create for our app. Additionally, we are proud of being able to accomplish so much with a framework that we had prior experience with.

What we learned

We learn how to use Flutter and Dart

What's next for Somnolence

We would use our ML model to communicate the fact that you are drowsy with the car and try and get the car to slow down gradually and turn on the caution lights of the car, while of course playing an obnoxious alarm to try and get the driver to wake up. If the driver is sleepy for too long then we will also contact someone from their contacts.

Built With

• c++
• cnn
• dart
• dnn
• firebase
• flutter
• kaggle
• python