Inspiration
Ramona is visually impaired and she founded Eyes for Success to conduct workshops for other visually impaired people to help them better handle day to day activities. She approached us to work on a solution to allow visually impaired parents bring their kids out for a walk.
What it does
A machine learning model is implemented into an Android App that detects hazard such as road side curb (drop offs) as well as braille bumps on the road. This information will then be combined with inputs from other sensor and relayed onto a raspberry pi. A decision will be made and this information will then be relayed to the visually impaired parents in the form of vibrations. We have created a haptic language to facilitate that.
How I built it
Using Microsoft Cognitive Services Custom Vision, I have created a machine learning model that differentiates pavements from braille bumps and curbs. An Android App (Java) is then built as a platform to implement the machine learning model.
Challenges I ran into
No prior experience with Java and android studios before this hackathon.
Accomplishments that I'm proud of
Creating a working prototype within a day!
What I learned
Basic Machine learning, Android Studio, Java
What's next for Baby Buggy
To integrate this with other sensors and the feedback system.
Built With
- android-studio
- azure
- custom-vision
- java
Log in or sign up for Devpost to join the conversation.