Inspiration
Our goal for social good is to limit the amount of landfills and litter in streets. We believe an application is needed to help people identify the correct bin and convince them to hold on to their trash instead of littering. They need to be aware of the available bins near them to do so. These two goals guided us to create GreenTrail.
What it does
Our apple application allows users to locate the nearest bin for their needs through a GPS system. These include compost, recycle, and trash bins.
How we built it
We built the iOS application with Swift, and we imported a python model with CoreML to make predictions.
Challenges we ran into
The most challenging part of the process was integrating the python model into Swift for prediction. We tried using TensorflowLite as an interpreter for our model, but we could not figure it out.
Accomplishments that we're proud of
We are proud to have taken on a difficult project, and we were able to learn new frameworks and new ways to tackle problems under time pressure.
What we learned
Working with Swift was a new experience. We learned how Swift handles the camera taking photos and how map features are implemented.
What's next for GreenTrail
GreenTrail can be improved in several ways. First, more data will greatly increase the capabilities of our application. Data would help our machine learning model generalize better to new cases and can even increase the number of objects it is able to detect. Having more data also gives users a comprehensive list of bins they can choose from. Second, a feature can be added to allow users to input bins and facilities into the application. These entries can be shared with others to benefit everyone looking for nearby bins.
Log in or sign up for Devpost to join the conversation.