Inspiration
We were inspired by the problem of “wishful recycling” which is when people put something in the recycling bin hoping it belongs there. We wanted to make sorting trash and recycling easier and help people make more informed decisions about where items go.
What it does
EcoChamber uses image recognition to classify an item and helps direct it to the appropriate bin. It can use the Gemini API for image recognition and an Arduino Uno to control the physical sorting mechanism.
How we built it
We connected the software’s classification flow to the hardware using an Arduino Uno and C++ firmware. The Gemini API analyzes images, and the Arduino receives commands to move the mechanism to the selected bin position.
Challenges we ran into
A major challenge was getting image recognition to classify items in a way that was useful and consistent for sorting. We also had to determine what the system should do for each classification and make sure the software and hardware communicated reliably.
Accomplishments that we're proud of
We’re proud to have brought image recognition and a physical sorting mechanism together in one project. EcoChamber turns an everyday recycling challenge into an interactive experience.
What we learned
We learned how to integrate hardware and software, connect an AI-powered image recognition service to an Arduino, and think through how classification results should translate into physical behavior.
What's next for EcoChamber
Next, we want to finish calibrating and testing the physical bin positions, improve classification reliability, and keep refining the sorting experience.
Log in or sign up for Devpost to join the conversation.