StockSeer — food waste reduction on Ring

Inspiration

What it does

How we built it

Challenges we ran into

Accomplishments that we're proud of

What we learned

What's next for StockSeer — food waste reduction on Ring

Inspiration

We noticed how much food is thrown away simply because people forget what is tucked away in their pantries. We wanted to use existing smart home technology to turn a camera into an intelligent assistant that alerts users to expiring goods.

What it does

StockSeer uses Amazon Ring devices to identify and track food stock levels in the kitchen. It processes this data to predict when items will run out or expire, sending notifications to users via the Ring app.

How we built it

We built the backend using Python and AWS Lambda to handle event-driven triggers from Amazon Ring. We utilized Amazon Forecast to predict demand and shelf-life based on historical consumption patterns, while boto3 managed all AWS service interactions.

Challenges we ran into

We struggled to accurately identify various food items from different angles using a standard Ring camera. We also had to refine the Amazon Forecast models to ensure they didn't over-predict for seasonal eating habits.

Accomplishments that we're proud of

We successfully integrated the Ring API with AWS-native forecasting to create a seamless feedback loop. Seeing the system correctly predict when we would run out of milk was a major win for our team.

What we learned

We learned a lot about the nuances of computer vision in domestic environments compared to industrial settings. We gained deep experience in how to optimize AWS Lambda functions for real-time video data processing.

What's next for StockSeer

We plan to expand our item recognition library to include more perishable produce and dry-stable goods. We also want to add a recipe suggestion engine that prioritizes ingredients getting closest to their expiration date.

Built With

• amazon-forecast
• amazon-ring
• aws-lambda
• boto3
• pantry
• stockseer