We saw a huge opportunity for machine leearning to be applied to AB Inbev's Off-Premise Operations

What it does

Utilizing SIFT and Hough algorithms, we solved availability and planogram compliance

How we built it

Webcam on top of Intel Edison to take a picture, send it to be processed, and then notify the necessary parties

Challenges we ran into

Manipulating the algorithms for our specific use, and finding clean data images were necessary hurdles

Accomplishments that we're proud of

Identifying bottles (and lack thereof)

What we learned

We are able to solve the visible problem at a fraction of the cost, and exponentially faster

What's next for Bud Wiser

Adding in more features, and increasing the functionality and accuracy of things we have already demonstrated

Built With

Share this project: