
Object Detection for Inventory Stocking
Software as a Service
NoCategory
AI & Machine LearningClients
Techstack
Purpose
Counting stock by hand is tedious and easy to get wrong, and the numbers drift out of date the moment someone forgets to log a change. A capstone team set out to prove that a camera and an AI model could keep an accurate count of phones in a storage cabinet on their own — no manual tallies.
Description
We trained a vision model to recognize and count each phone model in the cabinet from a live camera feed, then served the annotated video and running totals to any browser on the network. Every count is written to a records file so inventory stays current without anyone lifting a clipboard, and the whole pipeline runs on a small onboard computer right at the shelf. It is a practical piece of applied computer vision — the sort of real-world detection problem we take on and ship.




