Custom retail item detection in store

Shelf-level detection that keeps stock counts current and flags missing or misplaced items for inspection.

Focus

Inventory and theft monitoring

Model

YOLOv5, custom-trained

Edge

TensorRT on NVIDIA Jetson Nano

Input

Live video stream

A toy retailer

01 · Context

The situation

The store needed to protect stock from theft and keep inventory accurate without constant manual counts.

02 · Challenge

What had to be true

Recognise every toy on the shelf in real time and compare what the camera sees with the checkout system.

03 · What we built

The system

  • A dataset of every retail item in different backgrounds and orientations, randomly resized and skewed
  • labelImg annotations, an 80/20 split and a custom YAML file with all toy labels
  • YOLOv5 trained to detect toys on the shelf
  • Optimised from PyTorch to a TensorRT engine for the Jetson Nano GPU, running on the live stream
  • Stock levels per location compared with the checkout inventory, with mismatches flagged for manual inspection
04 Architecture

How it works, step by step.

Step through the system, or let it play.

  1. Shelf camera streams video
  2. YOLOv5 detects each item
  3. Stock levels updated
  4. Compared with checkout system
  5. Mismatches flagged
INPUTShelf cameraDETECTYOLOv5Jetson NanoCOUNTStock per slotCOMPARECheckout systemFLAGMismatchmanual check
05 · Outcome

Stock levels stay current from the camera, and possible theft or misplaced items are flagged quickly.

06 · Stack
YOLOv5PyTorchTensorRTNVIDIA Jetson NanolabelImg
Next case · Precious metals · Computer visionAutomated gold weight and purity detection
● Next step

Building something similar? Let's talk.

Book a 30-minute call →