Solution showcase · Computer Vision

Every shelf, every aisle, checked every hour

Store cameras that spot empty shelves and planogram gaps, and tell staff exactly what to restock.

Type
Solution showcase
Industry
Retail
Deployment
Edge in store, dashboard in the cloud
Services
Computer Vision, Cloud & Data

The challenge

In a busy store, an empty shelf loses a sale every time a shopper walks past it. Manual shelf audits happen a few times a day at best, and by the time a gap is noticed, the moment has gone.

The solution

Shelf Intelligence uses the ceiling cameras a store already has to scan shelves on a schedule. A detection model finds products, price labels and empty facings, compares them with the planogram, and sends a prioritised restock list to staff devices. Head office sees availability by store, aisle and brand on one live dashboard.

What it includes

  • Product and gap detection on existing CCTV
  • Planogram compliance scoring by bay
  • Restock tasks pushed to staff devices
  • Availability dashboard by store, aisle and brand
  • Processing in store, with no shopper identification

How it works

  1. 01

    Capture

    Existing cameras capture shelf images every hour, processed on a small edge device in the store.

  2. 02

    Detect

    A model trained on your range finds products, price labels and empty facings.

  3. 03

    Compare

    Detections are matched against the planogram to flag gaps and misplaced products.

  4. 04

    Act

    Staff receive a prioritised restock list, and managers see trends on a live dashboard.

Design targets

HourlyShelf checks, instead of a few manual audits a day
95%+Detection accuracy target, agreed on your footage before rollout
MinutesFrom an empty facing to a restock task

This is a solution showcase: a system Quibo designs and builds for this kind of problem. Figures are the design targets we build and test against, not results from a named client. Targets for your business are agreed and measured during the proof stage.

Ready to build?

Want a system like this?

Tell us about the process or the cameras you have. We will tell you honestly what is achievable, and propose a short proof stage on your own data.

Start a conversation