Case study 05 · Retail

Give every shelf a voice.

Existing store cameras detect empty shelves and misplaced products, then help the team move from an alert to replenishment.

Existing camerasAutomated shelf monitoring

Computer vision · Operations

Retail shelving with one empty facing lit up, a conceptual illustration of shelf monitoring
Retail computer vision
Sector
Retail
Geography
UK · France
Hardware
Existing cameras
Scope
Alerts to inventory

01 / The challenge

Spot shelf issues sooner.

Empty shelves and misplaced products are difficult to track through manual checks alone. Retail teams needed a way to identify those issues and route them to staff using the cameras already in their stores.

02 / The approach

Connect shelf visibility to action.

Computer vision analyzed store-camera feeds to detect empty shelf spaces and misplaced items. Staff alerts connected those detections to the people responsible for replenishment.

The broader Smart Shelves system added inventory recommendations and replenishment management, connecting shelf monitoring with the next operational steps.

03 / The outcome

From a camera feed to a replenishment task.

The project covered stores in the UK and France. It connected shelf detection, staff alerts, and replenishment support using existing camera infrastructure.

What we built

The system, in parts.

  1. 01

    Shelf vision

    Analyzes existing camera feeds for empty shelves and misplaced products.

  2. 02

    Staff alerts

    Routes detected shelf issues to store staff for attention.

  3. 03

    Smart Shelves

    Connects monitoring with inventory recommendations and replenishment management.

Selected work delivered across GOT AI, Rocket Farm Studios, and Full Cortex in engineering, technical leadership, and advisory roles. TensorFlow, the TensorFlow logo and any related marks are trademarks of Google Inc. OpenCV and its logo are trademarks of their owner. Logos identify technology the project used and link to their makers; no endorsement is implied.

Start with a conversation

Have a workflow like this?
Let’s look at it together.

Bring the process that takes up your team’s time. We’ll look at what it costs today, and whether AI, conventional automation, or a simpler fix is the right next step.