Retail · Supermarket · Illustrative scene
Queues and aisles measured, nobody profiled.
Neuvis measures checkout queues and aisle dwell time from the store’s existing cameras. It does not recognise faces, estimate age or sex, or build shopper profiles.
The twin marks 9 people and draws the checkout queue zone, an aisle dwell zone and an aisle. The queue has 4 people and is flagged for review. An out-of-stock marker is labelled roadmap: shelf detection is not built yet.
People 9 · In queue 4
No faces stored
Drag or use ← → to compare
Synthetic renders · no real people
Use cases
What Neuvis looks for in a store.
Checkout queue length and wait
People counted in each checkout lane’s queue zone, and how long the queue has been that long.
Aisle dwell time
How long people stay in each aisle section, as counts over time. No paths are kept per shopper.
Staff response to queues
Time from a queue building up to a second checkout opening, measured per lane.
Empty shelf detection
Gaps on the shelf flagged for restocking. Not built yet.
Specification
What Neuvis measures in a store.
| Queues | Per checkout lane: people waiting and time waiting |
|---|---|
| Dwell | Per aisle section, as counts over time |
| Personal attributes | None. No age, sex or other estimates |
| Identity | Not recorded. No face recognition |
| Where it runs | Built for an edge box on the store network |
Privacy by design
We measure work, not people.
- 01
No faces
Neuvis does not recognise faces. Faces are never stored or matched, and it does not estimate age or sex.
- 02
Stations, not individuals
Crew time comes from station polygons. Counting people in a station does not need to know who they are.
- 03
A person decides
Every alert waits for a supervisor to review it. Nothing reaches payroll or HR automatically.
Show us your hardest camera.
Tell us about the site and the camera that gives you the most trouble. We reply within one business day.