---
title: "Computer vision in retail, without the creep."
date: 2023-04-18
url: https://remiam.co.uk/notes/cv-in-retail-without-creep
tags: [Computer Vision, Edge, Retail]
read_time_minutes: 7
description: "Building anonymised, on-prem footfall computer-vision pipelines for retail — how to keep the data inside the building and the conversation inside the room."
---

# Computer vision in retail, without the creep.

*Published 2023-04-18 · 7 min read · by Liam (Remiam)*

On-premise anonymised footfall pipelines, why the data should never leave the building, and how to talk to a client about it without scaring them off.

Retail wants the data. Customers don't want to be the data. Privacy regulators don't want a tape full of faces leaving the building. There's a path through this that makes everyone — including the analytics team — happy: anonymise on the edge, never upload pixels.

## The shape of the pipeline

- Camera feed into an on-prem device. Often a Mac mini, sometimes a Jetson, increasingly an N100.
- Detection model runs locally. Faces are detected, counted, classified into broad demographic buckets if asked — never identified.
- Pixels never leave the device. Only counts, dwell times, and aggregated metrics get pushed to the cloud.

## A typical deployment

| Component | Role | What it does NOT do |
| --- | --- | --- |
| Camera (IP or USB) | Capture raw frames | Never store or transmit raw video |
| On-prem inference box | Run detection / counting model | Never upload pixels, never identify individuals |
| Local queue / DB | Buffer aggregated metrics | Never hold image data longer than the inference window |
| Outbound webhook | Push aggregated counts to cloud | Only carries numbers — counts, dwell times, hourly bins |

*Edge-first computer-vision pipeline for retail footfall.*

## What clients actually ask for

- Footfall by hour, by entrance, by zone.
- Dwell time on a specific display or product.
- Coarse demographic mix for staffing decisions, not targeting.

> Anonymise on the edge, never upload pixels. Every CV-in-retail project starts with that constraint, or it ends up in the news for the wrong reason.

## The conversation

The technology is mostly the easy part. The conversation about what gets stored, where, and for how long — that's where the work actually is. Do it before the cameras are ordered, not after.

Our standard kit list now starts with the privacy architecture before we spec a single piece of hardware. The deployment runs ten times more smoothly when the legal team has seen the data flow on day one rather than week ten.

## References

1. [ICO — guidance on use of facial recognition in retail](https://ico.org.uk/for-organisations/uk-gdpr-guidance-and-resources/)
2. [NVIDIA Jetson — on-prem AI hardware platform](https://www.nvidia.com/en-gb/autonomous-machines/embedded-systems/)