Do we need new cameras?

Usually not. We audit the estate first; the common blockers are camera angle, lighting and network bandwidth rather than resolution.

Does footage leave the store?

No. Inference runs on an edge device in the store and only counts, timings and zone events are sent onward.

Retail, FMCG & E-Commerce · In-store video analytics

See the store the way you see the website

Understand footfall, queues and dwell from the cameras you already own.

Book the Data Foundation Assessment

Footfall and capture rateVisitor-to-transaction conversionAverage queue wait and abandonmentDwell time by zone

The problem

What this fixes

Online you know every impression, click and drop-off. In store you know the receipt and nothing before it, so merchandising decisions rest on opinion.

Computer vision on existing CCTV that counts visitors, measures queue length and wait time, maps dwell by zone and correlates all of it with sales. Processing runs at the edge and outputs counts and heat maps, not identities, the store learns how it performs without building a face database.

Retail, FMCG & E-Commerce

Footfall and conversion by zone

Entries, dwell and purchase joined so you know which areas earn their space.

Retail, FMCG & E-Commerce

Queue and service levels

Waiting time measured continuously and staffed against, not guessed.

Retail, FMCG & E-Commerce

Display and campaign impact

Before-and-after evidence for the endcap you paid for.

Retail, FMCG & E-Commerce

Privacy-safe by design

Counts and anonymous events only; no identification, no face database.

In this sector

Where it earns its place

Delivery

How we build it

Foundation check

Before any build

We inspect the systems, the data behind them and the quality of the records this capability will depend on, then write down what has to be fixed before anything is built.

Narrow first release

First release

One workflow, one team, real traffic, measured against the baseline we captured before we started.

Controls and evaluation

Runs in parallel

Guardrails, approval gates, evaluation sets, logging and the evidence pack your auditor and your regulator will ask for.

Scale and hand over

After sign-off

Additional workflows, sites or languages, then runbooks and training so your team can operate it without us.

Data foundation

What has to be right first

A camera inventory with usable angles over entrances, tills and key aisles.
Store layout and zone definitions that match the planogram.
POS transaction data at the same time granularity, or conversion cannot be computed.
A posted privacy notice and a retention rule for footage.

Controls

Guardrails and KPIs

Every action is logged and replayable

Inputs, retrieved context, model version, output and the human decision are written to an immutable log, so an auditor can reconstruct any single interaction months later.

Data stays where your regulator requires

In-country, in-region or on-premise deployment, with the model portfolio right-sized to the workload instead of routing everything to a frontier endpoint abroad.

Accuracy is monitored, not assumed

A held-out evaluation set runs on every model or prompt change, with drift alerts and a documented rollback path when quality moves.

Counting, not recognising

No face matching, no cross-visit tracking of an individual and no demographic inference unless you have an explicit lawful basis and ask us for it in writing.