Unique Visitors, Not Footfall: Measuring the Real Store Journey

Many stores still measure their floor with one number: how many times the door opened. A door counter. A beam across the entrance. Every time something interrupts the beam, the number goes up.

The trouble is, that number can't tell people apart.

The same shopper who walks in, walks out to grab a coffee, walks back in, walks to the changing room, and walks back to the floor can count as five "visits." A family arriving side by side can count as one. The delivery driver who steps in to drop a parcel counts the same as the customer who spent forty minutes deciding on a jacket. The beam doesn't know who is who. It was never designed to.

A door count alone can't answer the question that matters: how many different people came in, and what did they do?

The Digital Mirror Image

Websites have long measured unique visitors, sessions and journeys, not just page hits: time per session, page-by-page paths, conversion funnels, drop-off points and returning visitors. Few website teams would settle for a hit counter.

In the US, e-commerce is still under a fifth of retail sales (U.S. Census Bureau, Q2 2026), so most retail still happens in physical stores. Many of those stores still measure their floor with a door count.

Pulses.ai exists to close that gap.

Why the Difference Is Edge AI

Here is how Pulses works differently from a door counter, and how it sits next to what a store may already have:

1. The beam. A beam counter registers each break of the beam. It cannot tell one person from another, so re-entries are counted again. It says nothing about what people did once inside.
2. Cloud analysis. Some systems send video to the cloud to be analysed. Pulses does that work on the device, so video stays on site.
3. Existing CCTV. Pulses works alongside existing CCTV; it doesn't replace it.

Pulses works differently.

Pulses Vision is purpose-built to understand what it sees on the device itself. Each person is one unique visitor, however often they step in and out, from the entrance to the womenswear floor, the fitting room and the till: a real shopper-by-shopper journey. This uses an Anonymous Unique FaceID, derived on the device; it can't be turned back into a picture and holds no personal data. What leaves the device is anonymous data, not video.

The result: unique visitors, not footfall.

What Retailers Actually Get

With Pulses CX deployed across a store, the store can see its floor the way it sees its website: unique visitors and their journeys as they move through the store. Time-on-store and time-per-zone — the physical equivalent of session duration and page time. The conversion funnel: entered the store, reached the floor, engaged with a product, entered the fitting room, arrived at the till, and, where the till system is connected, purchased. Drop-offs show up. Chokepoints get named.

Dwell time shows where people pause, hesitate or walk past. It can also show returning visitors.

Privacy Is Not a Trade-Off

Here, none of this needs video to leave the store.

Pulses processes what it sees on the device. What leaves is anonymous data, not video, and the device has no inbound ports. The store gets journey data without video leaving the site.

"Insights, not images." Measure the floor with the same care as the website.

Ready to begin?

Want to see your store the way the internet sees a website? Book a demo.

Source: U.S. Census Bureau, Quarterly Retail E-Commerce Sales, Q2 2026 release.