AI-Powered People Counting
People Counter
Enterprise-grade people counter sensors with 98%+ accuracy. AI-powered and privacy-first — count every visitor entering and exiting your space with confidence. From £720 / $995 per store per year.

Trusted by leading brands
The problem
Why You Need a People Counter
Without a people counter, you have no objective measure of how many visitors enter your space. Decisions about staffing, layout, and investment rely on estimates.
Infrared beam people counters achieve only 70-80% accuracy. At high-traffic entrances, miscounts of 20%+ make conversion rate calculations meaningless.
Batch reports delivered days later cannot help you react to today's traffic. Without a real-time people counter, you are always managing on stale data.
Simple setup
How People Counting Works
Mount the Sensor
Install the Hoxton AI people counter above your entrance in 15 minutes. Connect via PoE (single cable) or power plug plus WiFi. Adhesive or screw mounting.
Count Accurately
The people counter uses AI vision to count every person entering and exiting with 98%+ accuracy, even in groups or poor lighting.
Connect Your Systems
Integrate with your POS, BMS, or analytics platform. People counter data flows into your existing dashboards automatically.
Act on the Data
View real-time people counting dashboards. Optimise staffing, measure campaign impact, and benchmark locations.
People Counter Specifications
98%+
People counting accuracy
15 min
Installation time
500+
Locations worldwide
PoE/WiFi
Flexible connectivity
Everything You Need in One Package

Overhead S1 sensor installs in 15 minutes. PoE or WiFi connectivity, 98%+ accuracy, privacy-first, engineered in the UK.

People counts, conversion rates, peak hours, and location comparisons — all updated in real time from any device.

Out-of-the-box integration with Shopify, Square, and enterprise POS. Plus a full API for custom workflows.
Why 98%+ accuracy
Counting based on journey prediction, not simple line crossings
Most people counters fire a +1 the instant something crosses a beam or line. That's fast — but it's also why they overcount. Hoxton works differently: it uses an overhead view to recognise a complete in-view journey and only counts when the journey matches a real entry or exit.
Traditional counters
A single trigger = a count, every time the line is crossed.

- ●Security guard pacing near the doorway? Counted repeatedly.
- ●Customer steps in, hesitates, turns back out? Often counted twice.
- ●Staff working near the entrance? Every pass inflates the number.
Result: counts drift upward anytime there's “doorway noise”.
Hoxton AI directional event counting
A count is only created when the system confirms a genuine entry/exit event.
- ●Understands a person's in-view journey from arrival to departure.
- ●Someone loops, pauses, or changes their mind? No false extra counts.
- ●A count only registers when they arrive on one side and leave on the other — a real entry or exit.
Result: accurate footfall that matches what actually happened, not how many times a line was crossed.
How directional event and journey prediction works

Detect
Person enters the field of view
A person is detected as they arrive in the overhead zone.

Interpret
Movement is understood in context
The system evaluates whether the movement indicates entering, exiting, or lingering/turning back (including loops and hesitation).

Confirm
Count only when the journey is complete
A count is recorded only when the person leaves the zone in the opposite direction — confirming a true entry/exit event, once.
Trusted Across Industries
“The accuracy of the Hoxton people counter transformed our understanding of visitor patterns. We finally have data we can trust for staffing decisions.”
Center Parcs
Leisure and hospitality group
“We can now compare store performance fairly using conversion rates instead of just revenue. It has completely changed how we manage our franchise.”
Vodafone Franchise Partner
Telecommunications retail
People Counter FAQ
See It in Action
Book a demo and we'll show you real dashboards from spaces like yours.
