What does a shopping centre see beyond the visitor count?
Footfall tells you how many came. IRIS tells you what happened inside.
Which door they came in by, which floors they stayed on, which malls they avoided and what changed the day you launched the campaign. We show twelve cameras here: some measure, others raise alerts. A real centre has hundreds. The system is exactly the same. And everything counted is anonymous: IRIS counts bodies, it identifies nobody.
Without IRIS this is just people walking through a door.
AI-generated image
Counting is not understanding
Every month a report arrives with the visitor count. It goes up or down, and nobody can explain why. A mall on the first floor has been half empty for six months, and you find out the day the tenant there asks for a rent cut. The campaign cost money, and the only proof it worked is that more people came in that Saturday. Everyone knows about the half-past-one queue in the food court, and it is measured nowhere.
IRIS reads the cameras the centre already has. It counts which door people come in by, which floors they pass through, which malls fill up and which go cold, how many come up from the car park and how long the wait is at each counter. And all of it is anonymous: it counts bodies and measures routes. It does not recognise faces, it identifies nobody, and it does not follow a person around the centre. In a business that lives off visitor data, that line is worth having in writing.
And there are two ways to ask for things, because they are two different things. What you watch for is described in words: one sentence, and IRIS alerts you when it happens. What you measure is drawn: a line across the threshold, an area on the floor. A line does not fit in a sentence, you have to draw it — which is why Tuesday's number and Saturday's are measured the same way, and why they can be audited. Capacity goes further: people counting is type-approved by the Spanish Metrology Centre through NeuralPax, the body that says whether a weighbridge or a speed camera measures correctly. Mind the scope: what is approved is people counting, not the rest. And there is one line the camera does not cross: IRIS sees who stops in front of a shop window; whether that person went in and bought is something the tenant tells you from their till data.
The real scale
Twelve here. Hundreds in a real centre.
This demo shows twelve cases because twelve fit on a screen. A real centre has cameras at every entrance, in the car park and on its ramps, along the malls of every floor, in front of the shop windows, on the escalators, in the food court, in the atrium where events are staged, at the loading bays, all along the perimeter and at the doors of the toilets — where access and how often they are serviced are what is monitored, never the inside. Hundreds of them, and a few more with every refurbishment. Nobody can watch them all on a Saturday afternoon; that is exactly the problem IRIS solves: it analyses however many there are, all at once, and only interrupts when a rule is met. And where there is nothing to watch for, it measures: how many people come in through each door, how many go up to each floor, how long the wait is at each counter.
Examples
These twelve are just examples.
Each one shows a different kind of thing: an entrance, a mall, a shop window, a queue, an escalator, an exit. They are not the twelve things IRIS can do: they are the ones that fit on a screen. Open any of them and you will see the image as it is, and then with what IRIS understands on top.
Every simulation
Search by number plate
Show me every time that plate crossed the barrier this week, with the time and the video.
- What you are looking for
- Where to look
- What matches
- Who looks
Now think about yours
Imagine knowing which door your visitors use and which mall they avoid.
The car park door brings in twice as many people as the street door, and the tenants paying the highest rent are on the other side. A mall on the first floor that almost nobody walks through any more since the unit at the end closed. A shop window people stop in front of, and another they walk straight past. The weekend campaign that filled the atrium and moved nobody out of it. The half-past-one queue in the food court, with one counter overwhelmed and the one beside it idle. The number of people in the atrium during an event, which you must be able to show the authorities. The foot of an escalator where somebody has just fallen. A spill on the floor, half an hour before the first complaint. An abandoned trolley in the middle of the walkway. A child on their own who has been wandering for a while. Smoke in a corridor and the exit blocked by boxes.
All of that is happening in front of cameras your centre already owns and already paid for. And nobody knows until someone complains, or until a tenant shows you their sales and asks why. IRIS watches them all at once: it counts what you drew and alerts you when what you wrote comes true, with the camera and the time. And it does it without identifying anyone: it counts bodies and measures routes, it does not recognise faces and it does not follow a person around the centre.
Next step
What if the outage does not start with an attack?
13 cases, and in every one of them IRIS raises an alert when something happens. You see each image as it is, and then with what it understands on top.
And who watches the cameras?
0 cases, and in every one of them IRIS raises an alert when something happens. You see each image as it is, and then with what it understands on top.
And the best part
Video tells you what happened.An alert reaches you while it is happening.
Reviewing the recording helps you explain. Hearing about it at the time helps you get there. Two different things, and until now you only had the first.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.