CAM-78
How people spread across the floor
A fashion store floor seen lengthwise, from the door to the back: product tables in the foreground with people around them, fewer people in the middle and a back section that is nearly empty. IRIS counts how many people are in each area; it does not know who any of them are.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- product table
- floor staff
What this camera gives back
Nobody gets an alert here. Here you get numbers.
- 1.180Visitors today
- 48%Front of store
- 34%Middle of store
- 18%Back of store
- 7 minTime spent
- 19:00Peak hour
The figures on this screen are an example from the illustration, not any client's measurement.
IRIS incorporates NeuralPax, a separate licence certified by the Spanish Metrology Centre for people counting, occupancy and crowd-flow control. That the figure is right is guaranteed by a third party, not by us, and that is why it holds up against the regulations in force. The certification covers that measurement — counting people — not the whole product.
The series, not one figure
One number says nothing. A curve does.
Where people spread out
- Of everyone who comes in
| Slot | Of everyone who comes in |
|---|---|
| Front | 48% |
| Middle | 34% |
| Back | 18% |
The figures on this screen are an example from the illustration, not any client's measurement.
How the counting works
Counting is not something you ask for. You draw a line.
The floor is split into three areas drawn onto the image: the front, the middle and the back. IRIS counts how many people are inside each one and how long they stay on average. There is no line to cross here, because what matters is not who goes past but where they stop. The three areas are drawn once and stay put, so this month's campaign can be compared with last month's.
- front area · Dwell zone
- middle area · Dwell zone
- back area · Dwell zone
What changes
What changes for whoever runs the store
The back of the store is almost always visited far less than the front. Everybody knows that; what nobody has is how much less, in this store and this month. The store manager decides where the next campaign goes on instinct, and instinct always says the same thing: up front. With the three areas drawn he sees the real split and he can run a test — move the new-arrivals table to the middle and check next week whether the split has shifted. The percentages on the illustration are an example, not any store's measurement.
What people usually ask
Is this a heat map?
It is the same thing, counted in a way you can audit. A heat map paints pretty blobs and everyone reads them as they please; here there are three areas with a defined edge and one figure per area, and that figure can be compared month by month precisely because the area has not moved. If the edge changes, the figure is worthless — which is why the area is drawn once and stays.
Does IRIS know who comes in and the route each person takes?
No. IRIS counts how many people are inside each area at each moment. It does not recognise faces, it does not compare them against any database, it does not store who anyone is and it does not follow a person from one store to another. What comes out is a split of the floor, not anybody's route.
What if the back of the store is where the fitting rooms or the stockroom are?
Then the back figure means something else and has to be read that way. The areas are drawn by whoever knows the store, not by us from outside: if the back is the way through to the fitting rooms, that percentage does not measure interest in the product, it measures passing traffic. The figure does not say what to do; it says what is happening, and deciding is still a person's job.
The real interface, step by step
A new case each time. Always the same screen.
It plays by itself and shows one case from start to finish. It is a summary: the real screen has far more functions than fit in this box.
- The alert fires
- It lands in the tray
- You open it
- You confirm or dismiss
Next step
Who watches an entire motorway?
10 cases: 8 raise an alert when something happens and 2 only measure. You see each image as it is, and then with what IRIS understands on top.
Who watches a whole station at rush hour?
17 cases: 11 raise an alert when something happens and 6 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
One camera,and you already have a watchman. Four thousand cameras, and you have four thousand watchmen.
None of them tires, none of them looks away and none of them works shifts. And there is nothing to install: the cameras you already have can start understanding what they see.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.