What does a venue with twenty thousand people inside see?
When twenty thousand people leave at once, more screens will not help.
You need to know which gate is starting to block and how long you have to act. We show fifteen cameras here: eleven that raise an alert when something goes wrong and four that alert nobody, they just count. A large venue has hundreds. The system is exactly the same.
Without IRIS this is just a crowd on a screen.
AI-generated image
A packed venue, understood
On event day there are more screens than eyes. Queues build up outside, the security check jams, a stairwell fills and the control room finds out when people are already pushing. And by then you are not redirecting a queue: you are clearing an area.
IRIS watches for them. It analyses every camera at once and only interrupts when a rule written by the venue itself is met: density climbing in an access tunnel, an evacuation route blocked, a flare in the stand, someone on the ground. And it identifies nobody: it sees situations, not people. In a packed stand, that matters twice as much.
What arrives is not more video. It is an alert with the camera, the time, what is happening and what should be done. And when nothing happens, it is numbers: how long it takes to get in through each gate, how many people each turnstile clears, how many people are inside. That last number is the only one a third party has verified: 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. With that, a safe capacity is defended before the authorities with a measurement, not an estimate. Mind the scope: what is approved is people counting, not the rest.
The real scale
Fifteen here. Hundreds on event day.
This demo shows fifteen cases because fifteen fit on a screen. A real venue has cameras in the car park, at the coach stops, at the entrance gates, at the security check, at the turnstiles, in the concourses, on the stairs, in the access tunnels, in the stands, at the bars, in front of the stage and all along the perimeter. Hundreds of them, and a few more every season. No person can watch them all on a sold-out day; 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 counts: how many people come in through each gate, how long each queue lasts, how many people are inside at any moment.
Examples
These fifteen are just examples.
Each one shows a different kind of thing: a queue, a turnstile, a surge, an exit, a stand. They are not the fifteen 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.
Demo · IRIS at work
A camera looks. IRIS understands what it sees.
An extract of the real screen, no voice-over and hands-free. Each round poses another situation. What sits behind it is a good deal bigger than what you see.
- The rule gets built
- It goes to every camera
- Published, it watches alone
- And then it fires
Now think about yours
Imagine knowing while there is still time to act.
A gate that takes twice as long as the one next to it to let people in. A turnstile standing idle while the one beside it jams. A security check clearing fewer people than arrive. A stand where there are more people per metre every minute and nobody moves any more. A stairwell and an access tunnel turned into a funnel. Twenty thousand people leaving through a single door because the rest are shut. An evacuation route blocked by a merchandise stall or a badly placed barrier. A flare lit in the stand, and you need to know which row. A person on the ground who has not moved for a minute.
All of that is happening in front of cameras your venue already owns and already paid for. And nobody knows until someone shouts it over the radio, because there are not enough people to watch that many screens on a sold-out day. IRIS watches them all at once and tells you while it is happening, with the camera and the gate. In a fight it prioritises getting someone there: it does not decide who is to blame. A person decides that afterwards, with the video in front of them.
Next step
How long does it take to find a hand played two hours ago?
12 cases: 9 raise an alert when something happens and 3 only measure. You see each image as it is, and then with what IRIS understands on top.
What does a shopping centre see beyond the visitor count?
12 cases: 4 raise an alert when something happens and 8 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
IRIS only sees what the camera shows.Where we do not reach, we say so.
No software fixes a lens pointing the wrong way or covered in dust. Before promising anything, we say which cameras are in a state to see what you are asking of them.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.