Stadiums and venuesIntrusion detection
CAM-487
One person climbs the fence while everyone else uses the turnstile
Concert afternoon, in front of the access gate. Five turnstiles with green lights and people validating in line. On the right, next to the pillar, someone has climbed onto the metal fence: both hands on top and one foot on the rail. The steward is three metres away, with his back turned. IRIS sees that somebody has come in where nobody comes in, and saves the video.
Turn on IRIS Vision
AI-generated image
What IRIS is
IRIS keeps an eye on every gate for you.
IRIS is an artificial intelligence that watches the cameras you already have at the venue and understands what's happening at the gates and in the stands. When a crowd builds up at an entrance, a stand nears capacity, or something you've asked it to watch happens, it alerts you — and whatever can be counted, like people in each area, it counts in numbers. All day long, with no one needing to watch a screen.
You tell it what you need to watch, and IRIS does it.
Here, for example, when someone climbs the fence instead of going through the turnstile, IRIS spots it instantly and saves the video with the exact camera and time. That way you know someone has got in without paying and without anyone noticing. With that alert you decide to send a steward to that gate, then check if it happens again.
Works with the cameras you already have. Nothing to replace.
A person replies, not a form.
- Your footage never leaves your premises.
- It doesn't identify people.
- Certifications →
What IRIS understands
What it recognises in this scene
- person crossing outside the turnstile
- side fence
- bank of turnstiles
- venue steward
- spectators validating
What this camera measures
An alert says something is happening. The reading says how much.
- 1.860Validations counted at the gate
- 1Crossings outside the turnstile
- 2Two-person passes on one validation
- 5Turnstiles open
- 19:12Time of the crossing
The figures on this screen are an example from the illustration, not any client's measurement.
The rule
You decide once. IRIS applies it always.
If
a person crosses the fence outside the turnstile or two people go through on one validation
Then
- alert the gate staff with the camera and the turnstile involved
- save the video of the ten seconds before and the ten after
- add the crossing to the gate tally for the event report
The instruction that set it up«Tell me if somebody comes in outside the turnstiles, or if two people go through on a single validation.»
What changes
What changes for whoever runs security at the venue
Concert afternoon, and at the gate five turnstiles are validating one after another. By the pillar, someone has climbed onto the metal barrier; the steward is three metres away, back turned. Every person who gets in without validating is a ticket that was not sold, and also somebody inside that nobody knows about. In a venue where the audience is split into separate blocks, where they come in matters as well: a ticket for one block is not a right to stand in another. IRIS counts validations, counts crossings outside the line and flags two people going through on a single read. What happens next is the venue’s call.
What people usually ask
Does IRIS know who climbed the fence?
No, and it never will. IRIS does not recognise faces and does not compare them with any list. What it detects is a movement: a person crossed a fence where nobody crosses, at 19:12, in front of this camera. Who it was will come from the staff who get there, or from nobody at all. The system provides the fact, the place and the video.
Can it flag somebody heading for a block that is not theirs?
Yes, if the venue draws that separation on the image. A person moving from one block’s area into another’s is a line crossing, and the camera sees that. It does not say whether that person had a right to be there: it says they crossed. Matching ticket to block is the job of access control, not of the camera.
What if the queue was just crowded and two people went through together by accident?
It happens, and that is why the alert accuses nobody. IRIS says that two bodies went through that turnstile on a single read, and saves the seconds before. With the video in front of him, the gate supervisor sees in two seconds whether it was a shove from the queue or a deliberate jump, and decides. IRIS does not decide, and it calls nobody suspicious.
Other cameras
- CAM-480 · The queue tells you when the gates should open
- CAM-481 · One gate standing idle while the next one jams
- CAM-482 · Twenty-four arrive a minute, the search line clears nine
- CAM-483 · More people per square metre than three minutes ago, and nobody moves
- CAM-484 · The ramp is packed and the concourse next to it is empty
- CAM-485 · Twenty thousand people leaving at once, all through the same gate
See it for yourself
This isn’t a video. It’s a slice of the real screen.
A summary of the real interface, played hands-free. You see one case from start to finish; what you do not see are the other screens, and there are many.
- The rule gets built
- It goes to every camera
- Published, it watches alone
- And then it fires
See it somewhere else
Who sees the child who has fallen at the far end of the playground?
14 cases: 13 raise an alert when something happens and one only measures. You see each image as it is, and then with what IRIS understands on top.
Who is watching a site where there is almost never anybody?
44 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
At eleven the last person leaves.The cameras stay, and now they understand what is going on.
Nobody switches anything off on the way out. What happens in an empty building is understood right then, and nobody waits for the doors to open to find out.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.