CAM-491
A scuffle and a ring of people closing in
Half an hour before kick-off, on the forecourt between two access gates. Six men are grappling in the middle. Around them, a ring of onlookers that has closed in under a minute. A steward is coming in from the right. IRIS sees two things: physical contact between people, and a circle that grows and closes. From above, the ring shows up long before the contact does. It does not know who anybody is, and it does not know who started it.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- physical contact between people
- the ring closing in
- steward on his way
- access gates
- stall under a canopy
What this camera measures
An alert says something is happening. The reading says how much.
- 22 sSince first contact
- 6People in contact
- 46People in the ring
- 1Staff in shot
- 19:07:41Video starts at
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
there is physical contact between several people and the ring around them grows
Then
- alert the nearest steward with the gate, the camera and the time
- save the video from thirty seconds before the first contact
- show how many people are around and which way to get in
The instruction that set it up«Tell me if there is physical contact between people or a ring closing in on the forecourt, and tell me which gate.»
What changes
What changes for whoever runs security at the venue
Here it pays to be exact. IRIS detects physical contact and a ring closing in. It does NOT establish who started it, it does NOT identify anybody and it does NOT decide who is to blame. All it does is get the intervention there sooner, which is while a shove is still just a shove. That difference — thirty seconds — is what separates an incident settled with words from one that ends up in a report, in hospital or in the papers.
What people usually ask
Does IRIS say who started the fight?
No. IRIS detects physical contact and a ring closing in, and nothing more. It does not establish who started it, it does not identify anybody and it does not decide who is to blame. All it does is get the intervention there sooner, while a shove is still just a shove. Who was at fault is established by whoever investigates, with the video in front of them and under the venue’s procedures.
Why does it watch the ring and not only the people grappling?
Because the ring shows up first. From a high camera, a circle of people closing around one spot is a very clear shape, while two people shoving each other among twenty thousand is hidden. The moment people stop walking and turn towards the same place, something is happening there. It is the same cue any experienced steward uses, counted by a machine that never blinks.
And what if it is a celebration and not a fight?
It can happen, and that is why the alert goes to a person and not to a device. IRIS sees physical contact and a ring closing in; telling a celebration from a fight is done by whoever looks at the image, and it reaches them with the video, while it is happening. Ten seconds of unnecessary video costs nothing. Arriving late at the real one does. IRIS does not act: the decision to step in is always a person’s.
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
Everything comes in. Only what matters gets through.
This sums up what IRIS does with one alert, from the moment it appears until it is closed. The real screen holds far more; this is the main thread.
- Cameras on the map
- You draw an area
- What passed shows up
Next step
Who sees the child who has fallen at the far end of the playground?
13 cases: 12 raise an alert when something happens and 1 only measure. 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 four in the morning,the camera is still watching just as it does at noon.
No heavy eyelids, no distractions, no shift change. What happens at night is understood at night, not the next morning.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.