The prisonInfrastructure integrity
CAM-101
Blocked access on the landing
A two-tier cell wing seen from above. At the far end, in front of the barred gate that closes the passage, the laundry carts and the service bins have been pushed into a line until the gate is blocked. Three people in custody have stopped halfway down the tier, backs to the camera, looking toward that passage. Bottom left, an officer stands by the wooden benches with a hand on his radio.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognizes in this scene
- blocked passage
- barred gate
- people stopped on the tier
- officer on the tier
- stairs to the upper tier
What this camera measures
An alert says something’s happening. The reading says how much.
- 4 minBlocked for
- 6Objects against the gate
- 0Clear gap, in inches
- 3People in the gallery
- 1 / 2Usable ways out
- 11:42Time of the alert
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
an object comes to a stop in front of a door or a barred gate and is still there seconds later
Then
- alert the control room with the camera, the passage affected and the time
- open the video from the moment things started being moved there
- keep the clip for the incident report
The instruction that set it up«Tell me if anything is left in front of a door or a barred gate and stays there, because that is the way we have to get through.»
What changes
What changes for whoever answers for the facility
Today this gets noticed when someone walks the tier, or when that camera’s turn comes round on the wall of screens. A facility has hundreds of cameras and two people in the control room: nobody can hold their attention on all of them at once, and that isn’t a failing of the officer, it’s a human limit. Meanwhile the passage has been shut for minutes and whoever needs to come through doesn’t find out until they get there. With IRIS the alert goes out while the passage is being blocked, with the camera and the location, and the video of those seconds is kept. What you gain isn’t the picture: it’s the time. And that clip is what later backs up the incident report, which has to be written anyway.
What people usually ask
Does IRIS know who put the carts there?
No. IRIS does not identify anyone: it does not recognize faces, it does not compare them against any database, it does not store who anyone is and it does not follow a particular person. What it detects is a situation — a passage that has stopped being clear — and what it hands over is the place, the time and the video. It can’t be used to sanction a particular person: the one who watches the video, decides and answers for it is the facility.
What about the laundry carts, which go through there every day?
That’s exactly why the rule is written by the facility and not by us. You define which passage has to stay clear, at what hours, and how many seconds something may sit in front of it. A cart going through triggers nothing; a cart that stays does. If the alert fired every time the laundry went past, within a week nobody would look at it, and then it would be worth nothing.
Does this warn before something happens?
No, and we aren’t going to claim it does. IRIS doesn’t predict: it reports something that’s happening in front of the camera, not something that’s going to happen. It doesn’t score anyone and it doesn’t classify anyone by how they behave. All it sees here’s that a passage is blocked right now. What that means and what to do about it is decided by a person who knows the wing.
Demo · IRIS at work
You set the rule once. IRIS applies it every time.
You will see a summary of the interface, played step by step and hands-free. Each round starts with another case. The complete tool doesn’t fit in a demo.
- It lands in the tray
- You open it
- You confirm or dismiss
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 mall 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
A wall of monitors is impressive.Nobody can read forty tiles at once.
The more tiles there are, the less each one gets looked at. IRIS watches all four thousand cameras at once and points at a single one: the one that needs someone right now.
Tell us your problem and we’ll say whether IRIS understands it, or not yet.
A person answers, the same working day.