CAM-408
Somebody came over the fence and is among the tanks
Late afternoon at a small drinking-water plant, up on a clifftop. The compound is closed off with mesh and wire, and the open basin sits in plain view inside. On the hillside, a person in a dark hoodie and a cap has come over the fence and is leaning on the inner rail. A worker is coming across from the gate. IRIS does not say who they are or why they came: it says a closed boundary has been crossed.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- person who has crossed the fence
- line of the perimeter fence
- open water basin
- plant worker
- access gate
What this camera measures
An alert says something is happening. The reading says how much.
- 40 sInside the compound for
- 1Crossings of the perimeter
- 2People in frame
- 1Vehicles in frame
- 17:35Time 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
a person crosses the line of the fence at a point that is not an access
Then
- alert the duty service with the camera, the time and the video of the crossing
- keep the sequence from the moment the person appears outside the fence
- log the alert in the report with the exact spot of the fence that was crossed
The instruction that set it up«Tell me the moment somebody crosses the fence where there is no gate, at any hour.»
What changes
What changes for whoever answers for the plant
A small water plant has no gatekeeper and no control room: it has one visit a day and a van going past. Whatever happens between visits gets found out the next day, if at all. This camera changes when the manager finds out: the moment somebody crosses the fence, with the picture in front of him so he can decide whether to send the duty crew or call the police. IRIS neither decides that nor acts.
What people usually ask
Does IRIS know whether that person meant any harm?
No, and it will not hint at it either. IRIS does not judge intentions and does not label anyone. What it detects is a fact you can see in the picture: at this hour, at this point, somebody crossed a closed boundary. It could be a neighbour who has lost a dog, or somebody who should not be there. That is decided by the person who gets the alert, by watching the video.
Does it recognise the face of whoever climbed over?
No. IRIS does not identify anyone: it does not recognise faces, does not read number plates, does not compare against any database and does not store who anyone is. It detects situations, not people. The alert carries the camera, the time and the video of the crossing, and that is what you act on. Identification, if it is needed, is a matter for the competent authority, not for a camera.
What about animals and branches at night?
That is the right question, because a perimeter out in the countryside moves all the time. The rule is set on the line of the fence and on the shape and size of what crosses it, not on movement in general. A wild boar or a branch in the wind does not look like a person coming over the fence. And every alert carries the video, so closing it takes two seconds.
Other cameras
- CAM-400 · Water is coming up through the cover and the street is a river
- CAM-401 · The clarifier has filled with foam and it is going over the weir
- CAM-402 · The screen is packed with wipes and the water is not getting through
- CAM-403 · A tree has come down the channel and is blocking the intake
- CAM-404 · A jet is spraying from the flange and the puddle keeps growing
- CAM-405 · The container plugged in is not the one that belongs there
See it for yourself
We won't just tell you. We'll show you.
It is a summary of the real screen: it plays by itself, step by step, and shows only the path of one case. The actual tool has far more than fits in here.
- Finds the plate
- Reads the characters
- Follows the same plate
Next step
What does a venue with twenty thousand people inside see?
15 cases: 11 raise an alert when something happens and 4 only measure. You see each image as it is, and then with what IRIS understands on top.
When does a bad review get decided?
15 cases: 11 raise an alert when something happens and 4 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
Behind one camera you can put a person.Behind four thousand you cannot put anyone.
Adding a camera costs little; adding another pair of eyes does not. So the cameras keep growing and the attention does not. IRIS watches all four thousand at once and flags what matters today.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.