CAM-109
A car parked too long against the wall
The public road that runs right along the facility wall, seen from a high camera. A white van is parked at the kerb with a grey car in front of it. Two people are standing on the pavement below the sign on the wall, and another is standing against the fence further along. Beyond that, the staff door and the watch post. IRIS measures how long each thing has been there. Nothing else: it does not know whose car that is or who is inside it.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- car standing still
- person at the fence
- parked van
- people on the pavement
- staff door
The rule
You decide once. IRIS applies it always.
If
a vehicle or a person stays still in the strip outside the wall for longer than the facility has set
Then
- alert the control room with the camera, the point of the perimeter and how long it has been there
- open the video of those minutes so a person can look at it and decide
- log the time, so the facility learns whether that stretch of wall is one of the busy ones
The instruction that set it up«Tell me if a vehicle stays parked against the wall for longer than we have set, or if someone stays put against the fence, and tell me which point of the perimeter it is.»
What changes
What changes for whoever answers for the facility
Nobody watches the outside of the wall. There is a camera there, but in front of it there is one more screen among forty, and whoever is in the control room has other things to deal with. With IRIS that strip watches itself: if a vehicle or a person stays still there longer than the facility has set, an alert arrives with the camera, the point of the perimeter and the video of those minutes. What arrives is not an accusation, it is a question: look at this. A person decides what it means, and still does.
What people usually ask
This camera looks at a public road. What does IRIS NOT do here?
It identifies nobody. It does not read number plates, it does not recognise faces, it does not compare them against any database, it does not store who anyone is and it keeps no record on anyone. A car parked for a long time next to a wall can be anything: someone waiting for someone else, someone who pulled over to make a call, someone who is lost. All IRIS says is that this vehicle has been there longer than the facility has set, and at which point. Who is inside and what they are doing is not something IRIS knows, or could know: a person looks at that.
Can this be used to sanction someone?
No. IRIS identifies nobody and cannot be used to sanction a particular person. What it produces is an alert about a situation — a vehicle parked too long at one point of the wall — with its time and its video. There is no name in that alert, because IRIS does not have one and cannot have one. What the facility does next follows its own procedures, with people who look, decide and answer for what they decide.
What about the people who walk past every day?
Walking past is not staying. The rule looks at how long something has been still in the outer strip, and below that time nothing happens: someone walking by, pulling over for a moment and leaving, or waiting to be let in, produces no alert at all. How long is too long is written by the facility, not by us, and it can differ between day and night, or between one stretch of wall and another. That number is what decides whether the alert still means anything: if it fires constantly, everybody stops looking at it.
A different case every time
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.
- 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
You decide the rule onceand it is applied the same way every time.
At three in the morning it means what it means at noon, on camera one and on camera four thousand. It does not depend on who is on shift, or how tired they are.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.