CAM-137
The fire exit, blocked
A stair landing inside the building. At the back, the green fire door with its sign above it. Right against the leaves: a cart of balls, a blue recycling trash can, a crate, two stacks of cardboard boxes and four backpacks on the floor. On the right, a wooden cabinet pushed up against the door; on the left, classroom tables and chairs stacked up. A group of students is standing right in the middle of the passage. Down the stairs, the exit route carries on.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognizes in this scene
- things left in front of the exit
- fire exit door
- cabinet pushed against the door
- tables and chairs stacked up
- stairs going down
What this camera measures
An alert says something’s happening. The reading says how much.
- 6 hBlocked for
- 8Things left in the passage
- 0 / 2Door leaves left clear
- 9People on the landing
- 4Backpacks on the floor
- 11:35Time 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
something is left in front of a fire door or in a stairway passage and is still there after the number of minutes the school has set
Then
- alert the custodian with the camera, the door and what is in front of it
- save the image, so it is on record what was there and at what time
- alert again if it is still there a while later
The instruction that set it up«Tell me if anything is left standing in front of a fire exit or in a stairway passage, and tell me today, not in six months’ time.»
What changes
What changes for the school team
A blocked fire exit is one of the few things in a school that everyone can see and that still lasts for months. Nobody blocks it in bad faith: a delivery gets unloaded, the old tables come out of a classroom, the balls get left there “for a minute,” and that minute becomes the place where the balls live. The day that door really gets looked at is inspection day; the rest of the year a hundred people walk past it and none of them registers it. IRIS looks at that piece of floor every day and reports it the same day, with the picture of what’s standing there. Clearing it takes five minutes and a pair of hands: fixing it was never the problem, finding out was.
What people usually ask
Do we need a new camera for this?
No. If the landing already has a camera, IRIS works on that same image: you mark on it the piece of floor that has to stay clear and you set how long is too long. Which doors have to stay clear, how many minutes and who gets the alert is decided by the school, not by IRIS.
Does IRIS identify the students in the image?
No. IRIS does not identify any minor: it does not recognize faces, it does not compare them against any database, it does not store who anyone is and it keeps no record on any student. Here it doesn’t even need the people: what it looks at is whether things have been left standing in the passage. It can’t be used to write up a child — nor to find out who left the boxes there.
And the backpacks on the floor? Will the alert fire every recess?
It depends on what the school asks it for. A backpack that sits on the landing for two minutes isn’t the same as a cabinet that has been there since Monday, and the rule can tell them apart by time and by size. Starting narrow and tuning it during the first week is what keeps the custodian still looking at it next month: an alert that fires all the time stops being read.
A different case every time
Everything comes in. Only what matters gets through.
This sums up what IRIS does with one alert, from the moment it appears until it’s 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
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
By the eighth hour of a shiftnobody watches the way they did in the first. That isn’t a flaw.
It’s being human. A camera has no eighth hour: at four in the morning it understands what it understood at noon, and it speaks up just the same.
Tell us your problem and we’ll say whether IRIS understands it, or not yet.
A person answers, the same working day.