CAM-62
Breakdown on the shoulder
A car stopped on the shoulder with its reflective triangle out and smoke coming from the hood. The driver is standing outside the car, a step away from the lane where everyone else keeps driving past.

Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognizes in this scene
- stopped car
- person outside
- smoke
- reflective triangle
- passing traffic
The rule
You decide once. IRIS applies it always.
If
a vehicle stops on the shoulder
And alsoa person gets out and walks close to the running lane
Then
- alert the control room as high priority
- lower the speed limit and light up the sign for that stretch
- send the nearest patrol
The instruction that set it up«Tell me if someone gets out of their car on the shoulder and stands next to the traffic.»
What changes
What changes for whoever runs the road
The serious thing in this scene isn’t the car: it’s the person standing three feet from vehicles going past at highway speed. Today the control room finds out when the driver phones in, if he phones at all, and many don’t. With IRIS the operator sees the alert while that person is still outside the car: he lowers the limit on that stretch, lights up the sign and sends the patrol. The broken-down car can be towed later; the person can’t wait.
What people usually ask
Aren’t there cars stopped on the shoulder all the time?
Yes, and that’s why the rule isn’t triggered by the car alone. A vehicle stopped on the shoulder is information: it is logged and checked again a while later. What raises the alert to urgent is someone getting out and moving toward the running lane, or the car ending up half on the shoulder and half in the lane. That way the operator doesn’t get a hundred identical alerts, only the few where a person is exposed.
Does IRIS tell a broken-down driver from a maintenance worker?
Partly. IRIS sees the safety vest, the work vehicle and the amber beacons, and with that you can write a rule that stays quiet when there’s planned work at that spot. When the camera is far away or the light is poor, that difference is harder to see, and then the alert comes through anyway with the picture so the person in the control room can decide in two seconds. We would rather have one alert too many than someone alone on the shoulder with nobody aware of it.
Do the cameras on that stretch have to be replaced?
No. IRIS works with the cameras already installed along the road. What changes isn’t the sensor but what’s understood from the picture. If at a particular spot the camera isn’t good enough to make out a person on the shoulder, IRIS says so before it is installed, not afterward.
The real interface, step by step
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.
- It lands in the tray
- You open it
- You confirm or dismiss
Next step
The school
Who sees the child who’s fallen at the far end of the schoolyard?
14 cases: 13 raise an alert when something happens and one only measures. You see each image as it is, and then with what IRIS understands on top.
Critical infrastructure
Who is watching a site where there’s 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 already record.The hard part was always watching it.
Years of video that only get opened once something has gone wrong. IRIS understands those same images as they arrive, so the answer no longer lives only in the archive.
Tell us your problem and we’ll say whether IRIS understands it, or not yet.
A person answers, the same working day.