CAM-61
Multi-vehicle crash
Three cars have crashed and are lying across two lanes. Loose parts are scattered on the asphalt and a queue is building up behind them.

Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- vehicle involved
- debris
- queue
- lane blocked
The rule
You decide once. IRIS applies it always.
If
two or more vehicles end up stopped and lying across the lanes
And alsoa queue starts to build up behind them
Then
- alert the control room with the camera and the lane
- open the video from a few seconds before the crash
- call the road patrol and the emergency services
The instruction that set it up«Tell me the moment there is a crash on the road, and which lanes are blocked.»
What changes
What changes for whoever runs the road
The operator in the control room has dozens of cameras in front of him and cannot watch them all at once. Today he almost always hears about a crash from a phone call, and by then the queue is already hundreds of metres long. With IRIS the alert comes up while the crash is happening, with the camera, the blocked lane and the video of the seconds before. That operator closes the lane, lowers the limit on the signs and sends the patrol out before the second crash arrives: the car that brakes too late into the back of the queue.
What people usually ask
How does IRIS tell a crash from an ordinary traffic jam?
By the way the vehicles are sitting. In a jam the cars are stopped inside their lane, in a line; in a crash they end up across the lanes, at odd angles, with debris around them and people getting out. IRIS describes what it sees — stopped vehicles lying across lanes, parts on the road, people out of their cars — and the operator confirms it with the picture on the same screen. IRIS does not rule on the cause of the crash: that is the job of whoever writes the accident report.
Does IRIS call the ambulance by itself?
No. IRIS alerts the control room and puts the camera, the lane and the video in front of it; the call to the emergency services is made by a person, who decides. It can also be set up to fire automatic notices — a sound in the room, an email, a message to the shift supervisor's phone — but sending out resources stays a human decision, and it should.
Does it work at night or in fog?
It depends on what the camera can see. With the lighting of the stretch, with the traffic's own headlights or with a thermal camera, IRIS still sees stopped vehicles and queues. In thick fog or with a dirty lens it sees less, exactly as a person looking at that same screen would. That is why every spot is checked before the coverage is signed off, and where the camera does not reach, we say so.
A different case every time
Watch what happens. Then watch what IRIS does with it.
Not a recorded video and not a drawing: it is a summary of the real tool, with a different case each time round. The whole tool does not fit in a box.
- You ask
- IRIS searches
- It shows you
Next step
Stadiums and venues
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.
Hotels
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
Nothing to drill, nothing to rip out:the cameras already on your walls can start understanding.
No building work, no new cabling, no swapping equipment. It connects to what is already there, and what is already there starts telling you what it sees.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.