The highwayInfrastructure integrity
CAM-63
People walking on the roadway
Two people are walking along the roadway, very close to a tunnel entrance. A car and a truck are coming up the same stretch at highway speed.

Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognizes in this scene
- pedestrian
- tunnel entrance
- car
- truck
The rule
You decide once. IRIS applies it always.
If
a person is walking on the roadway or on the shoulder
Then
- alert the control room at the highest priority
- lower the limit and light up the signs on the stretch before
- send the patrol and call the traffic control center
The instruction that set it up«Tell me right away if you see anyone walking on the roadway, and all the more so near the tunnel.»
What changes
What changes for whoever runs the road
A pedestrian on a highway is one of the things that frightens a control-room shift the most, and it’s nearly always learned from another driver’s phone call. Near a tunnel it’s worse: there’s nowhere to step aside, and the driver goes from daylight into shadow exactly where those two people are. With IRIS the operator gets the alert while they’re still walking, and sees which lane they’re in and which way they’re going. He lowers the limit on the signs before the tunnel and sends the patrol, which is the only thing that gets someone out of there in time.
What people usually ask
What if they’re workers on the road?
The alert still comes through, and that’s how it should be. When work is scheduled, the time window and the stretch are marked, and during that period the alerts from that area are grouped instead of firing one by one. But a person walking on a highway is always recorded, with time and image: that’s exactly what you need if the way the work was done has to be reviewed later.
Can it mistake a shadow or a sign for a person?
It can happen, and that’s why the alert never arrives on its own: it comes with the image crop and the video, and the operator confirms it at a glance. IRIS goes by shape, movement and the size you would expect at that distance, so a still shadow or a painted silhouette rarely gets through. When a spot produces a lot of doubtful alerts, the framing or the watched area is adjusted; what isn’t done is switching the alert off.
Why is it so critical right at the tunnel entrance?
Because there the driver needs a moment to adjust to the change of light, there’s no wide shoulder to step onto, and braking takes longer than people think. That’s why cameras are placed on both sides of the entrance and each one is checked to make sure the approach and the exit roadway are clearly visible. If a camera ends up against the light and can’t make out a person, it is moved or another one is added.
A different case every time
Watch what happens. Then watch what IRIS does with it.
Not a recorded video and not a drawing: it’s a summary of the real tool, with a different case each time round. The whole tool doesn’t fit in a box.
- Finds the plate
- Reads the characters
- Follows the same plate
Next step
The highway
Who watches an entire highway?
10 cases: 8 raise an alert when something happens and 2 only measure. You see each image as it is, and then with what IRIS understands on top.
Public transport
Who watches a whole station at rush hour?
17 cases: 11 raise an alert when something happens and 6 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
No building work, no trenches, no new cabling:the cameras are already up and already looking.
What changes is what happens to the picture. It used to be stored and never seen; now it’s understood while it happens, on the same equipment you bought years ago.
Tell us your problem and we’ll say whether IRIS understands it, or not yet.
A person answers, the same working day.