Public transportIntrusion detection
CAM-89
Bikes and scooters through the gates
A bicycle and two scooters cross the line of ticket gates among the passengers walking in. One of the scooters goes through with its rider still on it.

Turn on IRIS Vision
AI-generated image
What IRIS is
IRIS keeps watch over the platform for you.
IRIS looks at the cameras you already have on platforms, gates and entrances and understands what's happening: an overcrowded platform, someone falling onto the tracks, a fight or a forced gate. When something important happens, it alerts you; and whatever can be counted, it counts. All day long, with no one watching a screen.
You tell it what you need to watch, and IRIS does it.
Here, for example, IRIS spots the moment a bike or scooter crosses the gates, even with the rider still on it, and logs it with the time and the camera that caught it. That tells you how many times a day it happens and which gate sees the most. With that number you decide whether to add bike parking, mark the floor, or put someone on that gate, and next month you check if it dropped.
Works with the cameras you already have. Nothing to replace.
A person replies, not a form.
- Your footage never leaves your premises.
- It doesn't identify people.
- Certifications →
What IRIS understands
What it recognises in this scene
- bicycle
- scooter
- line of ticket gates
The rule
You decide once. IRIS applies it always.
If
a bicycle or a scooter crosses the line of ticket gates
And alsoit is a time band in which the station does not allow them
Then
- alert the concourse staff, who are the ones who speak to the passenger
- keep the clip in case there is a bump or a fall afterwards
- add it to the day's count, by gate and by hour
The instruction that set it up«Tell me if bikes or scooters come in through the gates, and how many go through each day.»
What changes
What changes for whoever runs the station
Quarter to eight, rush hour in the concourse, and a scooter crosses the line of gates with its rider still on it. What collides here is not a scooter and a wall: it is a scooter and a person with a suitcase who has not seen it. The station manager knows it happens, but when he has to decide where to put a bike rack, where to paint the floor or whether that entrance needs somebody standing there, he has no number: he has the feeling that “a lot of them get through”. With IRIS, after a month, he has how many come in, through which gate and at what time. You can make a decision with that; with a feeling, you cannot.
What people usually ask
Can it tell a scooter from a wheeled suitcase or a trolley?
Yes, they are different objects and they look different: the suitcase trails behind a person at hand height, while the scooter is underneath, with bigger wheels and sometimes with someone standing on it. In a station this matters because suitcases are half of what comes through that door: if the rule got it wrong there, it would alert a hundred times a day and nobody would leave it on. It is checked against the camera itself before being signed off.
Who decides whether they are allowed in?
The station, with its own rules — and often with different hours: allowed outside the rush hour, not allowed during it. IRIS has no opinion on that; you tell it which time band applies and it detects inside that band. If the rule changes tomorrow, you change the band and that is it: nothing else has to be touched.
Is it for fining people who come in with a scooter?
No, and it could not: IRIS identifies nobody and recognises no faces, so there is nobody to fine. What it sees is an object — a bike, a scooter — crossing a place. It is good for two useful things: letting somebody in the concourse walk over and have a word at the time, and letting the station know, after a few weeks, where and when it happens, so decisions are made with data instead of arguments over anecdotes.
Demo · IRIS at work
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.
- The alert fires
- You open it
- You confirm or dismiss
See it somewhere else
The school
Who sees the child who has fallen at the far end of the playground?
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 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
We would rather promise less.Let the first week be the surprise, not the brochure.
What it cannot do gets said on day one, not on the last day. A short list that holds beats a long one that falls apart the moment it is switched on.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.