CAM-93
Bus stop: who boards and who doesn’t
A sheltered bus stop late in the afternoon: about thirty people waiting on the sidewalk and a bus that has just pulled in with its door open. IRIS counts how many are waiting and how many board; it does not know who any of them are.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognizes in this scene
- line
- bus
- shelter
What this camera gives back
Nobody gets an alert here. Here you get numbers.
- 34Waiting
- 21Boarded
- 4 minAverage wait
- 18:00 – 19:00Peak hour
- 2.860Total today
- 13Left behind
The figures on this screen are an example from the illustration, not any client’s measurement.
IRIS incorporates NeuralPax, a separate license approved by the Centro Español de Metrología — Spain’s national metrology institute — for people counting, occupancy and crowd-flow control. That the figure is right is guaranteed by a third party, not by us: the occupancy figure you show is measured and approved, not estimated. The approval covers that measurement — counting people — not the whole product. That approval is Spanish and it isn’t equivalent to any U.S. certification: we say so up front and not at the end.
The series, not one figure
One number says nothing. A curve does.
Waiting and people left behind
- Waiting
- Left behind
| Slot | Waiting | Left behind |
|---|---|---|
| 06 | 18 | 0 |
| 08 | 62 | 13 |
| 10 | 34 | 2 |
| 12 | 28 | 0 |
| 14 | 31 | 1 |
| 16 | 36 | 2 |
| 18 | 74 | 17 |
| 20 | 41 | 3 |
| 22 | 15 | 0 |
The figures on this screen are an example from the illustration, not any client’s measurement.
How the counting works
Counting isn’t something you ask for. You draw a line.
The line sits right at the bus door: everyone who crosses it inward is added to those who have boarded. The painted area covers the shelter and the stretch of sidewalk where people wait, and measures how many are there and since when. When the bus pulls away, whoever is still inside the area is whoever was left behind. That remainder can’t be asked for in a sentence: it comes from subtracting a line from an area, and for that you have to draw both onto the frame.
- boarding line · Counting line
- stop zone · Dwell zone
What changes
What changes for whoever runs the station
How many people get on a bus is already known: the ticket machine counts it. What nobody knows is how many stay at the stop watching a full bus leave, because whoever doesn’t board validates nothing and appears in no system. With the line and the area in place, that number finally exists: thirteen people at six thirty, and not one odd Tuesday but every Tuesday. With that the route manager asks for an extra service at that hour, or splits the frequency differently, and asks for it with a month of data in front of him instead of a complaint in the inbox. And if the extra service is put on, the same camera says whether it worked.
What people usually ask
How does IRIS know somebody was left behind?
IRIS knows it by subtraction. It counts how many people are in the stop area before the bus arrives, how many cross the door line, and how many are still inside the area when the bus leaves: that difference is the people who didn’t board. There’s an honest caveat worth stating: at a stop served by several routes, some of those people were waiting for something else. That’s why the figure is read by time band and compared with itself — if it spikes exactly on the peak-hour departures, it’s capacity, not coincidence — and at multi-route stops it is adjusted against the schedule before it is taken as good.
Does IRIS recognize the people who take the bus every day?
No, IRIS recognizes nobody — not the person who takes the bus every day, nor the one who takes it once a year. It doesn’t read faces, it doesn’t compare against any database, it doesn’t cross the count with travel cards and it keeps no record of anyone. It counts bodies crossing a line and bodies inside an area, and that’s all this camera produces. If someone wanted to know tomorrow who waits at that stop, this system would be no use to them: it isn’t built for that.
Is this figure enough to justify running more buses?
Yes, that’s exactly what this figure is for, and it’s its whole reason to exist. A frequency is changed on the back of two things: how many people board and how many are left behind. The operator already has the first; nobody had the second until the area is drawn. With both series together, by day of the week and by time band, you can see whether the problem is capacity, punctuality or how the routes are split, and you see it with numbers that can be repeated next month. What this figure doesn’t do is decide for anyone: it puts the number on the table so the decision is taken while looking at it.
See it for yourself
A new case each time. Always the same screen.
It plays by itself and shows one case from start to finish. It’s a summary: the real screen has far more functions than fit in this box.
- The rule gets built
- It goes to every camera
- Published, it watches alone
- And then it fires
Next step
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.
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
A wall of monitors is impressive.Nobody can read forty tiles at once.
The more tiles there are, the less each one gets looked at. IRIS watches all four thousand cameras at once and points at a single one: the one that needs someone right now.
Tell us your problem and we’ll say whether IRIS understands it, or not yet.
A person answers, the same working day.