CAM-97
Station parking lot
The station parking lot in mid-morning, seen from the light pole at the entrance: rows of cars almost full, the entry barrier at the back and two cars sitting across the line, taking up two spaces each.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognizes in this scene
- badly parked
- parking rows
- barrier
What this camera gives back
Nobody gets an alert here. Here you get numbers.
- 78%Occupancy
- 42Free spaces
- 5Badly parked
- 4 h 20 minAverage stay
- 09:00Peak hour
- 520Total today
The figures on this screen are an example from the illustration, not any client’s measurement.
The series, not one figure
One number says nothing. A curve does.
Occupancy by time slot
- Occupancy
| Slot | Occupancy |
|---|---|
| 06 | 22% |
| 08 | 78% |
| 10 | 86% |
| 12 | 84% |
| 14 | 82% |
| 16 | 80% |
| 18 | 61% |
| 20 | 38% |
| 22 | 19% |
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.
An area is painted over the rows of spaces. Inside it IRIS looks at two things: how many spaces have a car on them and how long each car has been in its own. A car sitting half in one space and half in the next is flagged separately, because it takes two and pays for one. Where the rows are and where each space ends can’t be written in a sentence: it has to be painted onto the image, once, and from then on the figure repeats the same way every month. And a warning about the screen: the 78% occupancy you see here’s an example from the illustration, not any client’s measurement.
- parking lot zone · Dwell zone
What changes
What changes for whoever runs the station
A station parking lot is two businesses sharing the same ground, and almost nobody knows how much of each there is. One is the person who leaves the car at seven and picks it up at eight in the evening because they took the train: one space, the whole day. The other pulls in for twenty minutes to drop somebody off. With the area in place, the manager sees the real mix by time band and knows whether spaces are genuinely short or whether it’s turnover near the entrance that’s missing. With that he sets tariffs, decides where the short-stay zone goes and whether an extension is needed at all. And badly parked cars stop being an anecdote people tell: they become a number tracked month by month.
What people usually ask
Does IRIS read the license plates in the parking lot?
No, this camera doesn’t read plates: it measures the space, not the car. The clock starts when a space becomes occupied and stops when it frees up, and that alone gives the average stay without knowing whose vehicle it is. It’s the simplest way to answer the question that matters — how many park all day and how many for twenty minutes — and the one that needs the least data. If a particular site needed plate reading for access control, that’s a different system and a different conversation: it is agreed in writing beforehand, with its purpose and its retention period.
What does IRIS count as a badly parked car?
Badly parked means whatever the drawn rule says it means, no more and no less. Because the spaces are painted onto the image, IRIS knows where each one ends: a car straddling two spaces, or standing outside any space but inside the area, gets flagged. There’s no opinion and no intent in it: there’s a geometry and a vehicle on top of it. That makes it arguable in the good sense — you can show the illustration and see why that figure came out — and it makes it comparable, because the line around the space is the same in January as in August.
Does this work at night or in a covered parking lot?
It works if there’s enough light and the camera doesn’t move, and both conditions are checked on site before installing. At night, with a parking lot’s normal lighting, occupancy measures well because a parked car is a large, still object; what degrades first is telling a badly parked car when shadow covers the line on the ground. Under cover there’s less light and more pillars in the way, so where the camera goes matters a great deal and sometimes two are needed. If a particular parking lot isn’t good enough to measure with confidence, we say so before rather than after, and any figure published carries that condition stated.
A different case every time
We won’t just tell you. We’ll show you.
It’s a summary of the real screen: it plays by itself, step by step, and shows only the path of one case. The actual tool has far more than fits in here.
- You ask
- IRIS searches
- It shows you
Next step
How many spaces are open right now?
15 cases: 9 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.
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.
And the best part
Nobody covers the night shift:the camera that is already on covers it.
It doesn’t tire, it doesn’t blink and it doesn’t go for coffee. What happens at night is understood just as it would be at midday, and whoever is on duty hears about it while it’s happening.
Tell us your problem and we’ll say whether IRIS understands it, or not yet.
A person answers, the same working day.