Skip to content
IRIS NEURALContact
Back to the car park

CAM-460

How many bays are left, and of what kind

Mid-morning on level 2 of a multi-storey car park. The whole deck is in shot: a blue accessible bay with a car on it, an occupied purple reserved bay, an orange row of motorcycle bays, two green charging bays with their posts, and one bay closed off with cones over red hatching. IRIS does not add entries and subtract exits: it looks at every bay and says whether a vehicle is on it.

Mid-morning on level 2 of a multi-storey car park. The whole deck is in shot: a blue accessible bay with a car on it, an occupied purple reserved bay, an orange row of motorcycle bays, two green charging bays with their posts, and one bay closed off with cones over red hatching. IRIS does not add entries and subtract exits: it looks at every bay and says whether a vehicle is on it.
CAM-460IRIS VisionLive

Turn on IRIS Vision

AI-generated image

CAM-460 · 4 ZONES · 50 BAYS · 24 h

What IRIS understands

What it recognises in this scene

  • bay closed off with cones
  • car on an accessible bay
  • car on a reserved bay
  • car on a charging bay
  • motorcycles on the two-wheeler bays
  • charging posts

What this camera gives back

Nobody gets an alert here. Here you get numbers.

  • 16 / 50Free bays right now
  • 2 / 6Charging bays free
  • 0 / 2Accessible bays free
  • 2 / 6Motorcycle bays free
  • 1Bays closed off
  • 09:30Time of the reading

The figures on this screen are an example from the illustration, not any client's measurement.

How the counting works

Counting is not something you ask for. You draw a line.

Over each group of bays there is a drawn zone: the blue accessible one, the purple reserved one, the motorcycle row and the green charging ones. Inside each zone IRIS looks bay by bay to see whether a vehicle is on it and for how long. Where each bay starts and ends does not fit in a sentence: it is drawn once over the frame and it stays there, so the nine o'clock reading and the seven o'clock one are measured the same way.

  • accessible bay zone · Dwell zone
  • reserved bay zone · Dwell zone
  • motorcycle bay zone · Dwell zone
  • charging bay zone · Dwell zone

And also, one rule

You decide once. IRIS applies it always.

If

only one free bay is left in the charging zone

Then

  1. update the count for that level and that bay type
  2. publish the number on the entrance sign and in the app
  3. save the reading with its timestamp so it can be checked later
The instruction that set it up«Tell me how many free bays are left on level 2 and how many of them are charging bays.»

What changes

What changes for whoever runs the car park

The manager cares about one thing: how many bays he can sell right now, and of what kind. If the number comes from counting entries and exits, the error piles up all day and by mid-afternoon nobody trusts it. Looking at the bays, the count squares again on every reading. And splitting the types changes decisions: if the charging bays fill up at nine and the motorcycle ones go spare, next year they get painted differently.

What people usually ask

Does IRIS read the number plate to know whether a bay is taken?

No. No number plate is read here. IRIS looks at the bay and sees whether a vehicle is on it or not, just as a person leaning over the railing would. That is where the count by level, by zone and by bay type comes from. If at some point you need to know whether that vehicle had authorisation, the car park system answers that, not the camera.

How is this different from a sensor on every bay?

In the coverage and in what it leaves behind. A sensor says taken or free; a camera covers many bays at once and leaves the image too, so you can check why the number says what it says. And it tells bay types apart: accessible, charging, reserved or motorcycle. The two systems live together fine; what does not work is trusting everything to entries minus exits.

Is the number that comes out here certified?

No. The approval we hold from the Spanish Centre of Metrology covers people counting, and what is counted here is bays and vehicles. The count is repeatable and auditable because the zones are drawn and do not move, and because the image and the timestamp remain, but it cannot be called certified.

The real interface, step by step

A camera looks. IRIS understands what it sees.

An extract of the real screen, no voice-over and hands-free. Each round poses another situation. What sits behind it is a good deal bigger than what you see.

  1. Four cameras at once
  2. Each understands its own view
  3. The numbers climb by themselves
IRIS NEURAL
30ES
IRISDirectoGrabacionesGISIncidencias3996SituaciónCasosLPRAutomatizacionesIRIS DATA
Ask a question or make a request…Send
IRIS · Infinity Neural

And the best part

Finding something in yesterday’s videoshould take as long as asking for it.

No more scrubbing back through six hours with your finger on the mouse. You type what you are after, in plain words, and the matching moments come up. Same cameras as always.

Tell us your problem and we will say whether IRIS understands it, or not yet.

We reply the same working day.