Skip to content
IRIS NEURALContact

The city

CAM-44

Horse-drawn carriages in the old town

The same old-town street, with a two-horse carriage coming down the road. Three people are aboard: the driver on the box and two passengers on the rear seat. A car follows behind and another is parked against the opposite curb. Nothing is happening: the street is working, and what’s needed is the figure.

The same old-town street, with a two-horse carriage coming down the road. Three people are aboard: the driver on the box and two passengers on the rear seat. A car follows behind and another is parked against the opposite curb. Nothing is happening: the street is working, and what’s needed is the figure.
CAM-44IRIS VisionLive

Turn on IRIS Vision

AI-generated image

CAM-44 · 1 LINE · 1 ZONE · 24 h

What IRIS understands

What it recognizes in this scene

  • harnessed horses
  • carriage
  • people on board
  • car
  • parked car

What this camera gives back

Nobody gets an alert here. Here you get numbers.

  • 38+6%Carriages today
  • 18:00 – 19:00Busiest time slot
  • 8Crossings in that slot
  • 09:00 – 20:00Hours with activity
  • 2Horses harnessed
  • 3People on board

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.

Crossings by time slot

  • Carriages
Crossings by time slot
SlotCarriages
060
084
107
126
143
164
188
206
220

Crossings by day of the week

  • Carriages
Crossings by day of the week
SlotCarriages
Mon22
Tue19
Wed24
Thu26
Fri38
Sat61
Sun54

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.

There’s a line drawn from curb to curb, across the direction of travel, and an area over that stretch of road. Every carriage that crosses the line is added up, and the direction of the line says whether it’s coming down or going up; the area measures how long it takes to cross the stretch and whether it stops inside. This isn’t asked for in words: counting needs to know exactly where the line runs and which way, and a line can’t be described in a sentence — it has to be drawn onto the frame. Asking is for searching and describing; counting is set up by drawing. That’s why the figure is repeatable and auditable: the line is where it was last year.

  • counting line · Counting line
  • road stretch · Dwell zone

What changes

What changes for whoever runs the city

In many cities horse-drawn carriages are a regulated trade: there’s a cap on licenses and a set of permitted hours. Today that’s enforced by putting an inspector on a corner with a notebook, for a while, one day. With the line drawn, the city knows how many carriages go past, at what times and on which days, all year and with nobody on the corner. And there’s a second reading, the one that ends up in the city meeting: animal welfare. Which part of the day the work happens, how many carriages are out at once and how many hours in a row there’s activity are figures nobody has today, and they’re exactly the ones campaign groups ask for. IRIS provides the number. The decision — how many licenses, what hours, which months — is political, and a camera doesn’t make it.

What people usually ask

Can IRIS tell me how many hours in a row one carriage has been working?

No. IRIS counts carriages crossing a line. It does not know which is which, it does not identify any particular carriage or its driver, and it cannot say “this one has been out for six hours.” What it can say is how many have gone past and at what time: how many crossings per time slot, when in the day they cluster, how many days of the week and from what hour to what hour there is activity in that street. That shows the pattern of the whole trade, which is what gets debated in a board meeting, without following anyone in particular. If somebody needs the history of one specific carriage, that doesn’t come from a camera: it comes from the license register.

What use is counting horse-drawn carriages to a the city?

For two things, and both come up every year. The first is enforcement: if there’s a cap on licenses and a set of permitted hours, somebody has to be able to check that the street matches that, and today it is checked by an inspector on a corner for a while. The second is animal welfare: which part of the day the work happens, how many carriages are out at once and how many hours in a row there’s activity. Nobody has those figures today and they’re the ones asked for in every debate. IRIS puts them on the table without taking sides: it counts crossings of a line, every day and at the same hours, which is why this year’s figure can be compared with last year’s. What’s done with it is decided by whoever has to decide it.

Isn’t it enough to tell IRIS “count the carriages”?

No, and the difference is what separates the two halves of the product. Asking is for searching and for describing a situation: that’s done by talking. Counting needs to know exactly where the line runs and which way, and a line can’t be described in a sentence — it has to be drawn onto the image. “Count the carriages in this street” doesn’t say whether to count the ones coming down, the ones going up or both, nor where the street begins. That’s why counting is set up by drawing: the line stays put, the same thing is measured every time, and the figure is repeatable and auditable a year later. Asking is for searching. Counting is for measuring. And they aren’t done the same way.

A different case every time

No extra alarms here. Just what needs looking at.

Not a recorded video, not an explanatory drawing: a summary of the real screen, with a different case every time it starts. There’s a lot more behind it.

  1. Finds the plate
  2. Reads the characters
  3. Follows the same plate
IRIS NEURAL
30ES
IRISDirectoGrabacionesGISIncidencias3996SituaciónCasosLPRAutomatizacionesIRIS DATA
Ask a question or make a request…Send
IRIS · Infinity Neural

And the best part

You can add more cameras;you can’t add more hours to anyone’s day.

Cameras can be multiplied; a person’s hours can’t. IRIS looks at everything coming in and leaves them the one thing no machine does better: deciding what to do.

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

A person answers, the same working day.