Skip to content
IRIS NEURALContact

Public safetyIntrusion detection

CAM-566

A truck tipping rubble on waste ground, in broad daylight

A patch of bare ground between an industrial park and the first houses, in full daylight. A dump truck has its bed raised and has just emptied a pile of rubble; beside it, a white van with both rear doors open and somebody unloading from inside. Another person stands by the truck, watching. On the ground there are drums, black bags, a large builder’s sack and material spread across the whole plot. They came in along a dirt track. IRIS doesn’t say who those people are or where the material comes from: it says two vehicles are stopped off the road and cargo is coming out of them, and at what time.

A patch of bare ground between an industrial park and the first houses, in full daylight. A dump truck has its bed raised and has just emptied a pile of rubble; beside it, a white van with both rear doors open and somebody unloading from inside. Another person stands by the truck, watching. On the ground there are drums, black bags, a large builder’s sack and material spread across the whole plot. They came in along a dirt track. IRIS doesn’t say who those people are or where the material comes from: it says two vehicles are stopped off the road and cargo is coming out of them, and at what time.
CAM-566IRIS VisionLive

Turn on IRIS Vision

AI-generated image

CAM-566 · 1 ROI · 2 MIN

What IRIS understands

What it recognizes in this scene

  • dump truck with the bed raised
  • van with its doors open
  • person unloading from the van
  • person standing by the truck
  • pile of rubble just tipped
  • drums and bags on the ground
  • large builder’s sack
  • material spread across the plot
  • dirt track they came in by
  • industrial park and houses in the background

The rule

You decide once. IRIS applies it always.

If

a vehicle stops off the road and cargo comes out of it

Duringit is on the plot and not at a collection point

Then

  1. alert the city crew with the exact spot and the time
  2. save the whole video of the unloading, start to finish
  3. attach the sequence to the case file, for whoever has to decide
The instruction that set it up«Tell me if a vehicle stops off the road on the waste ground and starts unloading.»

What changes

What changes for whoever goes out, whoever decides and whoever justifies it later

Twenty past eleven on a Tuesday. The dump truck has its body raised and the van beside it’s still unloading: in six minutes they’ll be gone. Fly-tipping on waste ground is almost always discovered when it’s already a heap, and by then there’s no way of knowing when it was left or where they came in. With this camera there’s a time, a place and a video, which is exactly what the inspector with the authority to draw up a report needs. And there’s something worth even more: clearing it costs public money, and that money is recovered when you can establish who left it. Without that, the town pays. Here IRIS establishes nothing on its own: it hands over the sequence, and a person draws the conclusion.

What people usually ask

Isn’t this accusing somebody of a crime?

No, and that difference is the whole point of this camera. The alert says: two vehicles stopped off the road, cargo coming out, at this time, at this spot. It doesn’t say it’s illegal, doesn’t say whose the material is and calls nobody anything. It could be permitted works, an authorized storage or fly-tipping. Telling those apart is a person’s job, with the recording in front of them and the rules that govern it. IRIS contributes the fact and the time; the legal characterization isn’t made by a camera.

Can any patch of waste ground in the town be watched like this?

A camera can be put where there’s a legal basis for it and where somebody has decided it is needed, and that decision isn’t ours. What we do state is what the camera does and doesn’t do: it sees vehicles and objects moving on a surface, and alerts on one specific pattern. It does not watch who walks down the street, does not follow anybody and does not tell neighborhoods apart. A plot with repeated fly-tipping is a place, not a group of people.

How does it tell fly-tipping from works that are operating there?

By the shape of the event, not by who is doing it: works have fencing, signage and continuous activity for weeks, while fly-tipping is a vehicle that comes in, unloads in a few minutes and leaves. That difference is described in words — “tell me if a vehicle comes in, unloads and leaves in under fifteen minutes” — and adjusted when needed. Even so, the last word on what that was belongs to a person looking at the video. The camera doesn’t decide.

Demo · IRIS at work

You set the rule once. IRIS applies it every time.

You will see a summary of the interface, played step by step and hands-free. Each round starts with another case. The complete tool doesn’t fit in a demo.

  1. The rule gets built
  2. It goes to every camera
  3. Published, it watches alone
  4. And then it fires
IRIS NEURAL
30ES
IRISDirectoGrabacionesGISIncidencias3996SituaciónCasosLPRAutomatizacionesIRIS DATA
Ask a question or make a request…Send
IRIS · Infinity Neural

And the best part

You can ask which van came in yesterday.Who was inside isn’t a question you ask here.

IRIS searches for things and situations, not people: it identifies nobody and recognizes no faces. You write what you’re looking for and it returns the matching minutes.

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

A person answers, the same working day.