Skip to content
IRIS NEURALContact

IndustryProduction efficiency

CAM-239

A cart of modules leaves through a door that isn’t its own

Night shift in the electronic module stockroom. Two operators are pushing carts loaded with gray trays. One is going down the central aisle, over the yellow arrow that marks the route. The other has reached a side door beside the pillar and is taking the cart through it. That door isn’t part of the path painted on the floor. IRIS sees that a loaded cart has left the frame somewhere carts don’t leave.

Night shift in the electronic module stockroom. Two operators are pushing carts loaded with gray trays. One is going down the central aisle, over the yellow arrow that marks the route. The other has reached a side door beside the pillar and is taking the cart through it. That door isn’t part of the path painted on the floor. IRIS sees that a loaded cart has left the frame somewhere carts don’t leave.
CAM-239IRIS VisionLive

Turn on IRIS Vision

AI-generated image

CAM-239 · MODULE STORE · OFF-ROUTE EXIT

What IRIS understands

What it recognizes in this scene

  • module cart at the side door
  • side door off the route
  • operator pushing the cart through the door
  • cart on the marked aisle
  • route arrow painted on the floor

What this camera measures

An alert says something’s happening. The reading says how much.

  • 4Trays on the cart
  • 2Carts in frame
  • 40 sTime off the marked route
  • 2People in frame
  • 22:41Time of the alert

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

The rule

You decide once. IRIS applies it always.

If

a loaded cart crosses an exit that is not on the marked route

Then

  1. alert the stockroom supervisor with the camera and the time
  2. save the video from the moment the cart came into frame
  3. log the movement so that a person can review it
The instruction that set it up«Tell me if a loaded cart leaves the stockroom through a door that is not on its route.»

What changes

What changes for whoever answers for the plant

The electronic modules of a car fit in a box and are worth a lot of money. When a cart goes missing, the inventory count finds out weeks later and by then there’s no footage left to look at. IRIS doesn’t say this is a theft and doesn’t know whether anybody had permission: it says a loaded cart went through that door at 10:41 p.m., with the video attached. From there the stockroom supervisor opens it and decides in a minute whether it was a shortcut, a rush order or something to look into.

What people usually ask

Does IRIS say this is a theft?

No, and it can’t. IRIS sees that a loaded cart went out through a door that isn’t on its route, at a specific time. It could be a shortcut, an urgent call from another line or a wrong turn. Who was pushing it and why is decided by a person with the video in front of them. The system identifies nobody and judges no intentions.

Does IRIS recognize the operators pushing the carts?

No. IRIS does not recognize faces and stores nobody’s identity. It detects situations: “a loaded cart has crossed this door,” with the camera and the time. If the plant needs to know who was on shift, that comes from its own records, not from the video system. The rule is written about the cart and the door, never about a particular person.

Can you count how many carts go out through each door?

Yes, and it’s a different thing from the alert. Asking is for finding; counting is for measuring, and they aren’t done the same way: a counting line can’t be described in a sentence, it has to be drawn on the image. With a line drawn at each door, the stockroom gets a number per shift and per day that can be repeated and checked. The alert tells you it happened; the count tells you how many times.

Demo · IRIS at work

Everything comes in. Only what matters gets through.

This sums up what IRIS does with one alert, from the moment it appears until it’s closed. The real screen holds far more; this is the main thread.

  1. Checks the whole system
  2. Flags what is failing
  3. Puts it on one screen
IRIS NEURAL
30ES
IRISDirectoGrabacionesGISIncidencias3996SituaciónCasosLPRAutomatizacionesIRIS DATA
Ask a question or make a request…Send
IRIS · Infinity Neural

And the best part

What happens outside the framedoesn’t exist for IRIS. No camera sees the whole world.

So the first thing we do is check what each camera covers and write it down: from here you can understand this, and not that. A dull hour that saves a lot of misunderstandings.

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

A person answers, the same working day.