Skip to content
IRIS NEURALContact
Back to industry

CAM-429

A man on foot between three machines that cannot see him

Quarter past nine in the morning on the tipping floor. A worker in helmet and hi-vis crosses the yard on foot, outside the walkway marked in yellow. To his left a wheel loader advances with a full bucket; ahead, a grab excavator swings with a loaded claw; to his right a truck is emptying its body. From none of the three cabs can he be seen in full. IRIS sees a person on foot inside the manoeuvring area.

Quarter past nine in the morning on the tipping floor. A worker in helmet and hi-vis crosses the yard on foot, outside the walkway marked in yellow. To his left a wheel loader advances with a full bucket; ahead, a grab excavator swings with a loaded claw; to his right a truck is emptying its body. From none of the three cabs can he be seen in full. IRIS sees a person on foot inside the manoeuvring area.
CAM-429IRIS VisionLive

Turn on IRIS Vision

AI-generated image

CAM-429 · TIPPING FLOOR · PERSON IN MACHINE ZONE

What IRIS understands

What it recognises in this scene

  • person on foot in the manoeuvring area
  • wheel loader with a full bucket
  • grab excavator swinging round
  • refuse truck emptying its body
  • covered tipping bays

What this camera measures

An alert says something is happening. The reading says how much.

  • 1people on foot
  • 3machines moving
  • 35 stime inside the area
  • 2crossings on foot this shift
  • 09:14time 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 person on foot enters the manoeuvring area while machinery is moving

Then

  1. alert the cab and the yard supervisor
  2. save the video with the camera and the time
  3. add the crossing to the shift count
The instruction that set it up«Alert me if there is a person on foot on the tipping floor while the machinery is working.»

What changes

What changes for whoever answers for the plant

There is no margin here: a loader that swings does not stop in time. Hi-vis is visible from a distance, but from the cab there is a blind spot behind and to the sides, and that is exactly where the worker is. An alert at that same moment reaches the cab and the yard supervisor, and buys the seconds needed to stop. At the end of the shift there is also the count of how many times it happened, and that is what says whether the walkway is where it should be.

What people usually ask

Does IRIS tell the worker on foot from the one in the cab?

Yes. It sees the person walking across the yard and it sees the machine as a machine; the operator inside the cab does not count as a person on foot. That difference is what separates a useful alert from an alarm every two minutes, and an alarm every two minutes ends up being ignored. What IRIS does not do is say who that person is: it does not recognise faces.

Is it useful for knowing whether the walkway is in the right place?

Yes, by counting. Beyond the alert, you can draw the area and count how many times it is crossed on foot over the shift and over the day. That figure says whether people avoid the marked walkway and where they actually go. With it, a barrier gets moved or a line repainted with a number on the table, not with somebody's impression.

Can IRIS stop the loader?

No. IRIS alerts; stopping the machine is the operator's or the supervisor's decision. The alert arrives with the image of what is happening and the exact spot on the yard, and that is what allows a fast, sound decision. Who acts, how and in what order is defined by the plant in its own procedure; IRIS does not act on its own and does not predict what is about to happen.

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 is closed. The real screen holds far more; this is the main thread.

  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

If the camera does not show it,IRIS does not see it. We say so up front, not afterwards.

No camera sees through a wall or in complete darkness. We would rather show you where the limit is, and place what you have well, than promise something that never appears on screen.

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

We reply the same working day.