CAM-381
Dark material going into the bay for pale aggregate
Mid-morning at the sorting yard. A yellow wheel loader raises its bucket and tips a load of dark, earthy material into the bay for sand and pale aggregate. The material cascades over the sand and stays on top, plainly visible. The neighbouring bays hold scrap metal, brown gravel and white limestone boulders, each with its pictogram fixed to the wall. IRIS sees that what is going in does not look like what is already there.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- dark material going into the bay
- wheel loader tipping
- bay for sand and pale aggregate
- bay class sign
- next bay, limestone boulders
What this camera measures
An alert says something is happening. The reading says how much.
- 10:14Time of the tip
- 9Tips into this bay today
- 2Tips flagged for checking today
- 5Bays watched in the yard
- 25 sTime since tipping started
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
the material being tipped does not match the look of the bay class
Then
- alert the yard supervisor with the camera, the bay and the time
- save the video of the bucket from lifting to emptying
- flag the bay for checking and log the tip in the shift report
The instruction that set it up«Tell me if a loader tips material into a bay that does not look like what is already in it.»
What changes
What changes for whoever answers for the plant
A contaminated bay is not found at tipping: it is found at the plant, when the product is already mixed and the whole lot has to be pulled out or sold for less. With the camera, the yard supervisor gets the alert while the bucket is still up: the machine, the bay, the time and the video of the tip. Taking out one fresh bucketload costs five minutes; emptying a whole bay costs a day.
What people usually ask
Does IRIS know which mineral it is?
No, and this is the limit to be clear about. IRIS tells materials apart by appearance: colour, shape, particle size, which stockpile the load came from and which bay it ends up in. That is enough to see that what is going in does not look like what is already there, and to raise the alert. The grade of the ore, the metal content, the silica, the moisture, comes from the laboratory, and no camera replaces it. What the image does is get the sample taken sooner.
And if two materials look very much alike?
Then the camera does not separate them, and that has to be said. Two aggregates of the same colour and the same size cannot be told apart in an image. What can always be seen is where the load came from and where it ended up: if the loader filled at the waste stockpile and tipped into the aggregate bay, that is a solid detection even when the two materials look alike. The path of the bucket counts as much as the appearance.
Who decides what counts as a wrongly classified tip?
The plant does. IRIS does not write the rules: the yard decides which class goes in each bay, which combinations are tolerated and which are not. Some aggregates take a little fines; some bays hold certified product where nothing else may go. That list is set by whoever answers for the product, and the camera only checks what it has been asked to check. If a bay changes use tomorrow, the rule changes, not the system.
Other cameras
- CAM-380 · A loaded truck leaves by a way that is not a way out
- CAM-382 · Good ore heading for the waste dump
- CAM-383 · A bucket of grey gravel on top of the wrong stockpile
- CAM-384 · A boulder too big for the crusher mouth going in anyway
- CAM-385 · A tanker loading under the wrong silo
- CAM-386 · A loaded truck slipping past the weighbridge
See it for yourself
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 is a lot more behind it.
- The alert fires
- You open it
- You confirm or dismiss
Next step
What can a camera see without pointing at anyone?
13 cases: 9 raise an alert when something happens and 4 only measure. You see each image as it is, and then with what IRIS understands on top.
What if the outage does not start with an attack?
13 cases, and in every one of them IRIS raises an alert when something happens. You see each image as it is, and then with what it understands on top.
And the best part
Behind one camera you can put a person.Behind four thousand you cannot put anyone.
Adding a camera costs little; adding another pair of eyes does not. So the cameras keep growing and the attention does not. IRIS watches all four thousand at once and flags what matters today.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.