CAM-397
A person sunk into the material inside the silo
Looking down into the mouth of the silo. Inside, the bulk material forms a cone and a person in a hi-vis vest and white helmet is lying on it, sunk from the waist down. The conveyor above keeps pouring material onto the same spot. The walkway access door is open and there is a burial hazard sign on the silo wall. There is nobody on the walkway. IRIS sees a person on top of the material.
Turn on IRIS Vision
AI-generated image
What IRIS is
IRIS watches the plant for you.
IRIS looks at the cameras you already have on the plant floor and understands what it sees: a stopped line, someone inside a robotic cell, someone without their safety gear on, jammed parts. When something like that happens, it alerts right away; and whatever can be counted, it counts in numbers. All day long, with no one needing to watch the screen.
You tell it what you need to watch, and IRIS does it.
Here, for example, IRIS sees the person sinking into the material inside the silo and raises the alert straight away, with the time and whether the conveyor above is still pouring material. So the control room finds out the moment it happens, not because a colleague notices someone is missing. With that alert they decide whether to stop the feed and which door to send the rescue through.
Works with the cameras you already have. Nothing to replace.
A person replies, not a form.
- Your footage never leaves your premises.
- It doesn't identify people.
- Certifications →
What IRIS understands
What it recognises in this scene
- person sunk into the material
- bulk material inside the silo
- feed pouring material in
- access door left open
- burial hazard sign
What this camera measures
An alert says something is happening. The reading says how much.
- 1People inside the silo
- 0People keeping watch outside
- 2 minTime since entry
- 2 minTime with the feed running
- 6 minTime with the door open
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
there is a person on top of the bulk material inside the silo
Then
- alert the control room and the rescue team with the camera and the time
- save the video from the moment the access door was opened
- count how many people are left outside, on the walkway
The instruction that set it up«Tell me right away if anyone climbs onto or falls onto the material inside the silo, and tell me whether anyone is keeping watch outside.»
What changes
What changes for whoever answers for the plant
Being buried in bulk material is resolved in minutes or it is not resolved at all. What usually happens is that nobody knows until a workmate misses someone. With the camera, the control room gets the alert while it is happening: a person on the material, the time, whether the feed is still running and how many people are keeping watch outside. With that, the rescue heads for the right door instead of searching the plant.
What people usually ask
Does IRIS stop the silo feed when it sees someone inside?
No. IRIS does not act on any machine: it warns. The alert reaches the control room with the image, the time and whether the feed is still running. Stopping the equipment, cutting the supply and calling the rescue team is decided and done by a person, following the plant's procedure. What the camera adds is that somebody knows straight away, instead of when a workmate is missed.
What if the person went in with a work permit?
It warns then too, and that is the point. The plant writes the rule: it can require an attendant on the walkway, the feed locked out and the entry inside an authorised window. If any of those conditions is missing, the camera says so with the image. An entry with a permit but with nobody watching is as dangerous as an entry with no permit at all.
Does it recognise who went into the silo?
No. IRIS does not identify anyone and does not compare faces against any database. It sees a person on bulk material inside the silo, at what time and through which door they came in. Who that is, is settled by the shift supervisor with the video in front of them and the work permit log. What reaches the alert is a situation, not a name.
Other cameras
- CAM-380 · A loaded truck leaves by a way that is not a way out
- CAM-381 · Dark material going into the bay for pale aggregate
- 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
See it for yourself
This isn’t a video. It’s a slice of the real screen.
A summary of the real interface, played hands-free. You see one case from start to finish; what you do not see are the other screens, and there are many.
- The hour, as a grid
- You look where it's dark
- You jump to that minute
See it somewhere else
Who watches a whole station at rush hour?
17 cases: 11 raise an alert when something happens and 6 only measure. You see each image as it is, and then with what IRIS understands on top.
Who sees the sales that never reach the till?
10 cases: 4 raise an alert when something happens and 6 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
Video is late by definition:you watch it once the thing has already happened.
IRIS tells you while it is happening, with the camera, the time and what it saw. Arriving in time changes the end of almost any story, and no new cameras are needed for that.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.