CAM-209
A split pack emptying itself onto the belt
Mid-morning on a juice line. The bottles come out of the filler and swing left around the curve of the belt, all the same size and all filled to the same level. Inside the red circle there’s one that isn’t: it is deformed, split down the side and pouring juice out of it; the stream drops off the belt onto the floor, next to the sampling table. Four people are working around it without noticing.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognizes in this scene
- split pack leaking product
- juice falling off the belt
- bottles at the right level
- filling machine
- sampling table
What this camera measures
An alert says something’s happening. The reading says how much.
- 2Packs outside the normal in the last hour
- 20 sSince the pack went past
- 74Bottles in the watched stretch
- 09:38Time of the alert
- 4People in the frame
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 pack goes down the belt with its level or its shape outside the normal, or leaking product
Then
- alert the line operator with the camera, the time and the picture of the pack
- keep the video of the moment and the point on the belt where product spilled
- keep the alert open until somebody confirms it has been pulled and cleaned up
The instruction that set it up«Tell me if a pack goes past that is not like the others: empty, badly filled, dented or leaking.»
What changes
What changes for whoever answers for the plant
Four people working around it and not one sees it go by: at belt speed, an empty or badly filled container isn’t something the naked eye picks up. And it isn’t just one lost container. The juice wets the band, gets into the rollers, glues the floor and forces a clean-down of the whole stretch; and if nobody sees it, it keeps dripping for the rest of the batch. IRIS compares every container that passes with the ones beside it and alerts when one falls outside the normal: empty, underfilled, overfilled, dented, open or losing product.
What people usually ask
Does IRIS measure the millilitres in each bottle?
No. IRIS compares what it can see: the height of the liquid in one bottle against the ones beside it, and the shape of the pack against the shape it should have. That catches an empty, an underfill or a split pack. The exact volume comes from the line’s checkweigher or filling system. What the camera adds is that it looks at every bottle and flags them while they’re going past.
Does it still work when the line changes format?
Yes. The reference is the other packs of the same batch going down the belt, not a fixed template. When the line changes format, the reference changes with it. What does have to be defined is what counts as outside the normal on that line, and that’s the plant’s decision, not the camera’s.
Does it also pick up the spill on the floor?
Yes, if the spill is in the frame. IRIS sees liquid where the floor should be dry and treats it as what it is: a slip risk and a clean-up waiting to happen. It doesn’t know what the liquid is or whether it’s hazardous. It gives the time, the area and the video; what gets done about it is the plant’s decision.
Other cameras
- CAM-200 · The line has stopped and nobody knows why
- CAM-201 · Bottles piling up on the accumulation table
- CAM-202 · The line is running and not one bottle goes by
- CAM-203 · A glove on the belt, among the trays
- CAM-204 · A water bottle in the middle of a juice run
- CAM-205 · A label that says the opposite of what is in the bag
The real interface, step by step
Watch what happens. Then watch what IRIS does with it.
Not a recorded video and not a drawing: it’s a summary of the real tool, with a different case each time round. The whole tool doesn’t fit in a box.
- 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 doesn’t 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
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.