CAM-222
A red mirror on a silver body
Assembly station, mid-afternoon. A red mirror is already fitted to the flank of the silver body shell. On the trolley alongside, the container mixes red and silver housings in the same compartments. An operator in a white helmet points at the mirror with her arm out; beside her, two colleagues look on. IRIS sees the colour and the position of the fitted part and compares them with what that body calls for.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- red mirror fitted to a silver body
- container mixing red and silver housings
- silver body shell at the station
- operator pointing at the mirror
- operator standing in front of the station
- operator beside the parts trolley
What this camera measures
An alert says something is happening. The reading says how much.
- 12Housings counted in the container
- 4Red housings in the container
- 3People in shot
- 2 min 15 sTime the body has been at the station
- 14:05Time it was fitted
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 colour or the side of the fitted part does not match what was expected
Then
- alert the station with the station number, the time and the image of the fitted part
- save the video of that part being fitted
- record which container the housing was taken from
The instruction that set it up«Tell me when the mirror fitted is not the colour or the side that body shell calls for.»
What changes
What changes for whoever answers for the plant
A mirror in the wrong colour turns up at the end, once the car has left the line, and taking it off costs more than the mirror itself. With the camera the alert comes out at the station, with the image of the fitted part and the time. It also records that the container had two colours mixed in the same compartment, which is where the mistake starts. Tidying the trolley is the plant’s call.
What people usually ask
Can a camera tell a left-hand part from a right-hand one?
Yes, when the difference is visible: the shape, the orientation and the point where it is fitted. What it cannot see is a part number moulded into dark plastic ten metres away. That is why the camera goes at the fitting point, and where the information exists only on a label, the label is what gets read. Better decided before installing, not after.
Does IRIS get it right with two very similar colours?
With red on silver, yes: that is a big, stable difference at any hour. With two very close greys, under different lighting and with reflections, the image stops being reliable evidence and the colour check belongs to the quality system. This gets said before the camera goes up, because it decides where it is worth it and where it is not.
Does IRIS identify the person who fitted the part?
No. IRIS does not recognise faces and does not compare them with anything. What it detects is a situation: at this station and at this time a part was fitted that does not belong. Who was at the post is known from the plant’s own shift record, not from the camera, and that separation is deliberate.
Other cameras
- CAM-220 · Three people standing idle in front of a body shell
- CAM-221 · A side frame that does not belong to this body
- CAM-223 · A fixing point left empty
- CAM-224 · The tool never reached one of the points
- CAM-225 · A connector left unmated on the line
- CAM-226 · The seat on the trolley is not the one for this unit
The real interface, step by step
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
- It lands in the tray
- You open it
- You confirm or dismiss
Next step
How many bays are free right now?
15 cases: 9 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.
What does a venue with twenty thousand people inside see?
15 cases: 11 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.
And the best part
Stop scrubbing through six hours.Ask what happened and watch only that.
You type what you are looking for in plain words — a white van, a door left open — and the moments it appears come back. What used to take an afternoon now takes minutes.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.