CAM-220
Three people standing idle in front of a body shell
Mid-morning on the assembly line. A silver body shell sits still on its skid with the bonnet up. In front of it an operator in a white helmet and hi-vis waits with his hands on his hips. Another, beside the parts trolley, has a hand on his chin. A third, by the rail, has his arms crossed. The robots behind them are not moving. IRIS sees that the body is not advancing and starts timing from the first second.

Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- operator waiting with his hands on his hips
- body shell stopped on the skid
- operator with his arms crossed by the rail
- operator waiting beside the parts trolley
- station signal light on
- next body shell held up on the line
What this camera measures
An alert says something is happening. The reading says how much.
- 6 min 10 sTime stopped
- 5People waiting in shot
- 2Body shells stopped on the run
- 4Stops counted this shift
- 10:37Time of the stop
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 body shell has been stopped at the station for more than a minute
Then
- alert the shift supervisor with the camera, the station and the exact time
- save the video of the minute before the stop
- time the stop until the body shell moves on again
The instruction that set it up«Tell me when a body shell has not moved on for more than a minute at the station, and show me the video from just before.»
What changes
What changes for whoever answers for the plant
The shift supervisor hears about the stop late, with whatever cause somebody remembers. With the camera he has the exact time, the minute the line moved again and the video of the seconds before. That footage shows what happened first: a jammed part, an empty container, a badly seated body or a robot at a standstill. Two-minute stops, the ones nobody writes down, stop being invisible.
What people usually ask
Does IRIS know why the line stopped?
Not on its own. IRIS sees that the body shell has stopped advancing, marks the exact minute and saves the video from before. That footage shows the first visible event: a jammed part, an empty container, a robot at a standstill or a badly seated body. A person writes the cause; the system hands them the time and the images so it takes a minute instead of half an hour.
Does this replace the system that already logs stoppages?
No. The plant system already knows that the line stopped and for how long. What it does not have is the picture of the minute before, which is where the cause is. IRIS supplies that image and the exact time, and works alongside what is already there, never instead of it.
Does the camera identify the operators who were waiting?
No. IRIS does not recognise faces and does not compare them with anything. It sees three people standing in front of a body shell that is not moving, and that is what it counts. Who each of them is it neither knows nor stores: the alert carries the camera, the station and the time, not a name.
Other cameras
The real interface, step by step
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.
- Checks the whole system
- Flags what is failing
- Puts it on one screen
Next step
The school
Who sees the child who has fallen at the far end of the playground?
13 cases: 12 raise an alert when something happens and 1 only measure. You see each image as it is, and then with what IRIS understands on top.
Critical infrastructure
Who is watching a site where there is almost never anybody?
44 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 add more cameras;you cannot add more hours to anyone’s day.
Cameras can be multiplied; a person’s hours cannot. IRIS looks at everything coming in and leaves them the one thing no machine does better: deciding what to do.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.