CAM-339
Someone opens a valve at night and fills a tank
Three fifteen in the morning, with the yard lights on. A person with no hard hat and no vest has both hands on a valve on the manifold. From that area a black hose runs across the gravel to a flatbed van. There, a second person holds the hose over a white tote loaded on the bed. IRIS sees a valve being operated at that hour and a transfer into a vehicle.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognizes in this scene
- person operating the valve
- manifold valve opened
- hose run out across the ground
- person holding the hose on the truck bed
- white tote loaded on the van
- flatbed van stopped on the road
What this camera measures
An alert says something’s happening. The reading says how much.
- 03:14time of the first movement on the valve
- 00:09time since the vehicle arrived
- 2people at the spot
- 1vehicles at the spot
- 1containers loaded on the bed
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
somebody operates a valve on the manifold in a window with no work order open
Then
- alert the security center with the camera, the time and the image
- save the video from the moment the person reached the valve
- count the people, the vehicles and the containers at the spot
The instruction that set it up«Tell me if anybody operates a valve on the manifold with no work order open, and all the more so at night.»
What changes
What changes for whoever answers for the plant
Three fifteen in the morning, and no operation is scheduled on that manifold. The difference between finding out now and finding out in the end-of-month balance is enormous: now the control center operator has an image, a time, the vehicle on screen and somebody to call; in the balance there’s only a gap nobody can explain. IRIS alerts while it’s happening, keeps the video from the first movement and leaves the report ready for whoever has to act.
What people usually ask
Does IRIS know that this is a theft?
No, and it doesn’t say so. What it detects is a specific situation: somebody is operating a valve in a window with no work order open, and there’s a hose run out toward a vehicle. That’s visible in the image and can be stated. Putting a name to it’s for people, with the video in front of them.
Does it recognize the person or read the license plate?
It identifies nobody: it does not recognize faces and does not compare them against any database. It sees two people, a vehicle and a container, and counts them. Plate reading is a separate function, enabled separately and only where you’re allowed to use it. The alert from this camera doesn’t depend on it.
And what if it’s genuine work outside normal hours?
Then there’s a work order open and the site knows about it. The rule is written against the order board: if the work is authorized, no alert goes out, even at three in the morning. When it isn’t, the alert arrives while it’s happening, and whoever is on duty decides whether to call, to drive out, or to do nothing.
Other cameras
- CAM-320 · A jet from the pump and a pool that keeps growing
- CAM-321 · Flame and smoke in the pump row
- CAM-322 · The flare isn’t burning the way it always does
- CAM-323 · The tank is overflowing from the top
- CAM-324 · The tank hatch is open and nobody’s up there
- CAM-325 · The hose is coupled to the wrong header
Simulation · how IRIS works
Everything comes in. Only what matters gets through.
This sums up what IRIS does with one alert, from the moment it appears until it’s closed. The real screen holds far more; this is the main thread.
- Four cameras at once
- Each understands its own view
- The numbers climb by themselves
Next step
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.
When does a bad review get decided?
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
You decide the rule onceand it’s applied the same way every time.
At three in the morning it means what it means at noon, on camera one and on camera four thousand. It doesn’t depend on who’s on shift, or how tired they are.
Tell us your problem and we’ll say whether IRIS understands it, or not yet.
A person answers, the same working day.