CAM-918
Greasy streaks
A narrow street running down towards the sea, early in the afternoon. A white van stopped in the middle of the road, a bin beside the kerb and a worker taking boxes out of a storeroom on the left. All of that is visible. What is not visible is the right-hand half of the frame: thick streaks run down in front of the façade, with lumps and spatter, not covering it completely but distorting what is behind. The same thing happens, more faintly, in the bottom left corner. IRIS sees that this part of the picture has stopped giving detail and stays put even when a car drives past behind it. What it does not know is what the stuff is: that is for whoever climbs up to look.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- streaks on the lens
The rule
You decide once. IRIS applies it always.
If
an area of the frame stops giving detail, does not move with the scene and looks the same the next day
Then
- alert maintenance with the camera, the time and the video showing the affected area
- mark on the picture which piece of the frame has been lost and how much of it it takes up
- raise a separate alert if the lost piece is one of the areas being watched
The instruction that set it up«Alert me if part of the frame goes fixed and blurred while the rest still looks fine.»
What changes
What changes for whoever answers for the cameras working
The trap with grease is that the camera looks like it can see. Half the picture is still perfect, the light is green and nobody writes it down as faulty. But the piece that has gone may be exactly the storeroom door or the bin where things get left. That gets found out weeks later, hunting for a video that no longer shows what is needed. With IRIS the alert arrives the day the streak appears, and it does not arrive alone: it says which part of the frame has stopped being visible and whether that part was one of the watched areas. Somebody goes up to that camera, and to that face of the dome. And the day it got dirty and the day it saw again are both written down.
What people usually ask
Does it not confuse grease on the glass with a stain on the wall opposite?
No, and the difference is easy to see. A stain on a wall is part of the scene: if a lorry drives in front of it, the stain is covered, and daylight changes it hour by hour. Dirt on the glass is stuck to the picture: it stays on top of the lorry, it looks the same at night and it distorts what is behind it instead of covering it. IRIS looks at those three things together and compares them with the same frame on earlier days.
In a kitchen or a workshop the lens gets greasy every week. Will the alert just stay on for ever?
Getting dirty often is not the problem; the problem is not knowing which one is into its third week. The alert is not a light left on: it is a dated entry. It opens when the streak appears and closes by itself when the picture comes back. If that happens weekly at your site, after a year you know how often each camera really gets dirty. That is what you use to fit the round to what actually happens, instead of guessing it.
Is this not already covered by the maintenance contract?
The contract sets the visits. This sets the priority and the proof. A job sheet that says “camera cleaned” does not say whether it was dirty, how long it had been like that, or which part of the frame had been lost. With IRIS you have the day the dirt appeared, the piece of picture that went missing and the day it came back. Whoever signs the contract stops arguing from memory and looks at the dates. IRIS cleans nothing: it makes cleaning something you can check.
Simulation · how IRIS works
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 hour, as a grid
- You look where it's dark
- You jump to that minute
Next step
Who is watching the cameras of a whole branch network?
13 cases: 12 raise an alert when something happens and one only measures. You see each image as it is, and then with what IRIS understands on top.
How long does it take to find a hand played two hours ago?
12 cases: 9 raise an alert when something happens and 3 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
Finding something in yesterday’s videoshould take as long as asking for it.
No more scrubbing back through six hours with your finger on the mouse. You type what you are after, in plain words, and the matching moments come up. Same cameras as always.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.