CAM-912
Drops that stay
The same street, at night and in the rain. You can see the lit shop windows, a cast-iron lamppost, somebody crossing under an umbrella and a dark car parked in the foreground. In front of all that, stuck to the dome glass, there are dozens of fat drops and several runnels sliding down. The drops are in focus and the street is not: each one works as a lens and turns the lights behind into bright discs. This picture, as it stands, is not a fault: it is raining, and that is what a camera looks like in the rain. The fault is the same picture the next morning, under a clear sky. IRIS sees that there is water on the optics and how much of the frame it takes away; what decides whether that is normal is how long it has been there.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- water on the optics
The rule
You decide once. IRIS applies it always.
If
there is still water on the optics after the time set from when the rain stopped
Then
- alert maintenance with the camera, the time and the video of the whole night
- log how many times it has happened to that same camera this month
- group into a single trip every camera in the area with the same problem
The instruction that set it up«Tell me if a camera still has drops on it once the rain has stopped, and tell me how long they have been there.»
What changes
What changes for whoever answers for the cameras working
The rain moves on. The water sometimes does not. A dome with a worn seal, with the coating on the glass long past its life, or mounted right under a downpipe keeps drops on it for hours after the sky clears, and keeps them again every time it rains. By day, in the sun, that camera looks perfect, so nobody touches it. The night somebody needs the video of that corner, what there is is a smear of lights. With IRIS the alert arrives once the water is still there after the time you set from when the rain stopped, with the camera and the hour on it. The repair is usually a new dome or a cloth. The expensive part is not fixing it: it is not knowing.
What people usually ask
Will it alert me every time it rains?
No. Rain is not a fault, and a camera with drops on it while the water is falling is doing its job. The clock for this rule does not start when the rain starts: it starts when the rain stops. From there it counts the interval you have chosen, and only if the water is still there at the end of it does an alert go out. If the sky clears and the glass dries by itself, nobody hears a thing, which is exactly how it should be.
Would it not be simpler to clean every camera twice a year?
You can, and that is what is done today. The trouble is that a calendar treats cameras with nothing in common as if they were the same. A dome under an eave may last two years; another under a downpipe streams with every storm and does not last a month. A blanket clean spends hours on cameras that were fine and arrives late at the three that were not. What changes with IRIS is who decides the round: the cameras that need it, not the calendar.
Do the drops make the camera detect things that are not there?
They can. A drop sliding down the glass moves, and at night each drop turns a distant light into a bright disc that appears and disappears. That produces detections that are nothing, and an operator who sees the same thing three nights running stops trusting that camera. This is why IRIS does not simply send the detections: it also says that this camera has water on it. Then you understand why it is restless tonight, and you fix the cause instead of putting up with the symptom.
See it for yourself
This isn’t a video. It’s a slice of the real screen.
A summary of the real interface, played hands-free. You see one case from start to finish; what you do not see are the other screens, and there are many.
- The hour, as a grid
- You look where it's dark
- You jump to that minute
Next step
What does a shopping centre see beyond the visitor count?
12 cases: 4 raise an alert when something happens and 8 only measure. You see each image as it is, and then with what IRIS understands on top.
What does an airport see before the queue forms?
14 cases: 7 raise an alert when something happens and 7 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
At eleven the last person leaves.The cameras stay, and now they understand what is going on.
Nobody switches anything off on the way out. What happens in an empty building is understood right then, and nobody waits for the doors to open to find out.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.