CAM-913
Cobwebs
A quiet corner in mid-morning: a wide pavement, two metal gates, a low wall with a planter, young trees, and across the road a brick building with plants on its balconies. Nobody is passing. What fills the frame is not in the street: it is a cobweb stuck to the dome glass, white strands lit by the sun that cross the whole left half and reach into the middle. You can tell it is on the glass because the strands are sharp while the street is not, and because they do not move when the trees move. IRIS sees that there are filaments on the optics and which part of the frame they veil. It does not know whether the spider is still there, and it does not need to.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- cobweb on the glass
The rule
You decide once. IRIS applies it always.
If
there are filaments stuck to the optics that veil part of the frame and do not move with the scene
Then
- alert maintenance with the camera, the time and the video of the previous night
- look at that camera again at dusk, when the infrared comes on, and keep both pictures together
- put the other cameras on the same mast into the same cleaning round
The instruction that set it up«Tell me if a camera has cobwebs in front of the lens, and tell me before it gets dark.»
What changes
What changes for whoever answers for the cameras working
By day it looks like nothing, which is why it has been there since August. At night it stops looking like nothing. The camera switches on its own infrared, and that light hits strands sitting five centimetres from the lens: the strands go white and there is no street any more, only the camera’s own lamp bouncing back. A good camera, chosen precisely because it saw well in the dark, goes blind in exactly the hours that matter. And because it only happens at night, whoever scans the video wall in the morning sees nothing wrong. On top of that, the strands move in the air and set off detections that are nothing, until the operator stops believing that camera. Fixing it takes ten seconds and a cloth. What is missing is that somebody knows.
What people usually ask
Is a cobweb not trivial next to somebody tampering with the camera?
By day, almost. By night, no. The camera switches on its own infrared, the light bounces off strands sitting five centimetres away and the frame turns white: that camera has stopped seeing the street. It happens every night, it is fixed with a cloth, and nobody notices, because by day the picture looks fine. It is one of the cheapest faults in the whole installation to repair, and one of those that takes away the most usable video. Somebody tampering with the camera gets noticed; this does not.
How does it tell a cobweb from something out in the street?
By three things visible in the picture itself. It is in focus when the rest is not, because it is touching the glass. It does not move with the scene: when the wind moves the trees behind, it does its own thing. And it stays in the same place hour after hour and day after day. When the three agree, IRIS raises it; when it is not clear, it raises it anyway and a person looks at the picture. Whoever decides to send someone up with a cloth is always a person, not the machine.
How often does the glass of a camera need cleaning?
It depends so much on the site that any general answer would be a lie. A dome under a tree or beside a streetlight, at the end of summer, may need it within weeks; the same model on a clean, airy facade may go years. Nobody can write a calendar that fits both, which is why blanket inspections always arrive early for some cameras and late for others. IRIS does not propose a calendar: it says which camera, and this week.
The real interface, step by step
A camera looks. IRIS understands what it sees.
An extract of the real screen, no voice-over and hands-free. Each round poses another situation. What sits behind it is a good deal bigger than what you see.
- It lands in the tray
- You open it
- You confirm or dismiss
Next step
What can a camera see without pointing at anyone?
13 cases: 9 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.
What if the outage does not start with an attack?
13 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
Recording is memory.Understanding is attention, and that is the part you had never bought.
The recording is still kept in case you need it. What is added is that those same images are understood as they arrive, not months later and not by hand.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.