What can a camera see without pointing at anyone?
The camera sees facts. The conclusions are drawn by a person.
A vehicle stopped where it cannot stop. Smoke coming out of the hillside. A slick spreading on the water. A door that opens at three in the morning. IRIS sees facts like these, timestamps them and hands them over with the camera, the time and the video. It recognises no faces, identifies nobody and follows no person. You will see a handful of cameras here: some raise alerts, others measure. A real service has thousands, and the system is exactly the same.
Without IRIS this is just a territory with a lot of cameras switched on.
AI-generated image
Seeing a fact is not accusing anyone
The call comes in by phone, and it comes in late. Someone saw smoke twenty minutes ago and it is no longer a bush, it is half a hillside. The pile of rubble turned up on the waste ground on Monday and nobody knows when it was dumped or which track they came in by. The queue at the vehicle crossing has spilled onto the hard shoulder again and the only way to know the wait is to send someone down to count it. And when, months later, somebody has to explain exactly what happened that night, all there is is a report written from memory.
IRIS reads the cameras that are already in place and reports facts. A vehicle stopped where it cannot stop. A blocked exit. A crowd that keeps growing. Smoke. A slick on the water. A boat that stops where there is no anchorage. And so the line is clear: IRIS does not recognise faces, does not build lists, does not profile anyone, does not cross-check any database, uses no biometrics and does not follow a person around the city. Nothing it does can predict who is going to do something. It sees what happens, timestamps it and hands it over with the camera, the time and the video. Nothing more, and nothing less.
There are two ways to ask for things, because they are two different things. What you watch for is described in words: one sentence, and IRIS alerts you when it happens. What you measure is drawn: a line on a turnstile, an area over a stretch of water. A line does not fit in a sentence, you have to draw it, which is why Tuesday's number and Sunday's are measured the same way and can be audited. People counting goes further still: it is type-approved by the Spanish Metrology Centre through NeuralPax, the body that says whether a weighbridge or a speed camera measures correctly. Mind the scope: what is approved is people counting, and nothing else. And two sentences that matter here more than any feature. First: detecting is not deciding — a person draws the conclusion. Second: the same recording used to give an order serves, months later, to prove that order was right, or to prove it was not.
The real scale
It is not thirteen cameras. It is every camera already installed.
Compound gates, vehicle crossings, quays, yards, hill roads, coastline, waste ground, evidence stores and custody rooms. And there are places nobody looks at, which is worth saying before anyone asks: not inside a home, not in a changing room, not in a toilet, not in an office where somebody is making a statement. When what you see is a person spending the night on the street, or somebody in crisis in the middle of a square, what is needed is not security: it is care. The alert exists to send whoever actually helps, not to move anyone on.
Examples, not a catalogue
One camera, one fact you can check
Some raise alerts, others measure. Each one tells you what is in the image, what rule governs it, which sentence or which drawn line set it up, and what changes for whoever uses it. None of them names anybody or describes anybody: they describe what is in front of the camera.
A different case every time
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.
- You draw the line
- It counts by itself
- A number comes out
And in your territory
Which fact would have changed your day if you had known it in time?
Think of the last alert that came in late. The smoke that was already half a hillside. The queue that spilled onto the hard shoulder. The waste ground that woke up with twenty cubic metres of rubble on it. In all three cases a camera was looking, and in all three the fact took hours to reach somebody who could act.
IRIS does not change the cameras: it changes how long a fact takes to reach somebody who can act on it. And it keeps the sequence, with its timestamp, for the day somebody has to explain exactly what happened.
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
You decide once what matters to you.It stops depending on who happens to be on shift.
You say it in your own words and it stays written down. Nobody has to remember anything at the start of a shift: what you decided is already in place, and still there tomorrow.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.