Skip to content

Questions · Intruder detection

Can you guarantee it will never go off falsely again?

No, and anyone who guarantees it is selling you something. A system that never fires without a reason only exists if it is switched off, or if it is so deaf that it does not detect the person who really does get in either.

What you can do is bring the alerts down to a number that burns nobody out, and say what it is done with: choosing the technology point by point instead of repeating the same detector across the whole installation, requiring agreement between two criteria where the surroundings are difficult, zoning so that nobody is forced to arm more than they need, putting in writing which zones are isolated during building work and on what date they come back, and verifying by image so that the alerts that still come in are dismissed in seconds instead of moving somebody.

And there is a part that is not technical. The biggest drop usually comes from fixing the use —real schedules, who has a code, how people say somebody is staying late— and from investigating every alert instead of piling them up. A system whose alerts nobody looks at does not improve on its own, it degrades.

Where you can see it working.

On the IRIS Neural website, on real scenes.

All the questions.

Five hundred and forty-four, grouped by topic. Each with its own page.

Get started

See it working.

A written answer is enough to decide whether it interests you. To know whether it works at your site you have to see it on a real scene, with the image as it is and, on top of it, what the system understands from it. That is on the IRIS Neural website, which is the group's product.