Intruder detection · IRIS Neural
The image of what set the alarm off.
In intruder detection the problem is not detecting: it is the false alarm. This does not add another detector — it adds the verification that turns an alert into a decision.
What it adds, and what it doesn't.
It does not replace the intruder detection panel. The panel does its job, with its grade, its regulations and its connection to an alarm receiving centre if there is one.
What it adds is what is missing when it goes off: knowing what it was. Whoever is on duty looks at the image of what set the alarm off and decides, instead of sending a patrol out blind or —what actually happens by the third week— not sending one at all.
A warning, and it comes first: IRIS Neural is a product of Infinity Neural, the other company in Upon Group. It heads this list and it is ours, so read it knowing that. With the rest we integrate; with this one, we are also the people who make it.
Zones and perimeters drawn over the image.
As well as verifying, it detects by itself: you draw a zone over the image and say what should not happen there and at what hours. A person on the loading bay at three in the morning, somebody crossing a line nobody crosses, a vehicle sitting still where nobody stops.
That takes no building work: the camera is already there and the zone is drawn. It is the difference between adding a layer of protection and having to cable a perimeter — and that is why it works well as a layer added on top of what is already there, in places where a physical detector would have nowhere to go.
And it works without internet, which in intruder detection matters more than anywhere else: a system that stops watching when the line goes down is exactly the one that is no use.
The false alarm, which is the real subject.
A perimeter that raises an alert five times a night because of a branch stops being a security system by the third week, because whoever is on duty learns to ignore it. And a system that gets ignored is worse than not having one, because it gives the feeling that something is covered.
Here the image helps twice. First because it tells things apart: a person does not move like a branch or like a cat, and that can be learnt. And second because, when it does still go off too often, whoever looks closes it in five seconds instead of sending somebody out.
What we are not going to promise is zero false alarms. Not with this and not with anything: anyone who promises that has never put a perimeter into service. What can be done is to make them few and to make the ones there are resolvable by looking.
Get started
Show us the perimeter.
Tell us what goes off and how many times a night. With that you can already say whether what is missing is verification, another detector, or moving the one that is there.