Shopping centresPersonal safety
CAM-545
A child alone in the middle of the walkway, and minutes count
Mid-afternoon, in front of the information desk. A child has been left alone, standing in the middle of the walkway. An adult is coming from one side and a guard from the other: both are already heading towards him. Behind them, the desk staff are serving somebody else and, further back, somebody is being helped in a seat. The child has been alone for two minutes and ten seconds. The nearest adult is six metres away.
Turn on IRIS Vision
AI-generated image
What IRIS is
IRIS keeps an eye on the mall for you.
IRIS is an artificial intelligence that looks at the cameras you already have and understands what's happening in the aisles, queues and stores. When a queue grows long, an area fills up, or something you want to track happens, it alerts you; and whatever can be counted, it counts in numbers. All day long, without anyone having to stare at a screen.
You tell it what you need to watch, and IRIS does it.
Here, for instance, IRIS notices a child has been alone for more than two minutes and alerts staff right away with the camera and the exact spot. That way you know where the child is and how long they've been unattended, without waiting for someone to notice. With that alert you decide who goes and check that an adult gets there quickly.
Works with the cameras you already have. Nothing to replace.
A person replies, not a form.
- Your footage never leaves your premises.
- It doesn't identify people.
- Certifications →
What IRIS understands
What it recognises in this scene
- child standing alone
- guard approaching
- adult approaching
- the information desk
- desk staff
- person being helped in a seat
- the mall directory
- the escalator at the far end
What this camera measures
An alert says something is happening. The reading says how much.
- 2 min 10 sAlone for
- 6 mNearest adult
- 2Staff alerted
- 9Cameras in the search
- 18:41:22Video from
The figures on this screen are an example from the illustration, not any client's measurement.
The rule
You decide once. IRIS applies it always.
If
When a child has been alone in a public area for over a minute
Then
- alert the information desk and the nearest guard
- prepare the search by clothing and approximate height — the operator launches it
- save the video from the moment he was left alone
The instruction that set it up«Show me where you have seen a child on their own over the last ten minutes matching the description the family has just given at the desk.»
What changes
What changes for operations, for asset management and for security
A lost child in a shopping centre almost always ends well, and almost always ends late: a tannoy announcement, a look at the desk, somebody walking the floor. What IRIS changes is the clock. The operator gets the exact spot and the video of the moment the child was left alone, and can ask the system to show where it has seen, over the last few minutes, a child matching the description the family has just given. And here we have to be exact: IRIS does not know who the child is, and it never will. There is no biometrics and it does not recognise faces. All it does is shorten the time until an adult reaches him.
What people usually ask
Does IRIS recognise the child’s face?
No. IRIS does not know who the child is, and it never will. There is no biometrics, no facial recognition, and no face is compared against any database. The search is done on non-identifying visual features — the colour of the clothes, the approximate height — and it is always launched by an operator, never by the system on its own. All IRIS does is shorten the time until an adult reaches him.
So what does IRIS actually show the operator?
Places and minutes. What the operator types is what the family has just told them at the desk, in the family’s own words, and IRIS returns the moments and the cameras where it saw something matching that description, so that he can look and decide. It does not say “this is the child”: it says “look here”. Identification and decision belong to the person, always. Detecting is not deciding.
Is a trail of the child kept anywhere?
No record of any person is created. What remains is the centre’s video, which is recorded anyway, and the log of the alert: when it was opened, who attended it and when it was closed. There is no profile, no identity, and nobody is followed around the mall outside that search, which lasts as long as the alert and is controlled by the operator. Who that child is will be known by his parents and by the desk staff. Not by IRIS.
Other cameras
- CAM-535 · How many people come in through each door, and when
- CAM-536 · An empty corridor twenty metres from a packed wing
- CAM-537 · Before, during and after: what the campaign actually brought in
- CAM-538 · Eighteen hundred walk past and two hundred stop
- CAM-539 · The ground floor packed and the upper walkway deserted
- CAM-540 · How many get out of the car and which door they end up using
A different case every time
We won't just tell you. We'll show you.
It is a summary of the real screen: it plays by itself, step by step, and shows only the path of one case. The actual tool has far more than fits in here.
- The alert fires
- It lands in the tray
- You open it
- You confirm or dismiss
See it somewhere else
Who watches the cameras of a whole city?
23 cases: 18 raise an alert when something happens and 5 only measure. You see each image as it is, and then with what IRIS understands on top.
Who watches an entire motorway?
10 cases: 8 raise an alert when something happens and 2 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
You decide the rule onceand it is applied the same way every time.
At three in the morning it means what it means at noon, on camera one and on camera four thousand. It does not depend on who is on shift, or how tired they are.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.