Skip to content
IRIS NEURALContact

Banking

CAM-512

Two people through the door on a single opening

It’s night and the branch is closed to the public; the ATM lobby is still open behind a controlled door. Two people come through the same glass leaf: one is already inside and walking on, the other holds the leaf with a hand and follows. IRIS sees two bodies and a single door opening. That’s all it sees, and that’s exactly what it says.

It’s night and the branch is closed to the public; the ATM lobby is still open behind a controlled door. Two people come through the same glass leaf: one is already inside and walking on, the other holds the leaf with a hand and follows. IRIS sees two bodies and a single door opening. That’s all it sees, and that’s exactly what it says.
CAM-512IRIS VisionLive

Turn on IRIS Vision

AI-generated image

CAM-512 · ENTRANCE LOBBY · TWO BODIES · ONE OPENING

What IRIS understands

What it recognizes in this scene

  • person holding the leaf and following through
  • person already through
  • glass leaf, opened once
  • briefcase
  • ATM on the left
  • ATM on the right
  • dome camera watching the machines

What this camera measures

An alert says something’s happening. The reading says how much.

  • 2Bodies that went through
  • 1Openings of the door
  • 6 sTime since they went through
  • 19:58Time of the alert
  • 19:58:12The video starts at

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

two bodies go through on the same opening of the door

Then

  1. alert whoever runs security with the door, the time and how many bodies went through
  2. save the video from a few seconds before the door opened
  3. leave the fact on record so it can be matched against the access log
The instruction that set it up«Tell me when two people go through on a single opening of the door.»

What changes

What changes for whoever answers for the branch network

The access control system knows how many credentials were used. The camera knows how many bodies went through. When the two numbers don’t match there’s something to look at, and today nobody looks, because there’s no way to compare them without wading through the whole recording. IRIS leaves the alert with the exact time and the video of those seconds, and whoever runs security takes a minute to see what happened. There’s no accusation anywhere: there’s a fact, a video and a person who decides.

What people usually ask

Does IRIS know whether the second person was allowed through?

No, and it can’t know. IRIS does not read the credential, does not identify anyone and does not consult any list of authorized people. All it sees is that two bodies went through on one door opening. The other figure belongs to the access control system, which knows how many credentials were used. Putting the two together and deciding whether there’s anything to review is a person’s job; the camera only puts the fact and the video on the table.

And what if both work here and come in together every day?

Then there will be nothing to review and the alert is closed in ten seconds. An alert isn’t an accusation: it’s a question with video attached. Many are settled the moment somebody looks at them, and that alone is worth it, because today nobody looks at those seconds. And if going through two at a time is normal at one particular door, the rule is adjusted for that door: decide once, and it applies every time.

Does IRIS recognize the people who come into the lobby?

No. In a bank branch IRIS does not recognize faces, does not compare them against any database and does not identify any customer or employee. It doesn’t read license plates here either. It counts bodies and measures times: how many went through, when, and how long the door stayed open. That’s enough to say what happened, and nothing more is needed.

The real interface, step by step

Everything comes in. Only what matters gets through.

This sums up what IRIS does with one alert, from the moment it appears until it’s closed. The real screen holds far more; this is the main thread.

  1. The rule gets built
  2. It goes to every camera
  3. Published, it watches alone
  4. And then it fires
IRIS NEURAL
30ES
IRISDirectoGrabacionesGISIncidencias3996SituaciónCasosLPRAutomatizacionesIRIS DATA
Ask a question or make a request…Send
IRIS · Infinity Neural

And the best part

At four in the morning,the camera is still watching just as it does at noon.

No heavy eyelids, no distractions, no shift change. What happens at night is understood at night, not the next morning.

Tell us your problem and we’ll say whether IRIS understands it, or not yet.

A person answers, the same working day.