Skip to content
IRIS NEURALContact

Solutions by typeCustomer experience

Why do I always hear about the queue after someone has complained?

The queue grows, the counters stay closed

It is 06:35. There are two lines in the check-in hall. The one on the left, for the staffed desks, is eighteen minutes long and doubles back on itself twice. The one on the right, for the self-service machines, clears in four. Above the desks four signs are dark: four positions never opened. The camera has been recording since five. In the office next door, nobody knows yet.

28 cameras across 10 sectors

This is how you ask for it

«“Alert me if a line goes over fifteen minutes and desks are still closed.”»

The first warning arrives when someone misses a flight or a written complaint comes in. By then the line has been building for over an hour and the shift has spent the morning firefighting by hand: radio calls, two desks opened, someone pulled off their break. At the end of the month nobody can say how often it happened, at what time, or for how long. All that is left is the feeling that mornings get away from you.

You decide once

You decide what counts as a long queue in your building: fifteen minutes at check-in, eight at the food court, ten people at the cash desk. You also decide when it matters and who gets told. You say it once. From then on IRIS watches that line at six in the morning, at two on a Saturday and in the middle of August, without anyone having to remember to ask again.

Almost nobody measures a queue. A queue gets looked at. Someone walks through the hall, sees it looks bad and calls it in on the radio. If that person is in a meeting that day, the line grows on its own. That is why the same queue takes six minutes on a Tuesday and thirty-five the following Friday with nothing else having changed: what changed is who walked past, and when.

IRIS watches the waiting area, counts how many people are in each line and measures how fast it moves. When the wait crosses the limit you set and positions are still closed, the alert arrives with the camera, the time and the video. It is not a figure for the end of the month: it is a warning while there is still time to open a desk.

Then there is the other half, and it is usually the half that pays for the install. The same camera that alerts also counts. How many people went through the tills on Saturday between twelve and two. The average wait over Christmas. Which desk opens late every Monday. That number is not asked for in words: you draw a line or an area on the image, and it comes out the same every day. Asking is for finding. Counting is for measuring. They are not done the same way.

What changes

Before, someone had to be there to see it, or someone had to complain. The supervisor walked down to the hall, counted by eye and decided. Now the alert arrives on its own, with the camera open and the video of the moment, and whoever is in charge decides whether to open another position or move someone. And at the end of the month nobody argues about whether it was a bad morning: the number is there, hour by hour.

Where we have seen it

  • Check-in hall at half past six. On the left, the line of staffed desks with their signs above; on the right, the bank of self-service machines for dropping a bag. In front, a belted snake with two hundred people inside it. The thing is, the two queues are nothing alike: the desk queue is running at eighteen minutes and the self-service one at four. And five desk positions have their screens switched off. IRIS measures the wait in each queue, how many people are inside it and how many positions are open while people wait.

    CAM-581Eighteen minutes in one queue, four in the one beside it

    «Tell me if a queue goes over fifteen minutes and there are still desks closed.»

    See this camera →Airports

  • Mid-morning. The armoured van is stopped at the kerb with its rear doors open. Two people from the crew carry a cash box to the branch door, where a third one waits. Between the van and the door there are eight metres of pavement: it is the only stretch of the journey where the money is in plain sight. IRIS times that stretch — when the doors open, how long the walk takes, when the box goes in — and alerts on one thing only: the rear door still being open with nobody from the crew beside it.

    CAM-517A cash box crosses eight metres of pavement

    «Tell me if the van’s rear door stays open more than a minute with nobody from the crew beside it, and keep the time of every collection for me.»

    See this camera →Banking

  • Saturday, just past midnight. At the cage, three windows are serving and two on the left are dark. Behind the velvet rope, a line of nine people is waiting; the floor in front of the closed windows is empty. IRIS counts how many are waiting, how many windows are open and how long each transaction takes. It does not know who anybody is: it counts bodies, not customers.

    CAM-527Three windows open, two dark, and the queue still waiting

    «Tell me when more than ten people are waiting at the cage, or when the wait goes over eight minutes with windows still closed.»

    See this camera →Casinos

  • Mid-afternoon in the packing area. Boxes come down the rollers one after another. At the fork, one box does not carry straight on to the inspection table: it takes the bypass and heads straight for the taping station, where an operator is already closing another one. The inspection table sits empty, its rollers still. The line signal tower stays green: as far as the system is concerned, nothing happened. IRIS follows each box and sees which way it went.

    CAM-246The box takes the bypass and skips inspection

    «Tell me if a box reaches the taping station without having gone over the inspection table.»

    See this camera →Industry

  • The front desk of an emergency department, late in the day. Two people are very close together, one on each side of the counter, arms out and moving abruptly. Another member of staff is coming over from the far side with her hands up in front of her, and a security officer is crossing the room at a brisk walk. Against the wall, people who are waiting have turned to look. IRIS sees two people very close together moving abruptly in a place where that is not normal. It does not know who either of them is, it does not say who is in the right and it classifies nobody.

    CAM-124Tension at the front desk

    «Tell me when two people get very close at the desk and start moving abruptly, or when somebody bangs on the screen, so that someone gets there sooner.»

    See this camera →The hospital

  • The double service door stands wide open and behind it you can see the pantry and the kitchen corridor. Someone not wearing the house uniform crosses it inwards, carrying a cardboard box. On the left, a housekeeper stops beside her trolley and follows them with her eyes. In the middle, the floor supervisor looks up from his tablet. On the right, a trolley loaded with parcels is waiting. IRIS does not say who that person is or what they are there for: it says that somebody has crossed a door that is not a public thoroughfare, and it says so while it is happening.

    CAM-508Someone goes through the service door carrying a box

    «Tell me when somebody goes through the service door without the house uniform, and always keep the video of what comes in and what goes out that way.»

    See this camera →Hotels

  • Mid-morning at the inspection table, before dispatch. On the table sits a cardboard box with its top burst open, the board swollen and a water stain around it. An operator in gloves lifts the torn flap. A colleague with a tablet writes down what she sees. Another holds an intact box on the rollers, waiting. Behind them a pallet stands ready with the pallet truck. IRIS sees the deformed board, the tear and the stain, and flags that parcel before it leaves.

    CAM-268A burst, soaked box about to go on the truck

    «Tell me if a parcel reaches the dispatch table torn, crushed or wet, and keep the photo for me.»

    See this camera →Industry

  • Almost ten at night in the controlled product store. One of the steel cabinets is open. In front of it, a person in a blue gown, hairnet and gloves is holding a personal black bag, open, level with the shelf. On that shelf sit boxes of the same product the cabinet holds. Further back, another person pushes the distribution trolley down the aisle. IRIS sees material being taken from the cabinet and checks whether a work order is open for that hour.

    CAM-297Boxes leave the controlled cabinet with no work order open

    «Tell me if boxes are taken out of the controlled cabinet when no work order is open for that hour.»

    See this camera →Industry

  • Eleven in the morning, scrap yard. The bays are separated by grade: rusty sections and tubes, coils of wire, bright light scrap and baled cans. In the middle, the charging basket holds material from four bays at once: rusty beams, tubes, galvanised offcuts and pale sections. The loader is bringing another mixed bucket. Two operators watch from the ground. IRIS recognises what the material looks like and which bay it came out of; what is actually inside the metal comes from the heat analysis.

    CAM-363The basket has been loaded from four different bays

    «Tell me if material from a bay that does not belong in this recipe goes into the basket, and tell me which bay it came from.»

    See this camera →Industry

  • Quarter to nine at night, before a concert. Under the canopy there are three walk-through detectors and two search tables, with staff in yellow hi-vis opening rucksacks. In front of them, the queue no longer fits on the forecourt: it doubles back on itself, stretches off to the right, and its last stretch has ended up nine metres from the kerb, with cars going past on the road. More people join the queue than the search line manages to clear. IRIS measures both, and the gap between them.

    CAM-482Twenty-four arrive a minute, the search line clears nine

    «Tell me when more people join the search queue than come out through the detectors, and when the back of the line gets close to the road.»

    See this camera →Stadiums and venues

What it does not do

IRIS does not identify anyone and does not recognise faces: it counts people and measures time. It also does not know why the queue formed — a doubled-up flight, a breakdown — and it does not open a desk on its own. It alerts, shows the camera and leaves the decision to whoever has to make it. And if the framing cuts the line in half, the number is worthless: look at the camera first.

Questions

Does IRIS know how long a person has been waiting?
No, not that person. IRIS measures the line, not who is in it: it counts how many people stand between the back and the counter and how fast the line moves. That gives the queue’s waiting time, which is the number you need to decide whether to open another position. You do not have to follow anyone across the hall to know the wait is eighteen minutes, and we do not.
Do I have to replace the cameras in the hall?
Not necessarily. IRIS is built to use the cameras you already have, where the installation allows it. What you do need is a camera that sees the whole line, from the counter to the last person to join. If the framing cuts the queue in half, the number comes out short and the alert arrives late. Before signing off on an area, look at that camera at peak hour, in the light of that hour.
Is this an alert or a number?
Both, and you ask for them differently. The alert is asked for in words: a sentence like “tell me if the wait goes over fifteen minutes”. The number is asked for by drawing: you trace a line across the door or mark the waiting area on the image, and from then on the count comes out by hour, by day, by season. Asking is for finding. Counting is for measuring. One camera can do both at once.
Does IRIS open a desk when the queue grows?
No. IRIS alerts; the people who open desks open them. Your organisation sets the limit, the hours and who gets told, and IRIS applies that rule the same way every time, at six in the morning and in the middle of August. What reaches the person is the camera, the time and the video, so the decision is made with the scene in front of them instead of a complaint from twenty minutes ago.

See all the questions

Every simulation

Something has spilled

Tell me if there is liquid or foam outside its place and it is still there two minutes later.

  1. The sentence
  2. Where it applies
  3. What it finds
  4. The same rule
IRIS NEURAL
30ES
IRISDirectoGrabacionesGISIncidencias3996SituaciónCasosLPRAutomatizacionesIRIS DATA
Ask a question or make a request…Send
IRIS · Infinity Neural

Not seeing yours here?

These words are the ones we have built, not the ones IRIS understands. The list falls short on purpose: you ask for it in a sentence, and sentences do not run out. Tell us what is in front of your cameras and we will tell you whether it understands it, or not yet.

See all solutionsTell us what you see

And the best part

At eleven the last person leaves.The cameras stay, and now they understand what is going on.

Nobody switches anything off on the way out. What happens in an empty building is understood right then, and nobody waits for the doors to open to find out.

Call us · +34 902 02 70 91Get in touch

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

We reply the same working day.