CAM-261
Two people, one turn of the gate
Early morning at the staff entrance. Someone presents a badge, goes through the full-height turnstile and the reader turns green. Right behind them, in the same turn, a second person comes in without presenting anything to the reader. In the booth on the right, the guard is watching a different wall of screens. Behind the fence the warehouse is already running. IRIS counts two bodies and a single green light.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognizes in this scene
- turnstile with only one validated pass
- first person through the turn
- second person in the same turn
- access reader showing green
- guard post with the screens
What this camera measures
An alert says something’s happening. The reading says how much.
- 2People in the turn
- 1Green reader lights in that turn
- 1,2 sGap between the two people
- 34Turns counted in the last hour
- 06:58Time of the pass
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 people cross the turnstile on a single read at the reader
Then
- alert the guard post with the camera, the gate and the time
- save the video of the ten seconds before and after the turn
- correct the head count of people inside the site
The instruction that set it up«Tell me when two people go through the gate on a single badge read, and show me the video of the pass.»
What changes
What changes for whoever answers for the plant
The access log says one person came through that gate this morning. In fact two did. With the camera that gap closes: every pass is counted and the one that doesn’t add up arrives with the video. It matters for evacuation head counts, for knowing how many people were inside when something happened, and for making the gate rule stick because it shows, not because it gets repeated at the safety briefing.
What people usually ask
Does IRIS know who came in without badging?
No. IRIS does not recognize faces and does not identify anyone. It only counts bodies and compares them with the reads at the reader: two people, one green light. Who the second person was is for the security team to work out from the video and the shift list, if they choose to. The camera supplies the fact and the minute; the name, if it is needed, comes from a person.
What if two people come in together on purpose, like an escorted visitor?
You solve it by writing the rule. The site decides at which gates and in which time bands a double pass is normal and where it isn’t. IRIS doesn’t decide what deserves an alert: it applies what it’s been told and saves the video in case somebody wants to review it later. If escorted entry is routine, it is logged without alerting and the count still adds up.
Is this count good enough for evacuation head counts?
Yes, and it’s the most useful part. IRIS people counting is approved by the Centro Español de Metrología, Spain’s national metrology institute, so the figure for how many people are on site is repeatable and auditable. If a pass isn’t registered at the gate, that number stops being reliable on exactly the day it matters most. Here the camera closes the gap: it counts bodies, not cards. The approval is Spanish. It doesn’t stand in for a U.S. certification, and we don’t present it as one.
Other cameras
- CAM-260 · A cage goes out through the wrong door
- CAM-262 · Hands on a trailer’s rear lock
- CAM-263 · The trailer is at the wrong dock
- CAM-264 · The truck pulls away with a worker still inside
- CAM-265 · The pallet going into the truck isn’t the one for that route
- CAM-266 · Twenty-two units go out and the order says twenty-four
Demo · IRIS at work
You set the rule once. IRIS applies it every time.
You will see a summary of the interface, played step by step and hands-free. Each round starts with another case. The complete tool doesn’t fit in a demo.
- Four cameras at once
- Each understands its own view
- The numbers climb by themselves
Next step
Who is watching the cameras of a whole branch network?
13 cases: 12 raise an alert when something happens and one only measures. You see each image as it is, and then with what IRIS understands on top.
How long does it take to find a hand played two hours ago?
12 cases: 9 raise an alert when something happens and 3 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
What happens outside the framedoesn’t exist for IRIS. No camera sees the whole world.
So the first thing we do is check what each camera covers and write it down: from here you can understand this, and not that. A dull hour that saves a lot of misunderstandings.
Tell us your problem and we’ll say whether IRIS understands it, or not yet.
A person answers, the same working day.