The hospitalIntrusion detection
CAM-125
Street clothes in a restricted area
A hospital hallway and the double door of a restricted area, wide open, with the red light on above it and the theater visible at the back. Someone in street clothes is standing in the doorway, hand on the door leaf, at a door you only go through in scrubs. On the right, two professionals are talking at the end of the hallway and another walks away; in the foreground, the unit desk, with someone working at it. IRIS sees that somebody is crossing a door that’s closed at this hour. It tells street clothes from scrubs; it does not know who anyone is.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognizes in this scene
- person in closed area
- restricted door
- access reader
- staff in the hallway
- unit desk
What this camera measures
An alert says something’s happening. The reading says how much.
- 1People inside the area
- 18 sInside for
- 42 sDoor open for
- 0Allowed at this hour
- 3Staff in sight
- 09:14Time of the alert
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
somebody crosses a door the hospital has marked as closed in that time band
Then
- alert the unit station with the camera, the door and the video of the moment
- say how long the door has been open, which is often the real problem
- keep the episode on file so patient safety can review it later
The instruction that set it up«Tell me if somebody goes through the restricted-area door without work clothes, and tell me while they are still in the doorway, not once they have been inside a while.»
What changes
What changes for whoever runs the unit
Today this is found out late, or not at all. The door stays open because somebody went through with a cart, and in comes whoever shouldn’t: a relative looking for their family, someone who took the wrong hallway. Nobody does it out of malice, and that’s exactly why nobody reports it. This isn’t a private-security problem: a clean area stops being clean, and a person ends up somewhere they can’t be. With IRIS the alert reaches the station while that person is still in the doorway, with the camera, the door and the video, and somebody goes and walks them out. And it leaves the other figure, the one nobody has today: how long that door stands open each day.
What people usually ask
Does IRIS know who went in?
No. IRIS does not identify anyone: it does not recognize faces, it does not know who any patient or any professional is, it keeps no file on anyone and it has no access to medical records. It tells street clothes from scrubs, the same way it tells a hard hat on a building site, and that’s where it ends. What reaches the station is “there’s someone at the restricted-area door,” with the camera and the time. Who they’re is worked out by the person who goes and asks.
What if the person going in is a professional not wearing scrubs?
Then the alert still fires, and it should. IRIS accuses nobody: it says there is someone at that door without the clothing that door requires. It may be a junior doctor running up, and the alert is closed in two seconds. The hospital writes the rule: which doors, which hours and which clothing counts, and if in a given band the door is open to everyone, there’s no rule and no alert. A check isn’t a sanction.
Are there cameras inside the theater?
No. These cameras look at common areas: hallways, lobbies and doors. There’s no camera in a room, in a bathroom or in an examination room, and there won’t be one. What you see beyond this door is exactly what an open door lets you see from the hallway: once it closes, you see nothing. The zone of interest drawn here stops at the threshold.
Every simulation
On foot among machines
Tell me if someone walks into where a machine is moving and stays there for more than five seconds.
- The sentence
- Where it applies
- What it finds
- The same rule
Next step
Who is watching a whole quay at three in the morning?
14 cases: 13 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.
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.
And the best part
A whole afternoon in front of a screennow fits into one written sentence.
The video hasn’t changed: it’s all still there, in the same place. What has changed is that you can ask it questions, and the answer comes with its camera and its time.
Tell us your problem and we’ll say whether IRIS understands it, or not yet.
A person answers, the same working day.