CAM-451
A container has ended up crooked on the stack
Mid-afternoon in the container yard. A heavy lift truck is still holding a red container that has ended up crooked on the stack: it is not sitting on its four corners and one end overhangs the aisle. Below it, the blue container has a panel caved in from an earlier knock. Four workers are watching from the aisle, with cones and a barrier already out. IRIS does not judge the manoeuvre: it sees a unit out of alignment and people close to its overhang.

Turn on IRIS Vision
AI-generated image
What IRIS is
IRIS watches the dock while you get on with the job.
IRIS is an artificial intelligence that watches the cameras you already have at the port and understands what's happening at the fence, the perimeter, and the water's edge. When someone lingers where they shouldn't, gets close to the dock, or something you've asked it to watch happens, it alerts you — and whatever can be counted, like access points, it counts in numbers. All day long, with no one needing to watch a screen.
You tell it what you need to watch, and IRIS does it.
Here, for example, IRIS sees a container left crooked on the stack, not resting on all four corners, plus anyone standing close to where it overhangs. That gives you the row, the height and the exact time it ended up like that. With that you decide whether to move it right away or close the aisle, and the footage also does the job for the damage report.
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
- container crooked on the stack
- caved-in panel on the container below
- lift truck still holding the unit
- crew watching from the aisle
- cones and barrier in the aisle
What this camera measures
An alert says something is happening. The reading says how much.
- 3Tiers in the stack
- 3 minTime not sitting on all four corners
- 4People in the aisle
- 3Cones and barriers set out
- 17:05Time 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
a container is left out of alignment on a stack or with one end overhanging a traffic aisle
Then
- alert the yard manager with the camera, the row and the time
- save the video of the set-down and the minutes before it
- attach the image to the damage report for that unit
The instruction that set it up«Tell me when a container ends up out of alignment on a stack or with one end overhanging an aisle, and tell me if there are people nearby.»
What changes
What changes for whoever answers for the terminal
The yard manager hears about this over the radio, if he hears about it at all. By the end of the shift nobody remembers what time it ended up like that. With the camera he has the row, the tier, the exact time and the video of the set-down, which is what he needs to decide whether to move it again now or close the aisle. And for the damage report on the dented container, an image with a time on it beats a description written three hours later.
What people usually ask
Does IRIS say the container is badly stacked?
Not quite. IRIS sees one concrete, measurable thing: the unit is not aligned with the stack and one end overhangs the aisle. It may be a set-down still in progress or a manoeuvre that went wrong. Which of the two it is, the yard manager decides, watching the video. The camera supplies the fact, the row and the minute.
Does it detect a damaged or dented container?
Yes, the damage that shows from the outside: a caved-in panel, a twisted door, a struck corner. What no camera can do is tell you what happened to the cargo inside, or whether the structure is compromised; that takes an inspection. What you do get is the image with a time on it, which is usually exactly what a damage report is missing.
Can it be used across a whole yard, with hundreds of rows?
Yes, but not with one blanket rule. Zones are drawn on each camera’s image: this row, this aisle, this maximum tier. What is normal in an empties yard is not normal in a reefer row, so the terminal writes the rules, camera by camera. IRIS applies what has been drawn for it, the same way, around the clock.
Other cameras
- CAM-440 · Somebody has come over the perimeter fence
- CAM-441 · Someone is swimming towards the quay
- CAM-442 · A car has sat eleven minutes where nobody ever stops
- CAM-443 · Two trucks, one single barrier opening
- CAM-444 · A container opened outside the working window
- CAM-445 · Someone has crawled under a trailer
The real interface, step by step
A new case each time. Always the same screen.
It plays by itself and shows one case from start to finish. It is a summary: the real screen has far more functions than fit in this box.
- Cameras on the map
- You draw an area
- What passed shows up
See it somewhere else
Camera health
And who watches the cameras?
34 cases, and in every one of them IRIS raises an alert when something happens. You see each image as it is, and then with what it understands on top.
The city
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.
And the best part
A recording gets watched when nothing can be done.An alert lands while there is still time to act.
IRIS raises the alert while it is happening and says where: the camera, the time and the images from that moment. With that, whoever is on duty is still in time to act.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.