CAM-72
Empty shelves in the aisle
A supermarket aisle seen head-on: in the middle there is an empty shelf with the bare backing on show and, right beside it, another one still full. A shopper has stopped in front of the gap with a hand on his head. Nobody is restocking.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- empty shelf
- stocked shelf
- shopper facing the gap
The rule
You decide once. IRIS applies it always.
If
a shelf runs out of product and is still empty after a few minutes
Then
- alert the floor manager with the camera, the aisle and the shelf
- open the image so the gap can be identified without walking down there
- log how long it took to refill, so the store learns which gaps keep coming back
The instruction that set it up«Tell me when a shelf runs empty and stays empty for a while, so I don't find out only when the stacker walks by.»
What changes
What changes for whoever runs the store
A gap on the shelf is lost sales happening live. In the picture there is a customer standing in front of the gap and nobody restocking: that is exactly how it happens. The customer who comes for his brand and doesn't find it will not wait: he takes another one, or he leaves and buys it next door. Today the floor manager finds out when the stacker walks past, which may be three hours later, and by then a lot of people have walked past that gap. With IRIS he knows while the gap is still there, with the aisle and the shelf, and he is also left with the list of which gaps keep coming back every week, which is what actually fixes the problem.
What people usually ask
Does IRIS know which product is missing?
IRIS sees the gap and says which aisle and which shelf it is on. What product belongs on that shelf is something the store knows, because the store owns the shelf plan; if that plan is given to IRIS, the alert can come out with the name on it. Without it the alert is still useful: the camera and the shelf are enough for the stacker to walk straight to the right spot.
What about when the shelf is empty because we are refilling it right then?
You tell IRIS to wait. The rule does not fire the moment the gap appears, but once the gap has been there for a few minutes, and it can be kept quiet while there is a restocking trolley parked in front of that stretch. A restocking trolley in front of the shelving is exactly what the camera sees, so the exception is written with the same material as the rule.
Do we need a new camera in every aisle?
It depends on the angle of the one already up there. Almost every store has cameras in the aisles, but many are aimed along the aisle from very high up, and from there you see the floor and not the shelves. Every aisle is checked before the coverage is signed off, and where the existing camera doesn't reach we say so and fix it by moving it, changing the lens or adding one. Promising that every camera works as it is would be a lie.
The real interface, step by step
Watch what happens. Then watch what IRIS does with it.
Not a recorded video and not a drawing: it is a summary of the real tool, with a different case each time round. The whole tool does not fit in a box.
- Cameras on the map
- You draw an area
- What passed shows up
Next step
How long before somebody comes down that corridor at four in the morning?
13 cases: 12 raise an alert when something happens and 1 only measure. You see each image as it is, and then with what IRIS understands on top.
Who sees the child who has fallen at the far end of the playground?
13 cases: 12 raise an alert when something happens and 1 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
Video is late by definition:you watch it once the thing has already happened.
IRIS tells you while it is happening, with the camera, the time and what it saw. Arriving in time changes the end of almost any story, and no new cameras are needed for that.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.