EPI
Hard hat, high-vis vest or goggles: present or not in an area that requires them. The alert appears in the area and is not linked to anyone by name.
Safety · Tailored
Plant safety with computer vision: PPE, hazardous areas and forklifts
Cameras that monitor areas of the plant, not specific people, and alert immediately and on site when there is a risk situation: someone in a hazardous area, a forklift near a pedestrian, missing PPE. The goal is to prevent the accident, not to score anyone.
Aisle B crossingVehicle and pedestrian close
Alert at the crossing itself with a light or a screen. No names or records.
Illustrative example
What it detects
Six risk situations that can be monitored
You draw each area with your prevention manager. The camera only monitors what has been agreed.
Danger zone occupied
Someone enters a marked area, such as a robot's radius or a press, with the machine running.
Forklift close to a pedestrian
It measures how close a vehicle and a person are at crossings and walkways, and alerts before contact.
Clear exits and walkways
A pallet or boxes blocking an emergency exit or a walkway.
Spill or fallen product on the floor
A puddle or product on the floor in a walkway, before someone slips.
On-site alert
A light or a screen in the area itself, so that the alert reaches whoever is there at the time rather than a report weeks later.
How the alert arrives
From data to the person who can act
An alert that does not reach the person who can fix it is no use. That's why we design it back to front.
- The camera monitors the area
It looks at a crossing, a marked area or an exit. It does not identify people: it detects that there is a person and where.
- Alerts immediately
The alert appears where the risk is: a light, a screen or an alert to the area manager.
- Only reports what is necessary
We store the number of alerts per area and shift so that prevention can see where there is more risk. We do not store who it was aimed at.
No fluff
What works today and what is custom-built
Everything on this page is custom-built. Today the product does not include camera-based safety detection. We design it with your prevention service, test it in one area and only expand it if it works. It does not replace the safety measures you already have or those required by your regulations.
Before installing a camera
Safety with cameras, with clear rules
Monitoring for safety does not exempt you from the rules. We explain how we approach it and what's down to you. Your prevention service and your advisor see it from the start.
How we approach it
- It detects the station, the belt or the area, not the person.
- No facial recognition: the system does not know who anyone is.
- No ranking or scoring of workers, and no comparing them with each other.
- No inferring emotions: at work this is a practice prohibited by Article 5 of Regulation (EU) 2024/1689, except for medical or safety reasons.
- No sound and no cameras in changing rooms, toilets or canteens.
- Images are processed on your own server, at the plant or in Europe, and are stored only briefly. What is kept are alerts and figures.
What's down to you, and we review it with you
- Inform first, expressly, clearly and concisely, the workforce and, if there are any, their representatives (art. 89 of Organic Law 3/2018).
- If there is a works committee, its prior report on work organisation and control systems, and the information on algorithms or AI systems that affect working conditions (art. 64 of the Workers' Statute).
- Carry out the data protection impact assessment where applicable (art. 35 of the GDPR).
- Watch the purpose: an AI system to monitor and evaluate the performance and behaviour of people at work is considered high-risk (Annex III of the Regulation). That's why we don't set it up that way.
LOPDGDD art. 89ET art. 20.3 and 64GDPR art. 35Regulation (EU) 2024/1689 art. 5 and Annex III
We review it with you and with your employment and data protection adviser. This is not legal advice or a guarantee of compliance: every plant is different. We go into more detail in Cameras and AI in the factory: what the law allows in Spain.
How we test it
One line first, then you decide
We choose one risk area
The one that gives the most scares: a forklift crossing, a press, a door.
Camera, rule and alert
We install the camera, set the rule with prevention and decide on site how the alert works.
We fine-tune with prevention
We remove false alarms and decide with your prevention team whether to extend it to other areas.
Frequently asked questions
What people usually ask us
Does it recognise people?
No. There is no facial recognition or identification. It detects that there is a person and where, not who they are.
Is it used to discipline or score people?
We don't set it up for that: there's no ranking or scoring of workers and we don't store who each alert was aimed at. How the system is used is agreed by you with your workforce and their representatives, and we review it with you.
Does it detect tiredness or mood?
No. Inferring emotions at work is a practice prohibited by Regulation (EU) 2024/1689. We only monitor physical risk situations: an area, a distance, a piece of protective equipment.
Does it replace a certified safety system?
No. It's an additional alert. Your machine safeguards and your prevention plan stay exactly as they are.
Keep reading
AI for factories
All use cases
The twenty-odd use cases, by area of the plant and with their label.
ReadFactory
Computer vision in production
Cameras that watch the line and raise an alert when something isn't right.
ReadBlog
Cameras and AI in the factory: what the law allows in Spain
What the law says about cameras at work and about the AI that analyses them.
ReadA quote, no commitment
Tell us about your line and we'll tell you what we'd set up
A short video call to understand what's stopping you, where and why. Then a written proposal with what we'd do, where the AI would run and how much it would cost. No commitment.