Unauthorized entry detection
Detect a person crossing a line or entering a restricted area — an instant signal that a boundary has been breached.
A boundary breach caught the moment someone enters
The "Unauthorized entry" scenario detects a person crossing a defined line or entering a closed area. It is a core control for perimeters and restricted zones — machine rooms, switchgear, high-risk storage, or areas taken out of service during work.
Automatic detection lets you react the moment the boundary is crossed — before an incident — instead of reconstructing the breach from footage afterwards.

Reaction at the moment of crossing
A detection raises an alert and andon signal the instant a person crosses the line of the watched zone.
Configurable lines and zones
You define the lines and closed areas yourself — detection runs only where the boundary matters.
Around-the-clock monitoring
Detection runs continuously, 24/7, with no fatigue or breaks — every shift is covered.
Example use and privacy
Around a shut-down production line or a service area the camera spots a person entering a no-go zone and immediately triggers a light signal and a notification to the guard, while the event lands in the report.
The system recognises only the boundary-crossing event, not the identity of the person — it performs no biometric identification or face recognition.

No personal identification
Detection is about an event and an area, not personal data — no face recognition.
A full event trail
Every crossing is logged with time and zone, ready for analysis in security reports.
Protecting people and the site
An alert on entry into a no-go area improves worker safety and protects the plant perimeter.
System
Our system is intuitive, but you can always count on us
We help your team work more efficiently every day.
Documentation
Customer support
Integrations
FAQ
Frequently asked questions
- A person crossing a defined line or entering a closed area. The system recognises the boundary-crossing event itself, not the person's identity.
- No. Detection is about an event and an area — there is no biometric identification or face recognition.
- Yes. The lines and detection areas are configurable, so the system reacts only where the boundary matters.
- The event triggers an alert, an andon signal, a dashboard entry and a report line; it can also trigger an action on a machine controller.
- Yes. The model runs at the edge on the vision server, so the reaction happens as the crossing occurs.
- Standard industrial IP cameras watching the zone boundary; the image is analysed locally by the vision server.
- No. Analysis happens at the edge — only events leave the site, not the video stream.
- Yes. Integration gateways link events to AndonCloud and PLC controllers — for example a light signal or a security notification.
The “Unauthorized entry detection” scenario flags a person crossing a defined line or entering a closed area. It is a core control for perimeters and restricted zones — machine rooms, switchgear, high-risk storage, or areas taken out of service during work.
In the AndonCloud platform, industrial cameras watch the zone boundary while vision servers run the SAM3 model with the prompt “person crossing restricted line”. When a crossing is detected, the integration gateway turns it into an event: an andon signal, an alert to security, and an entry in dashboards and reports, enabling an immediate response and later analysis.
For example, around a shut-down production line or a service area the system notifies the guard that someone has entered a no-go zone, improving both worker safety and site protection. The system detects only the boundary-crossing event — not a person's identity — and performs no biometric identification.
Contact
Contact us
If you have any questions, talk to our expert
We will respond within the next business day
sales@andoncloud.comPhone
Monday - Friday; 9:00 - 17:00
+48 71 340 70 15Marcin Wierzbicki
During the meeting, we will present the product and help you configure the system in your company efficiently and quickly. Our team is at your disposal.
Newsletter
Sign up for the newsletter
Want to stay up to date? Sign up for our database.
By subscribing to our newsletter, you agree to our Privacy Policy and to receive updates from our company.
