Detects two or more people passing through a secured door on a single credential (piggybacking), one of the most common access-control breaches, and alerts security in real time. Runs on any camera covering a door, turnstile, or mantrap with no extra hardware.
Visylix Tailgating Detection watches secured entrances for piggybacking, where a second person slips through a door, turnstile, or mantrap on someone else credential. It is one of the most common access-control breaches and is invisible to the badge system alone. Using any camera that already covers the entry point, the AI counts how many people pass through during a single access event and raises an alert in real time when more people enter than were authorized. It understands the direction of travel so it only reacts to people actually entering, lets you configure how many people and how much time count as a violation, and needs no integration with your badge or turnstile hardware to work.
Core capabilities of the Tailgating Detection model.
Flags the moment a second person follows an authorized entrant through a secured door, so security can respond immediately.
Runs on any existing camera covering a door, turnstile, or mantrap with no extra hardware to install.
Understands the direction of travel and reacts only to people actually entering the secured side.
Set how many people and how much time count as a violation to match each entrance.
Detects tailgating from video alone, with no integration into your badge or turnstile hardware required.
Raises an alert with a snapshot through dashboard, SMS, email, and webhook notifications.
Real-world applications for Tailgating Detection.
Stops unauthorized entry at the front door of offices, labs, and secured buildings.
Protects server halls and cages where a single unauthorized entrant is a serious breach.
Enforces one-person-per-credential passage at turnstiles and mantraps.
Guards doors into cash rooms, evidence stores, and other restricted zones.
Performance and deployment details.
Add Tailgating Detection to your video pipeline in minutes.
Assign the model to specific cameras with zone definitions and sensitivity settings through the web UI or API.
The model processes video frames in real time, generating structured detection events with bounding boxes and metadata.
Receive instant alerts via webhooks, trigger automated workflows, or query detections through the REST API.
Explore other computer vision capabilities.
Talk to our team to see this model in action on your video feeds.