Solutions / License Plate Recognition
License Plate Recognition (LPR / ANPR)
Every Plate Read. Every Read Kept. Every Question Answerable.
Plates are detected and read as text from the cameras already installed -- gates, lots, streets, yards. A watchlist match raises an alert the moment it happens, and every read is retained, so the vehicle you start caring about next month is already in the record.
The plate pipeline
Trusted where the stakes are high
Pick your estate, see what the plates already tell you
The plate is the thread. A partial plate from a witness becomes a search across every camera and every day the estate has seen.
- Watchlist alerts. A plate of interest raises an alert on sight, with the frame attached.
- Search after the fact. Unmatched reads are still recorded -- yesterday's traffic is searchable today.
- Evidence, not screenshots. Reads and footage held with chain of custody for the case that follows.
Depots, garages and corridors. Vehicle movement across a distributed estate, read continuously instead of reviewed occasionally.
- Fleet-aware yards. Arrivals and departures logged as searchable text, per camera and per day.
- Incident-to-vehicle. An event on the platform ties to the plates seen around it.
- Runs on the estate you have. RTSP and ONVIF over existing cameras and VMS.
Facilities, motor pools and perimeters. Who came and went, answerable without pulling tapes.
- Restricted-area vehicles. Zone rules raise events for vehicles where none should be.
- Audited access. Who searched what, on the record.
- Inside the boundary. On-premises or fully air-gapped where policy requires.
Gates, docks and yards. The vehicles entering a site logged and answerable, without a guard writing plates on a clipboard.
- Gate activity as data. Every arriving plate read and timestamped automatically.
- Unexpected vehicles. Alerts for plates that should not be on site, by list and by zone.
- Ties into workflows. A read can trigger the workflow you define -- log, notify, escalate.
Parking structures and perimeters. Vehicle presence across a campus, searchable when security needs it.
- After-hours movement. Vehicles where and when none are expected.
- The car in question. A reported vehicle found across days of footage in seconds.
- Retention by policy. Reads and footage aged out on the schedule you set.
What You Get
What plate intelligence on existing cameras gives you
Plates become searchable text
Detection reads the plate, not just the vehicle, so a plate is queried like a record rather than hunted for frame by frame.
Watchlists that alert on sight
A per-class text watchlist raises an alert the moment a plate of interest is read, with confidence thresholds you configure per class.
Everything kept, not just matches
The watchlist governs alerting, not capture. Unmatched reads are retained too, so an investigation can look backwards, not only forwards.
The vehicle, followed
An object keeps its identity as it moves through a scene and between cameras, so one vehicle's path is assembled rather than guessed.
Reads in context
Vehicle detection, zone rules and event correlation sit alongside the plate read, so a read is an event with a place and a moment, not a row in a log.
A map, not a list
Cameras with coordinates plot geographically, so reads are explored by location across an estate.
From read to record
Footage and reads around an event are preserved with chain of custody and audited access, ready for the case, the dispute or the audit.
Runs where the footage must stay
On-premises, private cloud or fully air-gapped with self-hosted inference -- plate data never has to leave your boundary.
How It Works
Read, alert, investigate
Read
Plates are detected and recognised as text on live streams from existing cameras, over RTSP and ONVIF, with every read retained.
Alert
A watchlist match raises an alert the moment it happens, with the frame and location attached, and can trigger the workflow you define.
Investigate
Search the full history of reads in plain language, follow a vehicle across cameras, and hand over an evidence record that survives scrutiny.
Products Inside
The products inside
Nexus
Enterprise content platform
The record underneath: storage, search, retention, audited access and chain of custody for reads and footage.
Explore Nexus →AI Live Insight
Real-time video analytics
Plate reading, watchlists, vehicle detection and tracking on existing cameras over RTSP and ONVIF.
Explore AI Live Insight →AI Intelligence Hub
Agentic AI platform
Event-driven workflows on a read or a match, and natural-language search across the history.
Explore AI Intelligence Hub →FAQ
License plate recognition, asked and answered
What is license plate recognition software?
Software that detects licence plates in camera footage and reads them as text, so a plate becomes something you can search, alert on and retain -- rather than an image someone has to find by scrubbing. The same capability is called LPR in North America and ANPR elsewhere; this is both.
Do we need special LPR cameras?
No. Recognition runs on streams from the cameras already installed, over RTSP and ONVIF, alongside the existing VMS or NVR. Read reliability still depends on what the camera can see -- angle, lighting, distance and resolution matter, and a camera positioned for general surveillance will not match a purpose-mounted gate camera.
How do watchlists work?
Plates of interest go on a per-class text watchlist. When a read matches, an alert fires with the frame attached, and confidence thresholds are configurable per class. The watchlist governs alerting only -- every read is captured regardless, so you can search history for a plate that was never listed.
Can it follow a vehicle across cameras?
Yes. Re-identification keeps an object's identity as it moves through a scene, disappears behind an obstruction, or passes from one camera's view into another's, so a vehicle's path across an estate is assembled rather than reconstructed by hand.
Can we enroll a vehicle by its appearance rather than its plate?
Not today. Live recognition galleries currently match face subjects; vehicle and object enrollment are planned. Vehicle alerting works through the plate text watchlist, and vehicle detection and tracking work on appearance without enrollment.
Is this a parking management system?
No. Parking management -- permits, payments, enforcement workflows -- is a dedicated category with its own systems. This is the recognition, alerting and investigation layer; a read can be passed to other systems through APIs and workflows.
What happens to the data, and who can see it?
Reads and footage are held under role-based access with every access audited, retention aged by the policy you set, and the record carries chain of custody for use as evidence. Deployment can be on-premises or fully air-gapped, so plate data stays inside your boundary.
Can a read trigger something automatically?
Yes. A read or a watchlist match can trigger an event-driven workflow -- log it, notify someone, escalate, or pass a validated event to an external system through your integrations. What runs is defined by you, with human approval where you want it.
How accurate is it?
Accuracy is governed by per-class confidence thresholds you control, and it inherits the physics of the camera: a clean, well-lit, well-angled view reads reliably; a distant plate at night reads worse. Low-confidence reads can be routed to a person rather than acted on.
Point it at one gate for a week
Pick a camera that sees vehicles. We will run recognition on your own footage and show you what a week of reads answers.