Platform

Everything your cameras can see and do.

Ten modules, one platform, one live wall — each running on the feeds you already have, each drawing as an overlay on live and recorded video.

Number-plate recognition result on a detected plate

ANPR & Vehicle Intelligence

Detects and reads number plates across multiple regional formats, corrects misreads and validates against real state codes, then enriches each read with vehicle type + dominant colour and — optionally — owner details via an RC/VAHAN lookup. Entry and exit reads pair into journeys.

multi-region readowner lookuptype + colourallow / deny listgate control

PPE & Safety Compliance

Hard-hat / helmet detection with a bare-headed-worker check, gated to the zones where PPE is actually required so you get signal, not noise.

helmetzone-gatedforensic trail

Parking Management

Slot-occupancy detection fused with ANPR into a single parking session: which vehicle sits in which slot, for how long, with overstay alerts.

occupancydwell timeoverstay

Traffic Violations

Triple-riding, no-parking-zone entry, wrong-way and over-speed detection — each violation named to the offending plate and owner.

triple-ridingno-parkingwrong-wayover-speed
People detection and counting on a live feed

Face Recognition & Enrolment

Enrol employees from reference photos, run watchlists, and blur faces for privacy — architected to stay on-prem and licence-clean.

enrolmentwatchlistprivacy blur

Weapon & Threat Detection

Firearm and edged-weapon detection with a two-step confirm before a critical alert fires — tuned to minimise false alarms.

firearmknife2-step confirm
Object detection on a live feed

People & Object Analytics

Detect and count people and objects, estimate demographics, draw intrusion and counting zones, and build occupancy heatmaps.

countingzonesheatmapsdemographics
Live wall of camera feeds

Recording & Forensic Search

24/7 continuous recording with motion-aware storage tiering, plus fast indexed forensic search across the whole archive.

continuoustieringsemantic search

Mobile App

On-device object & gender detection that runs entirely on the phone, plus "Go Live" — turn any phone into a camera that streams straight to the wall over a secure relay.

on-device AIphone-as-camerasecure relay

Alerts & Integrations

Every event fans out to webhooks, email and gate/barrier controllers in real time.

webhooksemailgate control
ANPR · live recogniser

Read the plate. Know the vehicle.

The number-plate recogniser runs on-prem across regional formats, corrects misreads and validates real state codes — then pairs each read with owner and vehicle details.

Detected number plate HR26 DK 8337 with the ANPR bounding box
Live plate read
HR26DK8337
RegionIndia (in) — auto-detected Recogniser92% exact · 91% char-accuracy on real-world plate imagery Ownerresolved via RC / VAHAN lookup Vehicletype + dominant colour Actionallow / deny · gate control · named alert

Plate text + region above are live output from the on-prem recogniser. Owner & vehicle fields are shown illustratively — a vehicle-facing gate camera supplies them on site.

How it works

Feed in. Intelligence out.

Connect

Your cameras, connected

A media gateway pulls one warm stream per camera from your NVRs — shared by the live wall, recorder and every AI module, so the NVR only ever serves one session.

Detect

Models on your hardware

Licence-clean AI models run in real time on-prem — CPU-only where needed — writing detections that overlay live and recorded video alike.

Act

Alerts, control, search

Named notifications, gate triggers and webhooks fire instantly; continuous recording + forensic search keep the evidence.

Good to know

Common questions

Does my footage go to the cloud?

No. VisionVault is self-hosted — every frame and every model runs on hardware you own. There are zero cloud dependencies, which is exactly why privacy-sensitive sites choose it.

Do I need special cameras?

No. It works with your existing IP cameras and NVRs over standard IP. No rip-and-replace.

What makes the AI "licence-clean"?

Every model is trained on commercially-usable data with verifiable provenance — no non-commercial, GPL or unverifiable weights. That means you can deploy it commercially without licensing risk.

Can it run without a GPU?

Yes. Core detection, ANPR and PPE run CPU-only; heavier workloads scale with a GPU when you have one.

How do alerts reach my other systems?

Every event is published as a notification that auto-fans to webhooks, email and gate/barrier controllers — so you can wire VisionVault into what you already run.

Want it running on your feeds?

We'll set up a live demo on cameras like yours and walk you through the modules that matter to your site.

Request a demo →