A campus runs on badges. The access system records every one of them precisely and cannot tell you who was holding the card. For most exceptions that distinction is the entire question.
Thousands of reads a day. The handful that are exceptions get cleared rather than checked, because checking means opening a second system.
Coverage spans buildings and shifts while the security team does not. Consistency of triage matters more than raw detection.
Reception, meeting floors and service entrances see a constant flow of people who are legitimately there but not employees.
Which of these apply to you, and which cameras can carry them, is what the site survey establishes before anything is proposed.
A credential is refused at a door.
The camera at that door captures the moment of the read.
Expired badge, wrong door, or someone trying cards — three very different situations with the same log entry.
Cleared in seconds, or escalated with the clip attached.
A badge opens a secure room outside the window set for that person.
The frame at the reader, with the badge holder on record beside it.
Whether the right person used the badge.
Acknowledged, or escalated to the duty manager with evidence retained.
A door stays open past its timer.
The doorway view for the period it was open.
A delivery, or a door propped for later.
Logged with footage; a repeated pattern becomes something the team can act on.
A person detected in a marked area during hours it should be empty.
The detection frame with the area drawn on it.
Cleaning crew, or an unexplained presence.
Alert to the desk and the on-call phone, with the clip.
Door events are read from an API, a database view or a scheduled export, and built against your system during onboarding.
Standard RTSP and ONVIF, directly or through the recorder, which keeps recording as before.
A reception guard, a building manager and a regional supervisor each see what belongs to them.
The appliance and the evidence sit on site; notifications go outbound only.
Matching a person against a badge holder means holding reference images of badge holders. That is a policy decision with privacy implications, and it needs an answer from your side before it is configured rather than after.
Capabilities are selected per site during the survey. Nothing is on by default, and several depend on camera placement and lighting — which is what the survey establishes.
Identify people, vehicles, objects and security events as they happen.
Add identity, context, movement and event intelligence to live video.
Trigger alerts, sirens, speakers, lights, guard workflows and evidence when action matters.
Camera streams, recording, playback, AI events, evidence clips, alerts, reports, users and roles and camera health — centralised in one appliance inside your premises. Faces, clips and reports stay on site.
Camera count, retention and storage are specified per appliance configuration and confirmed during the assessment.
We do not publish improvement percentages, because none have been measured across a fleet and yours would not match them anyway. What a bounded proof of concept gives you is your own numbers, on your own footage:
No. Pairing a door event with the footage from that moment needs no enrolment at all. Only the badge-versus-person check does, and it can be enabled for specific doors or groups rather than the whole campus.
Never. It reads events and correlates them with video. Door control stays entirely with your access-control system.
Three is usually right — a main entrance, a service or goods door, and whichever door generates the out-of-hours alerts. Three doors that work are worth more than forty configured on assumptions.
What is retained, for how long, and who can see it are decisions you make and we configure. They are written down during the assessment so your own review can approve them before anything runs.
See how PARVEK supports this workflow.
See how PARVEK supports this workflow.
See how PARVEK supports this workflow.
Access and perimeter events across halls, cages and the site boundary, each with the footage that explains it.
Perimeter, restricted zones, yard movement and shift-change activity on a working plant.
Unmanned compounds and remote sites, analysed at the edge where the link is thin or intermittent.
AI surveillance and analytics are technology-assisted and do not guarantee prevention or detection of every security incident or 100% accuracy.