AI Security Camera Dashboard

Workforce analytics
from the cameras you already own.

AI Security converts existing CCTV footage into an auditable record of how working time was spent — per person, per hour. Time at the workstation, time on a phone, time away from the desk.

  • No new hardware
  • No wearables
  • Works on footage you already have
Depth pass Tracks 0 AI Security Conf ——
Behaviour KPIs
MOMohan
Working100%
On phone0%
Away from desk0%
Scan summary
People found2
Peak at once2
Frames read225
Registered1
Analysed100%
80Object classes detected
512-dFace signature per person
4Behaviour states
0New cameras required
Capabilities Delivered in a single scan

One upload. A complete record.

Submit a clip and AI Security returns identified people, detected objects, per-person timings and a written summary.

Recognise your people

Register a face once and AI Security reports that person by name in every future scan, with a margin test so a near-miss stays unknown rather than becoming a wrong name.

Hours, not impressions

Working, phone and away time per person, as numbers you can put in a report and trend across weeks rather than a feeling about how the day went.

Objects as well as people

Eighty object classes with unique-track counting, so a single chair observed for an hour is counted once, not ten thousand times.

A summary in plain English

Every scan closes with a short written read-out of what happened, so the outcome of a shift is legible without interpreting a table.

Verify every figure

An annotated video comes back with every detection drawn on it, so any number on the dashboard can be checked against the footage that produced it.

Stays in your tenant

Footage and face data never leave the cloud environment you already control, and sign-in is handled by your own identity provider.

Measurement Mutually exclusive states

Four states. Every frame accounted for.

Each frame a person appears in resolves to exactly one state, so the totals always reconcile against the time they were on camera.

Working

At the workstation

Holding one position at a desk for a sustained stretch, with no phone in hand.

On phone

Handset detected

A phone resolved inside the person's own frame, counted wherever they are standing.

Away

Off the workstation

On camera but anchored nowhere — between desks, standing, passing through.

Static

Integrity check

Absolute stillness over minutes, so a jacket left on a chair is never recorded as a person.

Method How the measurement is derived

It never looks for the chair.

Most systems get this wrong in a way that quietly inverts the answer.

The trap

The intuitive rule is that a person overlapping a chair must be seated. On a real ceiling-mounted camera that collapses immediately, because the chair someone sits on is hidden behind their own desk. Tested against live footage, the overlap test held for none of the seated samples — while every empty chair across the room detected perfectly.

A system built that way reports the people who are working as absent, confidently.

The approach

AI Security decides a person is at a workstation when their position stays pinned to one spot for a sustained run. The reference point never drifts toward them, so walking can never be mistaken for settling in. It survives full occlusion of the chair, the desk and the lower body, and needs no per-camera configuration.

Where you want precision instead of inference, define explicit seat zones with SEAT_ZONES and they take priority immediately.

Identity

Unrecognised faces are grouped by similarity, so eight sightings of one visitor count as one person, not eight — which is what makes "how many strangers came through" a number you can trust.

Consistency

Every threshold is defined in seconds rather than frames. A fast scan that samples across a clip and a deep scan that reads every frame return the same verdict — confirmed by running both against identical footage and comparing totals.

Process From footage to reporting

Five stages, fully automated.

1

Ingest

Upload a clip, paste a link, or pick stored footage. Awkward codecs are converted without asking.

2

Partition

Long video is divided into segments, each dispatched as an independent job.

3

Resolve

Segments process in parallel — detection, identity and state — streaming previews as they land.

4

Reconcile

Results merge, faces re-cluster across the whole video, and per-person hours are totalled.

5

Report

A written summary, an annotated video, and a stored record you can trend over weeks.

Begin with footage you already hold.

No pilot programme, no installation and no change to how your teams work. A single clip is enough to evaluate the figures AI Security produces.

Get started

AI Security Camera Dashboard

AI Visualz