operations analytics

Occupancy analytics for space utilisation decisions

In short

Occupancy analytics reports how intensively a space is used over time, derived from directional counting at its entrances. Where occupancy monitoring raises live threshold alerts, occupancy analytics answers the planning question: how full is this space, how often, and how does that compare with its design capacity.

Request a pilot Send a sample video

Conceptual illustration of multi-site operational oversight. AI-generated conceptual image, not a customer deployment.

Scope

What this analytic does, and what it does not

What it detects

Occupancy level per space sampled across the day
Peak, median and sustained utilisation per period
Hours per week a space spends below a utilisation floor
Utilisation against design capacity per space

What it does not guarantee

An exact head count at any instant
Correct figures where a bounding door is not counted
Identification of who used a space or for what purpose
A basis for individual performance measurement

The problem

What customers are actually dealing with

These are the situations that lead teams to look at this analytic in the first place.

Meeting rooms are booked and unused, and the booking system cannot tell the difference.
A property team is asked to justify floor space with no measured utilisation data.
Cleaning and HVAC run to a fixed schedule regardless of whether a floor was used.
Hybrid working changed demand patterns and every space decision is now argued from opinion.

How it works

Detection workflow

Every event carries the rule that produced it, so an operator can see why they were alerted.

1

Count at boundaries

Directional counting at every door bounding each space produces entry and exit events.
2

Derive occupancy

A running occupancy figure is maintained per space and sampled at a fixed interval.
3

Re-baseline

Scheduled resets at known-empty times limit accumulated drift.
4

Aggregate

Samples are aggregated into utilisation statistics per space per period.
5

Publish

Utilisation series and capacity comparison are written to the dashboard and exported for planning.

Configuration options

Space definitions with their bounding doorways and design capacity
Sampling interval for the utilisation series
Scheduled reset times per space
Working-hours schedule so out-of-hours samples are excluded or reported separately
Utilisation floor and target bands per space type
Grouping of spaces into floors, buildings and portfolios

Alert quality

How irrelevant and duplicate alerts are reduced

No video analytic eliminates false alerts. These are the mechanisms that reduce them, and the residual rate is measured on your own cameras.

Scheduled resets at reliably empty times are the primary control on drift in a derived occupancy figure.
Sampling and aggregating over weeks removes single-day anomalies that would mislead a space decision.
Reporting utilisation bands rather than instantaneous counts reflects the accuracy the method can actually support.
Availability is reported alongside utilisation so gaps are visible rather than read as low usage.
Any uncounted door invalidates the space figure; completeness is checked before a space is reported.
Even with complete coverage, occupancy remains a derived figure carrying accumulated counting error between resets, and utilisation percentages should be read as bands rather than as exact measurements.

Prerequisites

Camera requirements and environmental limits

Camera suitability decides more of the outcome than any software setting. These are assessed per camera before commitment.

Camera requirements

A counting-suitable camera at every door bounding each measured space
Overhead or steeply angled views at each threshold
Adequate lighting during all hours included in the reporting window
Stable mounting across the whole measurement period, since a moved camera breaks comparability
Coverage of the full door width at each boundary

Environmental limitations

Occupancy is derived from counting and accumulates error between resets.
Small rooms with a single door are measured far more reliably than large open floors with many access points.
Utilisation says nothing about the value of the activity taking place in the space.
Comparisons between spaces are only fair where boundary coverage is equally complete.

Delivery

Alerts, evidence and where they land

Event and evidence fields

Space name, type and design capacity
Sample interval and timestamp
Occupancy at sample
Utilisation against capacity
Time since last reset
Boundary coverage completeness

VMS integration

Utilisation is a planning output rather than an operator alarm and is consumed on dashboards and in property reporting tools. Where the same space also needs live capacity alerting, occupancy monitoring provides those events.

See compatibility states →

Deployment options

Edge processing per building so only aggregate utilisation leaves the site
On-premise processing where doorway cameras already aggregate locally
Multi-site deployment for portfolio-level comparison across buildings

Compare architectures →

Measurement

Dashboard metrics and pilot acceptance criteria

Acceptance thresholds are agreed with you before the pilot starts. This site publishes no benchmark figures, because they do not transfer between sites.

Dashboard metrics

Utilisation percentage per space per interval
Peak and median occupancy per space per week
Hours below the utilisation floor
Booked-versus-occupied comparison where booking data is joined
Floor and building rollups
Boundary camera availability per space

Measurable pilot criteria

Occupancy drift measured between known-empty resets across a full working day
Counting error per bounding door against a manual count
Utilisation stability across two comparable weeks
Documented boundary completeness for every reported space
Agreement with an independent spot audit at sampled times

Governance

Privacy and governance

Utilisation is an aggregate measure of a space, not of the people in it.
No identity is established and the data must not be used to monitor individual employees.
Where spaces are staff areas, consultation and employee monitoring obligations commonly apply and should be addressed before deployment.
Aggregate series can be retained for property planning without retaining imagery.

Frequently asked questions

How is this different from occupancy monitoring?

Both derive occupancy from doorway counting. Occupancy monitoring is a live control that alerts when a space approaches a limit. Occupancy analytics is a planning output that reports how intensively spaces are used over weeks and months.

Can we use it to check whether individuals are at their desks?

No, and it should not be used that way. The output is an aggregate space measure with no identity attached. Using workplace analytics for individual monitoring raises significant legal and employee-relations issues and is outside the intended purpose.

Is it better than a desk sensor?

It answers a different question. Desk sensors measure a specific position; doorway-derived occupancy measures a whole space with fewer devices, using cameras that often already exist. Many estates use both, at different granularities.

Keep reading

A controlled pilot establishes what this analytic actually does in your environment, against acceptance criteria we agree before it starts. Send a sample video first if you would rather see an assessment before committing to a pilot.