Skip to content
CampaignVision
Camera-based crowd analytics

Count people, not phones.

Campaign Vision turns the cameras you already have into real-time crowd analytics for live events — true headcounts, dwell time, zone engagement, and AI-written client reports. No proprietary hardware. Privacy-first and anonymous.

Works with venue IP cameras, a webcam, or a GoPro · Set up in minutes

Built for experiential agencies & brand teams

Works with cameras you already have No proprietary hardware, ever Anonymous by design — no facial recognition Client-ready AI reports in minutes
The problem

Event ROI is guessed, not measured.

Brands now expect the same performance data from a live activation that they get from a digital campaign. Most agencies still can't give it to them.

A clicker and a guess

Headcounts come from a tired staffer with a clicker — or an estimate. There's no honest number to put in the recap.

Photos, not performance

The client debrief is a few nice photos and some social screenshots. None of it shows what actually happened on the floor.

WiFi misses people

Sensor tools count phones, so they miss groups sharing a device, kids, and anyone with WiFi off — undercounting real attendance.

Reports take all week

The post-event report is built by hand in slides, days after everyone's stopped caring. The story arrives too late.

How we fix this for agencies and for brand teams — or see how pricing works.

The engine

Boxes and timers become the client debrief.

The detections you saw above stream into a live dashboard — headcounts, dwell, zones — and an AI-written report when the doors close. That's the whole pipeline.

Live · Sample event — 2 days · 4 zones

Unique reach

4,800

2.6× avg frequency

Visitors

940

▲ 14.6% vs last event

Engaged dwell

1m 28s

Across all zones

Engagement

26%

240 engagers · ≥30s

How did the crowd convert?

12,450 → 240

Impressions 12,450
Reach 4,800
Visitors 940
Engagers 240

Where the crowd stood

Quiet Packed

Top zones

Main Floor 940
Entrance 890
Sample Bar 620

What was peak dwell at the Sample Bar?

Ask

Every box is a person, counted once

Anonymous detection turns the crowd into a true headcount — people, not phones.

Every timer is dwell

The counter on each visitor is attention being measured, second by second.

Nothing is kept

Frames are processed in memory and discarded — no faces used, no video stored.

Runs on cameras you already have · how privacy is enforced

How it works

From a camera to a client report — in three steps.

No installs, no sensors, no data scientists. If you can point a camera at the crowd, you can measure the event.

01

Point a camera

Use the cameras you already have — venue IP cameras (RTSP), a webcam, or a GoPro. No sensors to order, ship, or install. Setup takes minutes.

02

See live analytics

Watch headcounts, dwell time, zone engagement, and density update in real time on a clean dashboard during the event.

03

Get an AI report

When the event ends, generate a client-ready report with the story already written — impressions, engagement, peak times, and zone performance.

See the whole flow in detail →

What you get

Everything you need to prove the event worked.

Robust core metrics every brief asks for — plus advanced capabilities for richer engagement insight.

True headcounts

Count actual people in frame — not phones or devices. The reliable visitor number every brief asks for first.

Dwell time

How long visitors spend at a booth, display, or zone — so you can show engagement, not just footfall.

Zone engagement

Draw zones on your space and get per-zone visits, dwell, and peak times. See which corners of the activation actually work.

Impressions & reach

Walk-by impressions and engaged visitors, reported in the language brands buy in — reach, frequency, and engagement rate.

Density heatmaps

A live and post-event heatmap of where crowds form, so you can place staff, product, and signage where the people are.

Capacity & queue alerts

Set a capacity per zone and get real-time alerts as it fills up — useful for safety, staffing, and queue management.

AI reports & chat Q&A

Auto-generated, client-ready narrative reports — plus a chat you can ask questions of in plain English ("What was peak dwell at the bar?").

Plus cross-camera journeys, an attention signal, and estimated demographics — see the full capability set.

People, not phones

Why cameras beat WiFi sensors.

WiFi and Bluetooth sensors count devices, so they undercount real attendance and can't see engagement. Cameras see the people who are actually there.

Feature comparison: Campaign Vision versus WiFi and sensor-based crowd analytics
Capability Campaign Vision WiFi / Bluetooth sensors
Counts people, not devices WiFi/Bluetooth counts phones — missing groups sharing a device, kids, and anyone with WiFi off. Modern phones also randomize their WiFi identifiers by default, making device counts less reliable every year. Yes No
No device identifiers collected WiFi/BLE tracking works by logging device identifiers (MAC addresses) — personal data under GDPR. Campaign Vision stores derived metrics only, no identifiers of any kind. Yes No
Works with cameras you already have No proprietary sensors to order, ship, or install. Yes No
Dwell-time & engagement quality Yes Limited
Zone-by-zone heatmaps Yes Limited
Anonymous cross-camera journeys Capability Limited
No proprietary hardware to rent Yes No
Set up in minutes Yes No
AI-written client reports Yes No

Comparison is with WiFi- and Bluetooth-based crowd-analytics tools that count devices. The “people, not phones” advantage applies to those device-counting approaches — not to 3D-sensor people-counters or other camera-based computer-vision tools. Curious how our own numbers are defined and validated? Read how we measure.

Privacy-first

Powerful analytics, anonymous by design.

You can give brands real performance data without surveilling their customers. Privacy isn't a trade-off here — it's the default.

No facial recognition

Visitors are distinguished by body shape and clothing for the duration of an event — not by their face. The platform doesn't run facial recognition.

No video stored

Camera frames are processed and discarded. What's kept are derived metrics — counts, dwell, zones — not footage of your visitors.

Anonymous by design

No names, no biometric identity, no personal profiles. Track IDs are temporary and reset — built to support a GDPR/CCPA anonymous-processing posture.

Privacy and compliance posture depends on your deployment and local regulations. We'll help with venue signage and consent guidance during onboarding — this isn't legal advice.

Read the full privacy & data breakdown →

See your next event, measured.

Book a 20-minute demo and we'll walk you through a live dashboard and a sample client report — using a setup like yours.