Count the Traffic, Not Just the Crowd
CrowdSense Desktop counts vehicles crossing a line or sitting in a zone and tells a car from a van, a truck, a bus or a bike. Event access roads, drop-off zones and local streets, from cameras you already run.
The Traffic Plan Was Written Before Anyone Arrived
Event traffic plans, council counts and road studies tend to rely on a tube count from last year or a person with a clipboard on the day. Neither tells you how many buses arrived in the last hour, or how long the drop-off zone has been full.
Counting and classifying vehicles from a camera gives you that answer live, by type and by direction, and keeps it as history for the next plan.
What a Camera Can Tell You About Traffic
Counts by direction
A line across a road or an entry counts vehicles each way, so arrivals and departures are separate.
Classified by type
Each vehicle is classed as a bike, car, van, truck or bus, so a shuttle count is not lost in the car count.
Zones and dwell
Draw a zone over a drop-off bay or loading dock and see how many vehicles are in it and for how long.
People and vehicles apart
The same camera counts pedestrians and vehicles separately, which suits shared entries and crossings.
Patterns by hour
Volumes by hour, day and event, for traffic management plans and reports.
Data where you need it
Dashboards and reports in the portal, plus the REST API and webhooks for your own systems.
Count Vehicles in Four Steps
- 01
Install on a Windows PC
Download CrowdSense Desktop and install it on a Windows 10, 11 or Server PC on the same network as your cameras, then sign in.
- 02
Add your cameras
Paste in each camera’s RTSP address, find it over ONVIF, or plug in a webcam. Choose the AI vehicles & people profile, which tells a bike from a car, van, truck or bus.
- 03
Draw lines and zones
Draw a counting line across each lane or entry, and a zone over any bay where dwell matters.
- 04
Watch the traffic
Counts by type and direction appear in the portal live, with hourly and daily reports.
Where to Put the Camera
Detection profile: AI vehicles & people. Any IP camera that streams over RTSP works, with ONVIF optional, and so does a USB webcam.
For vehicles, use the AI vehicles & people profile and a camera angle between 20° and 90°: angled or side-on, not straight down.
A vehicle needs to fill at least 4% of the frame’s width seen from the front or back, or 10% seen side-on.
A side-on or slightly raised view separates vehicles best. Avoid a view where queued vehicles hide behind each other.
Bad weather and night reduce what any camera sees. Check the picture at the hours you need to count.
Pay per Camera, per Event or per Month
All prices in Australian dollars, excluding GST. One feed is one camera stream.
Event pass
$195
per feed, per event
One event is one primary location, one name and branding, up to 5 days. Feeds go live 14 days before the first day for set-up and testing; dashboards and the post-event report stay readable for 3 months after.
Always-on
From $39
a feed a month, yearly plan
For venues that count every day. Month to month it is $69 a feed for up to 9 feeds, and less at volume. Every band is on the pricing page.
Free trial
14 days
up to 4 feeds
A card is taken at sign-up. Nothing is charged until day 15, and you can cancel any time before then.
No cameras where you need them? For events, we hire Vision Nodes and the crew to install them.Get an events quote.
Who Counts Vehicles With It
Event traffic managers
Arrivals, shuttles and rideshare at the access roads and drop-off zones, live on the day.
Councils
Local street volumes by type for planning, without a tube count every season.
Venues and precincts
Delivery, coach and car movements at service entries and forecourts.
Traffic consultants
Classified counts from existing cameras for audits and studies.
Video Stays on Your PC. Only the Numbers Leave.
CrowdSense Desktop analyses the video on the Windows PC it is installed on. What reaches the portal is text: a line was crossed, a zone filled, a queue grew. No video and no images are uploaded, and nothing sent can identify a person.
The software detects people and vehicles so it can count them; it does not identify anyone. No facial recognition, no biometric identification of people. Ever. Your cameras, your recordings and your footage stay on your site, under your control.
Vehicle counting, Answered
Which vehicle types does it recognise?
The AI vehicles & people profile classes each vehicle as a bike, car, van, truck or bus, and counts pedestrians separately.
Can it read number plates?
No. It counts and classifies vehicles. It does not read plates or identify any vehicle or person.
What camera angle works best?
An angled or side-on view between 20° and 90°, where vehicles do not overlap much. A vehicle needs to fill at least 4% of the frame width from the front or back, or 10% side-on.
Can it measure speed too?
Yes, as an estimate from two calibrated lines. See vehicle speed detection.
What if we have no cameras on the road?
For events, we hire Vision Nodes and the crew to set them up. Start with the events quote.
Try It Free on Your Own Cameras
14 days free on up to 4 feeds. Install on a Windows PC, add a camera, draw a line.
