Crowd counting
In a crowd, people hide each other.
Your product has to count heads it can only partly see, and warn you before the crowd gets too big. We do it with crowd density estimation, and help you build it in.
Last updated
Request a demo
How it works
From your camera to a live headcount
Counting one person at a time fails when people overlap and fill the view from near to far. Crowd density estimation counts the crowd as a whole instead.
Your system: Crowd
Everyone in view, near and far.
Your system: Camera
Your camera, mounted high above the space.
Our solution: Density estimation
Maps how closely people stand, so people it can only partly see still count.
Our solution: Headcount
One live count, updated as people come and go.
Your system: Crowd dashboard
Warns your staff when the count reaches your limit.
What it handles
Counts people, not posters
We tune it to your site, then check the headcount against hand counts of frames from your camera.
What it counts
- Dense crowds
- People packed closely together.
- Light crowds
- A few people spread across the view.
- Near and far
- People at different distances from the camera.
- Growing and shrinking
- Crowds that build up and thin out.
- High, wide views
- Cameras high above a hall, stand or concourse.
What it ignores
- Pictures of people
- Posters, signs and screens showing people.
- Bags and coats
- Objects that can look like heads from above.
- Shadows
- Shadows cast across the floor.
- Stage lighting
- Spotlights and house lights dimming at events.
- Empty seats
- Rows of seats that can look like a crowd.
Applications
Where it's built in
Your product gets a live headcount, the peak and an alert at your limit.
Crowd cameras
Crowd levels at entrances, stands and stages.
Occupancy sensors
Live headcounts for platforms and gates.
Building management systems
Crowd alerts for stores, walkways and food courts.
Evaluation
Interested in this solution?
Get in touch with our engineering team to evaluate it for your system.
Qualification note placeholder: the legal qualification for this solution, kept word for word on each of its pages.
Other use cases
More on computer vision
Five more ways we put computer vision to work.
Object tracking
Detects the objects you choose, tracks each one and counts those in a zone or crossing a line.
Intrusion detection
Person detection raises an alert when someone enters the area, and records a clip of each event.
Driver monitoring system
Tracks head pose and eye state to score drowsiness and distraction, and spots phone use and smoking.
Tennis pose estimation
Estimates the player's pose and reads each movement over time to count forehands and backhands.
Emotion tracking
Classifies expressions as happy, sad, angry or surprised, so your product can respond.
