Automotive · Proven
Cabin Census — Per-Car Occupancy for Transit
Counts riders in every bus and train car — no phones, no cameras.
Demonstrated on real public research data.
How it works
Each body on board soaks up and scatters a little of the signal. More riders, more effect — a relationship already measured to be very reliable. It keeps working in tunnels and in standing-room crush loads, exactly where phone-counting and cameras fail.
In the physics: Each human body absorbs and scatters 2.4/5GHz energy; aggregate body count shifts mean CSI attenuation and motion richness, while spatial distribution shapes which RTI voxels attenuate. Count-to-CSI relationship is already demonstrated at r=0.9.
See it work
This is real pipeline output for Automotive, replayed. The exact reading depends on your room.
Go deeper
How the field becomes an answer
How we prove it
WiMANS multi-person and OPERAnet occupancy tasks for the counting core; own pilot: one instrumented commuter car vs APC infrared gate counts over 2 weeks.
Who it is for
GDPR-clean crowding telemetry feeding real-time 'which car is empty' passenger apps — sold to transit authority operations and passenger-experience directors.
runtime Runs today in LatentField 2.0 as occupancy_estimate
The matching solution
Complete first-room estimateCabin Presence Node1 nodes · ~$40 parts · 45 min Request kit, subscribe, or set up →Compatible DIY hardware options
45 min · intermediate