Automotive · Strong theory
Seat-Level Occupant Classifier — Smart Restraint Input
Knows each seat holds an adult, a child, or just a bag.
The physics is solid; our own validation is scheduled.
How it works
Living passengers breathe, and their breathing marks the signal at their seat — a grocery bag never does. Children are smaller and breathe faster than adults, and both differences show in the signal. That is enough to set airbags and belt reminders correctly, without weight mats in the seats.
In the physics: Living occupants produce breathing-band micro-Doppler localized to their seat zone; adults vs children differ in scattering cross-section (body-size-dependent attenuation in RTI voxels) and breathing frequency (children breathe faster, 0.3-0.7Hz). Objects attenuate but produce zero physiological modulation.
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 for multi-person zone separation; own-hardware: 4-seat cabin matrix (adult/child/object/empty x seat position), 20 subjects, confusion-matrix target >90% per-seat accuracy.
Who it is for
One RF stack replaces four seat-mat sensors for occupant classification and belt reminders — sold to interior-systems Tier-1s chasing per-vehicle BOM reduction.
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