Home · Proven

Occupancy Integrity Auditor (Vacation Rentals)

Knows how many people are really in your rental — no cameras, ever.

Proven Proven live in runtime

Demonstrated on real public research data.

Every moving person stirs the WiFi signals in a room a little more. The system measures how much the signal is stirred, and that tracks the number of people very closely. It counts bodies without ever seeing faces — a number, never a picture.

In the physics: Each additional moving body adds independent scattering paths and Doppler energy; aggregate CSI variance and multipath richness scale monotonically with occupant count. LF2 occupancy count already achieves r=0.9. Count is a statistic, not an image — privacy-preserving by physics.
Preparing the recorded fieldLoading real LatentField pipeline output…

This is real pipeline output for Home, replayed. The exact reading depends on your room.

Bring this into the real roomHome Presence & Intrusion2 sensing nodes · ~$90 parts · about 45 min
Go deeper

How the field becomes an answer

Doppler activity energy (stage 2) + CIR path-count richness (stage 1) regression on anomaly-manifold coordinates (stage 3) compartment Kalman smooths per-room counts and CUSUM flags sustained over-occupancy vs a booking-derived setpoint (stage 6).

How we prove it

WiMANS (multi-user, labeled counts) and OPERAnet for cross-validation; field pilot in 10 rental units comparing nightly count curves against booking manifests.

Who it is for

"Party detection that guests can't find and regulators can't object to." For Airbnb/Vrbo host-tool platforms and rental property managers.

runtime Runs today in LatentField 2.0 as occupancy_estimate

Complete first-room estimateHome Presence & Intrusion2 nodes · ~$90 parts · 45 min Request kit, subscribe, or set up →
Compatible DIY hardware options
Prosumer DIY$18–35

45 min · intermediate

Prosumer Pro (paired node)$110–150

60 min · intermediate

← All Home capabilities