Hospitality · Proven
QueueSense — live queue length and wait-time
It counts the line and tells you the wait — no cameras.
Demonstrated on real public research data.
How it works
People standing in a queue soak up and stir the WiFi crossing that corridor. More people means more stirring, and different node pairs cross different parts of the line. So the system reads both how long the queue is and where it bunches — and turns that into a predicted wait.
In the physics: Human bodies (~60% water, high eps_r) attenuate and scatter 2.4/5GHz links; each added body in a link's Fresnel zone shifts multipath amplitude variance and adds low-frequency Doppler from postural sway (0.1-2Hz). Spatial ordering along the queue corridor is recoverable because different link pairs cross different queue segments.
See it work
This is real pipeline output for Hospitality, replayed. The exact reading depends on your room.
Go deeper
How the field becomes an answer
How we prove it
WiMANS multi-person counting for the count head; own ESP32 mesh strung along a real cafe queue with ground-truth video annotation for the spatial/wait-time layer.
Who it is for
Live wait-time and 'open a second till' alerts with zero cameras — for the retail store-ops manager measured on conversion and walkout rate.
runtime Runs today in LatentField 2.0 as occupancy_estimate
The matching solution
Complete first-room estimateFloor & Bar Pulse3 nodes · ~$130 parts · 90 min Request kit, subscribe, or set up →Compatible DIY hardware options
120 min · advanced