Mapped to a shared offline runtime family and usable with a recording or compatible ESP32 CSI stream.
Intended capability
Pilot this intended outcome through the shared Occupancy estimate family, then validate it against site-specific ground truth: Per-cab occupancy count for dispatch optimization, load pre-warning and after-hours single-rider assurance — a camera-free count inside a space where cameras are least welcome.
This describes the intended outcome. Readiness is shared-family mapped, evidence is class B, and a catalog mapping or recording is not proof of this outcome at a real site.
Solution blueprint
See the environment before installing it.
This exact kit is one of 191 first-class designs. It includes geometry, objects, nodes, wording, scenarios, installation, limitations, and catalog-bound readiness.
No rendered revision is available yet.
Bundled recording
A related Buildings scene
This is one recorded vertical scenario. It is not separate validation of every capability in the catalog.
01 The physics
The cab is a bounded RF cavity: each body adds an independent perturbation direction to the dynamic CSI covariance. Count-to-CSI correlation r=0.9 is proven in rooms; a 2-3m cavity concentrates multipath, sharpening per-person separation while capping the useful ceiling (~8).
02 Shared processing path
Empty-cab eigen-mode baseline (fit per cab, refreshed nightly) -> eigen_mode_count kernel: residual eigen-spectrum rank + energy -> per-trip count stream with door-state gating from the motion band.
This is a capability design path. Components may be shared with other catalog entries; it is not presented as a unique algorithm.
03 Validation plan
WiMANS priors for multi-person counting; own-hardware: one node per cab across 200 trips vs door-camera ground truth, report confusion matrix 0-6 occupants and the saturation ceiling.
04 Commercial hypothesis
For building ops: 'Dispatch by real load, spot the overloaded car before the buzzer, and audit single-rider policy at night — no cab camera.'