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 Through-wall presence family, then validate it against site-specific ground truth: Non-contact fill-level measurement of water heaters, IBC totes, chemical drums, and silos located in closets or behind walls — no sensor on the vessel.
This describes the intended outcome. Readiness is shared-family mapped, evidence is class C, 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 Frontier scene
This is one recorded vertical scenario. It is not separate validation of every capability in the catalog.
01 The physics
The liquid column is a massive dielectric body: paths crossing the vessel below the fill line acquire large excess delay and attenuation (water eps_r~80, lossy), paths above the line barely change. The air/liquid interface is also a strong specular reflector whose height moves the geometry of a reflected tap. Fill level maps monotonically to which CIR taps are delayed/attenuated.
02 Shared processing path
Stage 1 CIR sparse recovery tracks the delay/amplitude of the vessel-crossing path family -> Stage 5 NeRF field reconstruction inverts these into a vertical eps_r profile of the vessel volume (fill height = eps_r step) -> Stage 6 compartment Kalman smooths level dynamics and CUSUM flags abnormal drain/fill rates (theft, leak, stuck valve) -> Stage 7 axis discovery calibrates the level axis by one observed fill/drain cycle.
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
Own-hardware: 200L water tank behind a drywall panel, ESP32 mesh, fill/drain in 10% steps with float-gauge ground truth; target <10% full-scale level error and monotonicity across furniture rearrangement.
04 Commercial hypothesis
'Wireless level gauges you never install' — for facilities/ag/light-industrial operators monitoring tanks, totes, and fuel drums with the site WiFi mesh.