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: Detects a person hiding or crawling in the raised-floor plenum, ceiling void, or cable vault — the classic camera-blind and PIR-blind spaces used to bypass access control.
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 Datacenter scene
This is one recorded vertical scenario. It is not separate validation of every capability in the catalog.
01 The physics
A crawling/stationary human in a confined void still produces breathing-band (0.1-0.5Hz) CSI micro-modulation and low-velocity Doppler; the plenum acts as a partial waveguide, so links grazing it are strongly perturbed by a body that is invisible to every optical sensor in the room. A 24 GHz radar cone aimed along the void holds static presence via micro-motion energy — a hider who freezes still breathes — and because raised-floor tiles block 24 GHz, the radar mounts inside the void itself, covering the run it is aimed down and nothing more.
02 Shared processing path
Doppler + breathing-band extraction on floor/ceiling-grazing links -> adaptive PCA+MVE anomaly manifold with rolling baseline (void spaces are normally static, so any bio-signature is a huge deviation) -> in-void mmWave radar cone holds static presence: micro-motion energy keeps a frozen hider detected after Doppler goes quiet -> RTI differential imaging to localize along the void.
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
Breathing/presence detection proven (class A) in open rooms — validate in the confined-void geometry: own-hardware raised-floor mockup with a person prone under tiles, measure detection AUC vs. empty plenum baseline; sanity-check features against SenseFi/EHUNAM respiration benchmarks.
04 Commercial hypothesis
Coverage for the spaces your cameras and PIRs physically cannot see — 'nobody hides under the floor of this datacenter' — sold to red-team-humbled security directors of tier-4 facilities. Plus tier: an mmWave radar mounted inside the void holds a hider who freezes. Its limits are stated plainly: the cone covers the run it faces, an informed intruder can route around it, and 24 GHz can be jammed — the WiFi field stays the wide net beneath it.