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: Device-free detection and coarse tracking of a person moving in the yard, porch, or hallway outside the home, before any door or window is touched — an invisible pre-entry tripwire with approach-vector estimation (walking toward a window vs passing on the sidewalk).
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 Home scene
This is one recorded vertical scenario. It is not separate validation of every capability in the catalog.
01 The physics
A human body (~60% water, eps_r~50 at 2.4/5 GHz) attenuates and scatters the RF links between mesh nodes even through drywall and brick; crossing a link changes per-link RSS/CSI attenuation, and torso motion imprints 1-3 Hz body Doppler on NLOS paths. Trajectory geometry falls directly out of which links dim in which order.
02 Shared processing path
Per-link CSI attenuation -> RTI differential imaging (stage 4) for 0.5-1m localization -> Doppler band (stage 2) confirms biological motion vs wind-blown objects -> PCA+MVE anomaly manifold (stage 3) gates approach-trajectory vs passerby-trajectory.
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
Through-wall LOS/NLOS AUC 0.69 already proven (class A base); extend with ESP32-wall dataset plus own-hardware yard experiment: 50 scripted approach paths vs 50 pass-by paths around an instrumented house, score trajectory classification accuracy and pre-door-contact lead time.
04 Commercial hypothesis
"Know someone is in the yard 20 seconds before they touch the door — no cameras, no beams, works in the dark." For gated-community security operators and smart-alarm OEMs.