Agent Skills: Radar Signal Processing

Radar Signal Processing

Get from a raw binary I/Q capture to a clean 1-D phase trace that downstream vital-signs / motion analysis can consume.

Pipeline (do every step in order)

1. Parse binary I/Q to complex samples. Use the JSON/YAML sidecar to determine format — never assume. See references/iq-formats.md.
2. (FMCW only) Range FFT across fast time → 2-D range matrix. CW skips this step.
3. Remove static clutter. Subtract the temporal mean:
   • CW: iq -= iq.mean()
   • FMCW: R -= R.mean(axis=0, keepdims=True) on the range matrix
4. (FMCW only) Pick the subject range bin. See references/range-bin.md.
5. Extract phase with unwrap:

   phase = np.unwrap(np.angle(iq_or_bin))
   phase -= phase.mean()
   

6. If fs >= 500 Hz and downstream needs sub-Hz filtering, decimate first:

   from scipy.signal import decimate
   phase_ds = decimate(phase, q=int(fs/50), ftype='iir', zero_phase=True)
   fs_new = fs / int(fs/50)   # ~50 Hz target
   

Critical rules

| rule | why (short) | |---|---| | Use phase, not magnitude | 1 mm motion at 24 GHz ≈ 1 rad; magnitude is ~40 dB worse SNR | | Clutter removal goes before np.angle | DC offset anchors phase off zero, eats the unwrap budget | | Never design a 0.1 Hz filter against a 2 kHz signal | SciPy biquad silently NaNs; decimate to ~50 Hz first | | Never argmax(magnitude) across all range bins | DC bin (bin 0) and static reflectors dominate — restrict to a physical subject-range window |

When things go wrong

If the output is garbage, walk through references/debugging.md in order — it's fast and catches most ingestion/SNR bugs.

Not in scope

Pulse/UWB time-of-flight, MIMO angle-of-arrival, Doppler-only gesture radar.