Python tool for aircraft Doppler audio geolocation using historical ADS-B flight data (Source-available)
Python acoustic-geolocationads-baircraft-trackingairplaneaudio-forensicsdoppler-effectdoppler-shiftgeolocationosintsignal-processing
Reuse CPA schemas and track samples across bounded tile chunks (#248)
Cinna Davisc37128bb08f1
diff --git a/src/dopplergeist/search.py b/src/dopplergeist/search.pyindex b1e5759..c4fad38 100644--- a/src/dopplergeist/search.py+++ b/src/dopplergeist/search.py@@ -11,6 +11,11 @@ from scipy.spatial import cKDTreefrom .geometry import AcousticSupportError, ecef+# Most national track/receiver chunks are empty; construct their schema once.+_EMPTY_CPA_TABLE = pd.DataFrame(columns=[+ "point_id", "flight_id", "emission_time", "receive_time", "distance_m", "speed_mps"])++def cpa_table_dense(tracks, points, max_distance, c=343.0, step_s=2.0, chunk_size=256):"""Vectorized piecewise-linear CPA prefilter; supports repeated local passes.@@ -71,22 +76,31 @@ def cpa_table_dense(tracks, points, max_distance, c=343.0, step_s=2.0, chunk_sizreturn pd.DataFrame(rows,columns=["point_id","flight_id","emission_time","receive_time","distance_m","speed_mps"])-def cpa_table(tracks,points,max_distance,c=343.0,step_s=2.0,chunk_size=512):+def cpa_table(tracks,points,max_distance,c=343.0,step_s=2.0,chunk_size=512, *, _sample_cache=None):"""Spatial-radius CPA graph, retaining every local pass without dense tensors.The radius includes two complete sample steps beyond the audible envelope,so both neighbours of an in-range sampled minimum are present. Each minimumis refined on its two actual adjacent segments. The dense reference aboveprovides an independent regression oracle for this search optimization.+ The private sample cache lives only across one track's bounded tile chunks."""observers=ecef(points.lat.to_numpy(),points.lon.to_numpy(),points.elev_m.to_numpy())point_ids=points.point_id.to_numpy(dtype=int)rows=[]for track in tracks:track.validate_motion_support(c)- t=np.unique(np.r_[np.arange(track.time[0],track.time[-1],step_s),track.time[-1]])- pos=track.position(t)- max_step=np.max(np.linalg.norm(np.diff(pos,axis=0),axis=1))+ key = (id(track), step_s)+ sampled = None if _sample_cache is None else _sample_cache.get(key)+ if sampled is None:+ t=np.unique(np.r_[np.arange(track.time[0],track.time[-1],step_s),track.time[-1]])+ pos=track.position(t)+ max_step=np.max(np.linalg.norm(np.diff(pos,axis=0),axis=1))+ if _sample_cache is not None:+ # Retain the track too, so its object ID cannot be reused.+ _sample_cache[key] = (track, t, pos, max_step)+ else:+ _, t, pos, max_step = samplednear=np.flatnonzero(np.all((observers>=pos.min(axis=0)-max_distance)&(observers<=pos.max(axis=0)+max_distance),axis=1))if not len(near):continue@@ -161,6 +175,8 @@ def cpa_table(tracks,points,max_distance,c=343.0,step_s=2.0,chunk_size=512):rows.append({"point_id":int(point_ids[chosen[oi[j]]]),"flight_id":track.id,"emission_time":float(when[j]),"receive_time":float(when[j]+distance[j]/c),"distance_m":float(distance[j]),"speed_mps":float(speed[j])})+ if not rows:+ return _EMPTY_CPA_TABLE.copy()result=pd.DataFrame(rows,columns=["point_id","flight_id","emission_time","receive_time","distance_m","speed_mps"])if not result.empty:# A CPA exactly at a sample can be proposed twice under roundoff.diff --git a/src/dopplergeist/tiled_search.py b/src/dopplergeist/tiled_search.pyindex ef508e1..bd88f91 100644--- a/src/dopplergeist/tiled_search.py+++ b/src/dopplergeist/tiled_search.py@@ -391,11 +391,14 @@ def _score(points, tracks, events, measurements, budget, parameters, filters, st# of minima before we inspect the returned table.chunk_points = max(1, budget.max_cpa_rows // samples)track_tables, track_rows = [], 0+ sample_cache = {}try:if track.outside_observer_radius(observers, radius, parameters.get("c", 343.0)):continuefor first in range(0, len(points), chunk_points):- table = cpa_table([track], points.iloc[first:first + chunk_points], radius, parameters.get("c", 343.0), budget.cpa_step_s)+ table = cpa_table([track], points.iloc[first:first + chunk_points], radius,+ parameters.get("c", 343.0), budget.cpa_step_s,+ _sample_cache=sample_cache)track_rows += len(table)if count + track_rows > budget.max_cpa_rows:raise DataUnavailable("Tile CPA-row memory budget exceeded")diff --git a/tests/test_real_cpa_spatial_sieve.py b/tests/test_real_cpa_spatial_sieve.pyindex 9d8bc87..0a054ed 100644--- a/tests/test_real_cpa_spatial_sieve.py+++ b/tests/test_real_cpa_spatial_sieve.py@@ -66,15 +66,28 @@ def test_real_multi_point_sieve_does_not_discard_cpas():for track in tracks:try:outside = track.outside_observer_radius(observers, 20000)+ table = cpa_table([track], points, 20000)except AcousticSupportError:unsupported += 1with pytest.raises(AcousticSupportError):cpa_table([track], points, 20000)continue- table = cpa_table([track], points, 20000)if outside:excluded += 1assert table.empty+ if excluded == 1:+ expected = table.copy()+ table.drop(columns=["flight_id"], inplace=True)+ repeated = cpa_table([track], points, 20000)+ pd.testing.assert_frame_equal(repeated, expected)else:+ if retained_rows == 0 and len(table):+ cache = {}+ step = max(1, len(points) // 2)+ chunks = [cpa_table([track], points.iloc[i:i + step], 20000,+ _sample_cache=cache) for i in range(0, len(points), step)]+ repeated = pd.concat(chunks, ignore_index=True).sort_values(+ ["point_id", "flight_id", "emission_time"]).reset_index(drop=True)+ pd.testing.assert_frame_equal(repeated, table)retained_rows += len(table)assert excluded > 0 and retained_rows > 0 and unsupported > 0