def do_beamforming(self, mic_data):
""" Beamforming using Acoular """
mg, rg, st = self.get_acoular_essentials()
count = 0
#Divide audio samples as per frame rate (10fps) and do beamforming
for s_time in tqdm(
np.arange(self.start_time, self.end_time, self.interval)):
audio_data = mic_data[:,
int(s_time *
self.sample_rate):int((s_time +
self.interval) *
self.sample_rate)]
audio_data = np.transpose(audio_data)
if audio_data.shape[0] == 0:
continue
#Acoular needs audio input through .h5 file
target_file = self.outfile + '/temp.h5'
if os.path.exists(target_file):
os.remove(target_file)
with h5py.File(target_file, 'w') as data_file:
data_file.create_dataset('time_data', data=audio_data)
data_file['time_data'].attrs.__setitem__(
'sample_freq', self.sample_rate)
#.h5 file has issues with closing. Change 'ulimit' if not working
ts = TimeSamples(name=target_file)
ps = PowerSpectra(time_data=ts,
block_size=128,
window='Hanning',
overlap='50%')
bb = BeamformerEig(freq_data=ps, steer=st)
pm = bb.synthetic(self.freq_query, self.octave_band)
Lm = L_p(pm)
if count == 0:
bf_data = np.zeros(
(Lm.shape[0], Lm.shape[1],
len(
np.arange(self.start_time, self.end_time,
self.interval))))
bf_data[:, :, count] = Lm
else:
bf_data[:, :, count] = Lm
count += 1
# remove temp.h5 file after its finished
os.remove(target_file)
return bf_data, rg
n=12)
be3Full = BeamformerEig(freq_data=f,
grid=g,
mpos=m,
r_diag=False,
c=346.04,
steer='true level',
n=12)
be4Full = BeamformerEig(freq_data=f,
grid=g,
mpos=m,
r_diag=False,
c=346.04,
steer='true location',
n=12)
Lbe1Rem = L_p(be1Rem.synthetic(4000, 1))
Lbe2Rem = L_p(be2Rem.synthetic(4000, 1))
Lbe3Rem = L_p(be3Rem.synthetic(4000, 1))
Lbe4Rem = L_p(be4Rem.synthetic(4000, 1))
Lbe1Full = L_p(be1Full.synthetic(4000, 1))
Lbe2Full = L_p(be2Full.synthetic(4000, 1))
Lbe3Full = L_p(be3Full.synthetic(4000, 1))
Lbe4Full = L_p(be4Full.synthetic(4000, 1))
bm1Full = BeamformerMusic(freq_data=f,
grid=g,
mpos=m,
r_diag=False,
c=346.04,
steer='classic',
n=12)
bca3Full = BeamformerCapon(freq_data=f, grid=g, mpos=m, r_diag=False, c=346.04, steer='true level') bca4Full = BeamformerCapon(freq_data=f, grid=g, mpos=m, r_diag=False, c=346.04, steer='true location') Lbca1Full = L_p(bca1Full.synthetic(4000,1)) Lbca2Full = L_p(bca2Full.synthetic(4000,1)) Lbca3Full = L_p(bca3Full.synthetic(4000,1)) Lbca4Full = L_p(bca4Full.synthetic(4000,1)) be1Rem = BeamformerEig(freq_data=f, grid=g, mpos=m, r_diag=True, c=346.04, steer='classic', n=12) be2Rem = BeamformerEig(freq_data=f, grid=g, mpos=m, r_diag=True, c=346.04, steer='inverse', n=12) be3Rem = BeamformerEig(freq_data=f, grid=g, mpos=m, r_diag=True, c=346.04, steer='true level', n=12) be4Rem = BeamformerEig(freq_data=f, grid=g, mpos=m, r_diag=True, c=346.04, steer='true location', n=12) be1Full = BeamformerEig(freq_data=f, grid=g, mpos=m, r_diag=False, c=346.04, steer='classic', n=12) be2Full = BeamformerEig(freq_data=f, grid=g, mpos=m, r_diag=False, c=346.04, steer='inverse', n=12) be3Full = BeamformerEig(freq_data=f, grid=g, mpos=m, r_diag=False, c=346.04, steer='true level', n=12) be4Full = BeamformerEig(freq_data=f, grid=g, mpos=m, r_diag=False, c=346.04, steer='true location', n=12) Lbe1Rem = L_p(be1Rem.synthetic(4000,1)) Lbe2Rem = L_p(be2Rem.synthetic(4000,1)) Lbe3Rem = L_p(be3Rem.synthetic(4000,1)) Lbe4Rem = L_p(be4Rem.synthetic(4000,1)) Lbe1Full = L_p(be1Full.synthetic(4000,1)) Lbe2Full = L_p(be2Full.synthetic(4000,1)) Lbe3Full = L_p(be3Full.synthetic(4000,1)) Lbe4Full = L_p(be4Full.synthetic(4000,1)) bm1Full = BeamformerMusic(freq_data=f, grid=g, mpos=m, r_diag=False, c=346.04, steer='classic', n=12) bm2Full = BeamformerMusic(freq_data=f, grid=g, mpos=m, r_diag=False, c=346.04, steer='inverse', n=12) bm3Full = BeamformerMusic(freq_data=f, grid=g, mpos=m, r_diag=False, c=346.04, steer='true level', n=12) bm4Full = BeamformerMusic(freq_data=f, grid=g, mpos=m, r_diag=False, c=346.04, steer='true location', n=12) Lbm1Full = L_p(bm1Full.synthetic(4000,1)) Lbm2Full = L_p(bm2Full.synthetic(4000,1)) Lbm3Full = L_p(bm3Full.synthetic(4000,1))
################ Elevation Azimuth Frequenzbänder Frames
DL_Matrix = zeros((NPOINTS_ELE, NPOINTS_AZI, len(FREQBANDS), FRAMES))
# Wenn .npz, dann keine FRAMES, weil die in einzelne .npy-Tabellen?!
# DL_Matrix = zeros((NPOINTS_ELE, NPOINTS_AZI, len(FREQBANDS)))
for frame_index, frame in enumerate(range(STARTFRAME, ENDFRAME)):
print('### FRAME: ', frame - STARTFRAME, ' (', frame, ') ###')
for freq_index, freq in enumerate(FREQBANDS):
print('FREQ =', freq)
ts.start = frame * NUM
ts.stop = (frame + 1) * NUM
result = zeros((4, rg.shape[0], rg.shape[1]))
for i in range(4):
be.n = i
result[i] = be.synthetic(freq, 3)
maxind = argmax(result.max((1, 2)))
# WARUM IMMER MAXINDEX = 3 ???
# print('Result Beamforming: Maxindex = ', maxind)
Lm = L_p(result[maxind]).reshape(rg.shape).flatten()
max_idx = argmax(
Lm.flatten()) # position in grid with max source strength
max_cartcoord = rg.gpos[:, max_idx]
max_idx = argmax(
Lm.flatten()) # position in grid with max source strength
max_value = amax(Lm.flatten())
temp_azi = arctan2(sin(rg.phi[max_idx]), cos(rg.phi[max_idx]))
# Opt 1
maxval1 = zeros(len(FREQBANDS))
maxval2 = zeros(len(FREQBANDS))
# Opt 2
tot_maxval1 = 0
tot_maxval2 = 0
# Opt 3
tot_maxval = 0
# Befüllen von Src1_Matrix und Src2_Matrix
for freq_index, freq in enumerate(FREQBANDS):
be.n = -1 #Eigenwerte der Größe nach sortiert -> größter Eigenwert (default)
Lm = L_p(be.synthetic(freq, 3)).reshape(rg.shape).flatten()
Src1_Matrix[:,:,freq_index] = Lm.reshape(rg.shape).T
max_idx1 = argmax(Lm.flatten()) # position in grid with max source strength
max_value1 = amax(Lm.flatten())
be.n = -2 #Eigenwerte der Größe nach sortiert -> größter Eigenwert (default)
Lm = L_p(be.synthetic(freq, 3)).reshape(rg.shape).flatten()
Src2_Matrix[:,:,freq_index] = Lm.reshape(rg.shape).T
max_idx2 = argmax(Lm.flatten()) # position in grid with max source strength
max_value2 = amax(Lm.flatten())
# Opt 1
maxval1[freq_index] = max_value1