# than the second threshold value.
# First we remove the stationary background in order to increase the contrast [1]
# Then we convert the spectrogram into dB
Sxx_power_noNoise = sound.median_equalizer(Sxx_power,
display=True,
**{'extent': ext})
Sxx_db_noNoise = power2dB(Sxx_power_noNoise)
# Then we smooth the spectrogram in order to facilitate the creation of masks as
# small sparse details are merged if they are close to each other
Sxx_db_noNoise_smooth = sound.smooth(Sxx_db_noNoise,
std=0.5,
display=True,
savefig=None,
**{
'vmin': 0,
'vmax': dB_max,
'extent': ext
})
# Then we create a mask (i.e. binarization of the spectrogram) by using the
# double thresholding technique
im_mask = rois.create_mask(im=Sxx_db_noNoise_smooth,
mode_bin='relative',
bin_std=8,
bin_per=0.5,
verbose=False,
display=False)
# Finaly, we put together pixels that belong to the same acoustic event, and
s, fs = sound.load('../../data/rock_savanna.wav')
s_filt = sound.select_bandwidth(s, fs, fcut=100, forder=3, ftype='highpass')
db_max = 70 # used to define the range of the spectrogram
Sxx, tn, fn, ext = sound.spectrogram(s_filt, fs, nperseg=1024, noverlap=512)
Sxx_db = power2dB(Sxx, db_range=db_max) + db_max
plot2d(Sxx_db, **{'extent': ext})
#%%
# 1. Find regions of interest
# ---------------------------
# To find regions of interest in the spectrogram, we will remove stationary background noise and then find isolated sounds using a double threshold method. Small ROIs due to noise in the signal will be removed.
Sxx_db_rmbg, _, _ = sound.remove_background(Sxx_db)
Sxx_db_smooth = sound.smooth(Sxx_db_rmbg, std=1.2)
im_mask = rois.create_mask(im=Sxx_db_smooth,
mode_bin='relative',
bin_std=2,
bin_per=0.25)
im_rois, df_rois = rois.select_rois(im_mask, min_roi=50, max_roi=None)
# Format ROIs and visualize the bounding box on the audio spectrogram.
df_rois = format_features(df_rois, tn, fn)
ax0, fig0 = overlay_rois(Sxx_db, df_rois, **{
'vmin': 0,
'vmax': 60,
'extent': ext
})
#%%