Automatic detection of estuarine dolphin whistles in spectrogram images
This work addresses the need for automated monitoring of dolphin vocalizations in marine biology, but it is incremental as it applies existing image processing and machine learning techniques to a specific dataset.
The researchers tackled the problem of automatically detecting estuarine dolphin whistles from spectrogram images, achieving a system that reliably classifies about 97% of detected patterns as whistles or false positives.
An algorithm for detecting tonal vocalizations from estuarine dolphin (Sotalia guianensis) specimens without interference of a human operator is developed. The raw audio data collected from a passive monitoring sensor in the Cananéia underwater soundscape is converted to spectrogram images, containing the desired acoustic event (whistle) as a linear pattern in the images. Detection is a four-step method: first, ridge maps are obtained from the spectrogram images; second, a probabilistic Hough transform algorithm is applied to detect roughly linear ridges, which are adjusted to the true corresponding shape of the whistles via an active contour algorithm; third, feature vectors are built from the geometry of each detected curve; and fourth, the detections are fed to a random forest classifier to parse out false positives. We develop a system capable of reliably classifying roughly 97% of the characteristic patterns detected as Sotalia guianensis whistles or random empty detections.