Automatic detection of marine mammals using information entropy

Abstract

This article describes an automatic detector for marine mammal vocalizations. Even though there has been previous research on optimizing automatic detectors for specific calls or specific species, the detection of any type of call by a diversity of marine mammal species still poses quite a challenge--and one that is faced more frequently as the scope of passive acoustic monitoring studies and the amount of data collected increase. Information (Shannon) entropy measures the amount of information in a signal. A detector based on spectral entropy surpassed two commonly used detectors based on peak-energy detection. Receiver operating characteristic curves were computed for performance comparison. The entropy detector performed considerably faster than real time. It can be used as a first step in an automatic signal analysis yielding potential signals. It should be followed by automatic classification, recognition, and identification algorithms to group and identify signals. Examples are shown from underwater recordings in the Western Canadian Arctic. Calls of a variety of cetacean and pinniped species were detected.

Automated detection and localization of bowhead whale sounds in the presence of seismic airgun surveys

“…Adding additional features into the classifier that characterize the frequency spectrum of the ambient noise background, including cepstral or entropy-based (Burg spectrum) measures (Erbe and King, 2008), could mitigate the impact of vessel noise.…”

Generalized marine mammal detection based on improved band-limited processing

“…The entropy algorithm, first applied to marine-mammal detection by Erbe [7], uses band-limited Shannon entropy to form the time-series data. First, each spectral band is normalized to unit energy:…”

Real-time acoustic classification of sperm whale clicks and shipping impulses from deep-sea observatories

“…However, the fully automated detection and classification of many cetacean species remains challenging, especially when it must work reliably under the diversity of background noises and acoustic events expected over long time periods (see also Ref. [8]). …”