A COMPARISON OF 20-HZ FIN WHALE CALL DETECTORS
The benefit of passive acoustic monitoring is indisputable; it is non-invasive to marine life and can capture vast quantities of data over large stretches of space and time. The limiting factor of analysing large volumes of data quickly overwhelms the analyst, and by utilising some form of automatic...
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://researchportal.bath.ac.uk/en/publications/fd835c41-f67f-4a50-9848-fa8eddd39c08 https://purehost.bath.ac.uk/ws/files/299833353/ICSV_v3.pdf http://www.scopus.com/inward/record.url?scp=85170648652&partnerID=8YFLogxK |
Summary: | The benefit of passive acoustic monitoring is indisputable; it is non-invasive to marine life and can capture vast quantities of data over large stretches of space and time. The limiting factor of analysing large volumes of data quickly overwhelms the analyst, and by utilising some form of automatic signal identification this process can be substantially faster. Here we compare the performance of a deep learning detector, simple correlation, and a more traditional energy detector (or the fin whale index). Here we compare three detectors on data from the Lofoten-Vesterålen Observatory in Norway (northern Atlantic Ocean), and the Comprehensive Nuclear-Test-Ban-Treaty Organisations hydrophone station at Ascension Island (southern Atlantic Ocean). |
---|