eCite Digital Repository

Kernel methods for the detection and classification of fish schools in single-beam and multi beam acoustic data

Citation

Buelens, B and Pauly, T and Williams, RN and Sale, AHJ, Kernel methods for the detection and classification of fish schools in single-beam and multi beam acoustic data, I C E S Journal of Marine Science, 66, (6) pp. 1130-1135. ISSN 1054-3139 (2009) [Refereed Article]


Preview
PDF
Not available
215Kb
  

Copyright Statement

The definitive publisher-authenticated version is available online at: www.oxfordjournals.org Copyright © 2009 Oxford University Press

DOI: doi:10.1093/icesjms/fsp004

Abstract

A kernel method for clustering acoustic data from single-beam echosounder and multibeam sonar is presented. The algorithm is used to detect fish schools and to classify acoustic data into clusters of similar acoustic properties. In a preprocessing routine, data from single-beam echosounder and multibeam sonar are transformed into an abstracted representation by multidimensional nodes, which are datapoints with spatial, temporal, and acoustic features as components. Kernel methods combine these components to determine clusters based on joint spatial, temporal, and acoustic similarities. These clusters yield a classification of the data in groups of similar nodes. Including the spatial components results in clusters for each school and effectively detects fish schools. Ignoring the spatial components yields a classification according to acoustic similarities, corresponding to classes of different species or age groups. The method is described and two case studies are presented.

Item Details

Item Type:Refereed Article
Keywords:classification, detection of fish schools, kernel methods, multibeam sonar.
Research Division:Information and Computing Sciences
Research Group:Computer vision and multimedia computation
Research Field:Pattern recognition
Objective Division:Environmental Management
Objective Group:Terrestrial systems and management
Objective Field:Assessment and management of terrestrial ecosystems
UTAS Author:Buelens, B (Mr Bart Buelens)
UTAS Author:Williams, RN (Dr Ray Williams)
UTAS Author:Sale, AHJ (Professor Arthur Sale)
ID Code:61647
Year Published:2009
Web of Science® Times Cited:10
Deposited By:Information and Communication Technology
Deposited On:2010-03-04
Last Modified:2015-02-13
Downloads:1 View Download Statistics

Repository Staff Only: item control page