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

Abstract

Buelens, B., Pauly, T., Williams, R., and Sale, A. 2009. Kernel methods for the detection and classification of fish schools in single-beam and multibeam acoustic data. – ICES Journal of Marine Science, 66: 1130–1135. 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.

Acoustic identification of small pelagic fish species in Chile using support vector machines and neural networks

“…Korneliussen et al (2009) combined acoustic data with information on the morphological properties of schools and the geographical distribution of fish. Buelens et al (2009) applied kernel methods to classify fish schools in single beam and multibeam acoustic data. Fablet et al (2009) used a probabilistic model introduced in Bishop and Ulusoy (2005).…”

Comprehensive Detection of Gas Plumes from Multibeam Water Column Images with Minimisation of Noise Interferences

“…New generation multibeam echosounder systems (MBES), such as the Kongsberg EM710/EM302 [ 1 , 2 , 3 ] and Teledyne Reson 7125/8125 [ 4 , 5 ] can collect water column (WC) data. WC data include the full acoustic information from the MBES transducer to the seafloor [ 1 ] and provide an effective way to find underwater objects such as fish schools [ 4 , 6 , 7 , 8 ], wrecks [ 9 , 10 , 11 ], eelgrass [ 12 ], gas plumes [ 13 , 14 ], and internal ocean waves [ 15 , 16 ]. Gas plumes may be an indicator of the presence of gas hydrate.…”

Support vector machine under uncertainty: An application for hydroacoustic classification of fish-schools in Chile

“…Fernandes (2009)(see [11]) presents a complete list of studies including principal component analysis, discriminant-function analysis, artificial neural networks, nearest-neighbor analysis, k-means clustering and mixture models. Buelens et al (2009) (see [4]) use kernel methods to classify fish schools in single beam and multibeam acoustic data. In Robotham et al (2010) (see [19]), support vector machine methods (tool for discriminating between two groups, see [8]) are used for the automatic classification of small pelagic fish species from acoustic surveys data.…”