Hostname: page-component-cd9895bd7-lnqnp Total loading time: 0 Render date: 2024-12-25T19:35:17.518Z Has data issue: false hasContentIssue false

MOVIES-B: an acoustic detection description software. Application to shoal species' classification

Published online by Cambridge University Press:  15 February 2007

Alain Weill
Affiliation:
IFREMER - Centre de Brest, DITI/GO, BP 70, 29280 Plouzané, France
Carla Scalabrin
Affiliation:
IFREMER - Centre de Brest, DITI/GO, BP 70, 29280 Plouzané, France
Noël Diner
Affiliation:
IFREMER - Centre de Brest, DITI/GO, BP 70, 29280 Plouzané, France
Get access

Abstract

Software, MOVIES-B, developed by IFREMER (Institut français de recherche pour l'exploitationde la mer), enables the recognition of echogram features as acoustic detection structures according to spatial-energetic contiguity criteria. These structures (shoals, plankton layers) are described by energetic, morphological, spatial and temporal descriptors. Specifying acoustic detections as individual shoals will allow shoal by shoal echo-integration and may lead to better biomass estimation and shoal species description. The conceptual and operational framework of MOVIES-B is presented in the first part of this paper. The second part presents preliminary work performed in order to assess the feasibility of classification and possible species identification of shoals using MOVIES-B software. This research has studied the data set obtained from four fisheries acoustic surveys, in the Bay of Biscay. The data set is a matrix of 29 descriptors from 13,122 shoals. A limited knowledge of species composition was obtained from trawling. Eight species were captured: Sardina pilchardus, Clupea harengus, Sprattus sprattus, Engraulis encrasicolus, Micromesistius poutassou, Trachurus sp., Scomber sp. and Capros aper. Cluster analysis and linear discriminant analysis were performed on trawled identified shoals data (808 shoals), after a reduction of the space descriptors by a stepwise technique. A partition into 6 clusters was carried out and clusters are described by species composition and continuous variables values. After grouping the six species shoals in two groups, 84% of shoals from the testing data set could be correctly classified using the linear discriminant function.

Type
Research Article
Copyright
© IFREMER-Gauthier-Villars, 1993

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)