Fish species identification using image analysis of echo-sounder images
Thesis (M.Eng.)--Memorial University of Newfoundland, 2003. Engineering and Applied Science Includes bibliographical references. Acoustic surveys for marine fish in coastal waters typically involve identification of species groups. Incorrect classification can limit the usefulness of both distributi...
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis |
Language: | English |
Published: |
2002
|
Subjects: | |
Online Access: | http://collections.mun.ca/cdm/ref/collection/theses3/id/87604 |
id |
ftmemorialunivdc:oai:collections.mun.ca:theses3/87604 |
---|---|
record_format |
openpolar |
spelling |
ftmemorialunivdc:oai:collections.mun.ca:theses3/87604 2023-05-15T15:27:38+02:00 Fish species identification using image analysis of echo-sounder images Lefeuvre, Patricia, 1967- Memorial University of Newfoundland. Faculty of Engineering and Applied Science Canada--Newfoundland and Labrador; Grand Banks of Newfoundland 2002 1 v. (various foliations) : ill., maps Image/jpeg; application/pdf http://collections.mun.ca/cdm/ref/collection/theses3/id/87604 eng eng Electronic Theses and Dissertations (15.96 MB) -- http://collections.mun.ca/PDFs/theses/Lefeuvre_Patricia.pdf a1614905 http://collections.mun.ca/cdm/ref/collection/theses3/id/87604 The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission. Paper copy kept in the Centre for Newfoundland Studies, Memorial University Libraries Fishing surveys--Newfoundland and Labrador Fishing surveys--Grand Banks of Newfoundland Echo sounding in fishing--Newfoundland and Labrador Echo sounding in fishing--Grand Banks of Newfoundland Text Electronic thesis or dissertation 2002 ftmemorialunivdc 2015-08-06T19:18:45Z Thesis (M.Eng.)--Memorial University of Newfoundland, 2003. Engineering and Applied Science Includes bibliographical references. Acoustic surveys for marine fish in coastal waters typically involve identification of species groups. Incorrect classification can limit the usefulness of both distribution and biomass estimates. Fishing catch data can assist in identification, but are rarely spatially comparable to acoustic data and are usually biased by gear type. This thesis describes a technique and a software toolkit, "FASIT" (Fisheries Assessment and Species Identification Toolkit), developed by the author to enable automated identification of Atlantic cod (Gadus morhus), capelin (Mallotus villosus), and redfish (Sebastes spp.) based on high resolution acoustic imaging offish aggregations. The approach has been to assess and analyze various amplitude, shape and location features of the acoustic returns from shoals and individual fish, then to use these features to develop algorithms which discriminate among species. Fourteen classifiers based on Three-Nearest Neighbour classification and Mahalanobis distance classification have been implemented and tested. The best classifier had an average correct classification rate of 96.8%. The data used for this thesis are fisheries data from a number of Newfoundland bays and the Grand Bank region collected using a 38 KHz digital echo- sounder. Thesis atlantic cod Newfoundland studies University of Newfoundland Memorial University of Newfoundland: Digital Archives Initiative (DAI) Canada Newfoundland |
institution |
Open Polar |
collection |
Memorial University of Newfoundland: Digital Archives Initiative (DAI) |
op_collection_id |
ftmemorialunivdc |
language |
English |
topic |
Fishing surveys--Newfoundland and Labrador Fishing surveys--Grand Banks of Newfoundland Echo sounding in fishing--Newfoundland and Labrador Echo sounding in fishing--Grand Banks of Newfoundland |
spellingShingle |
Fishing surveys--Newfoundland and Labrador Fishing surveys--Grand Banks of Newfoundland Echo sounding in fishing--Newfoundland and Labrador Echo sounding in fishing--Grand Banks of Newfoundland Lefeuvre, Patricia, 1967- Fish species identification using image analysis of echo-sounder images |
topic_facet |
Fishing surveys--Newfoundland and Labrador Fishing surveys--Grand Banks of Newfoundland Echo sounding in fishing--Newfoundland and Labrador Echo sounding in fishing--Grand Banks of Newfoundland |
description |
Thesis (M.Eng.)--Memorial University of Newfoundland, 2003. Engineering and Applied Science Includes bibliographical references. Acoustic surveys for marine fish in coastal waters typically involve identification of species groups. Incorrect classification can limit the usefulness of both distribution and biomass estimates. Fishing catch data can assist in identification, but are rarely spatially comparable to acoustic data and are usually biased by gear type. This thesis describes a technique and a software toolkit, "FASIT" (Fisheries Assessment and Species Identification Toolkit), developed by the author to enable automated identification of Atlantic cod (Gadus morhus), capelin (Mallotus villosus), and redfish (Sebastes spp.) based on high resolution acoustic imaging offish aggregations. The approach has been to assess and analyze various amplitude, shape and location features of the acoustic returns from shoals and individual fish, then to use these features to develop algorithms which discriminate among species. Fourteen classifiers based on Three-Nearest Neighbour classification and Mahalanobis distance classification have been implemented and tested. The best classifier had an average correct classification rate of 96.8%. The data used for this thesis are fisheries data from a number of Newfoundland bays and the Grand Bank region collected using a 38 KHz digital echo- sounder. |
author2 |
Memorial University of Newfoundland. Faculty of Engineering and Applied Science |
format |
Thesis |
author |
Lefeuvre, Patricia, 1967- |
author_facet |
Lefeuvre, Patricia, 1967- |
author_sort |
Lefeuvre, Patricia, 1967- |
title |
Fish species identification using image analysis of echo-sounder images |
title_short |
Fish species identification using image analysis of echo-sounder images |
title_full |
Fish species identification using image analysis of echo-sounder images |
title_fullStr |
Fish species identification using image analysis of echo-sounder images |
title_full_unstemmed |
Fish species identification using image analysis of echo-sounder images |
title_sort |
fish species identification using image analysis of echo-sounder images |
publishDate |
2002 |
url |
http://collections.mun.ca/cdm/ref/collection/theses3/id/87604 |
op_coverage |
Canada--Newfoundland and Labrador; Grand Banks of Newfoundland |
geographic |
Canada Newfoundland |
geographic_facet |
Canada Newfoundland |
genre |
atlantic cod Newfoundland studies University of Newfoundland |
genre_facet |
atlantic cod Newfoundland studies University of Newfoundland |
op_source |
Paper copy kept in the Centre for Newfoundland Studies, Memorial University Libraries |
op_relation |
Electronic Theses and Dissertations (15.96 MB) -- http://collections.mun.ca/PDFs/theses/Lefeuvre_Patricia.pdf a1614905 http://collections.mun.ca/cdm/ref/collection/theses3/id/87604 |
op_rights |
The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission. |
_version_ |
1766358056969437184 |