Grant: Applied Research and Development Grants - Level 1
Nova Scotia Community College
$25,000.00
Developing methods for automated multibeam backscatter classification
EF 2017-18
Résumé
Seabed classification involves the analysis of acoustic remote sensing data to characterize the physical,geological, and biological properties of ocean, lake, and river beds for production of thematic maps. Acousticremote sensing can be done using almost any sonar, but multibeam echo sounders (MBES) have become afavored and widely used technique in recent years for seafloor reconnaissance surveys in a wide range of oceansector industries. MBES record information relating to seafloor bathymetry (depth), and acoustic seafloorbackscatter strength (which can be used to infer seafloor geological and habitat characteristics). Automatedsoftware methods offer an objective and robust classification approach compared to conventional expert ""byeye"" interpretation of such data sets to produce interpreted maps of seafloor features (e.g. maps of seafloorsediments or seafloor habitats). Even though software classification methods have progressed over the pastdecade, there is still significant scope for innovation and improvement of software tools for semi-automatedclassification of the MBES data sets. In this collaborative project, NSCC will partner with Maritime WayScientific Ltd. to explore new and innovative segmentation routines for improved seafloor classification andcharacterization of MBES data sets. These routines will be tested on MBES data sets held by NSCC tovalidation performance compared against in situ ground-truthing of the seafloor geological and habitatcharacteristics. The anticipated scientific and technical advances offer direct value to the private sector partnerby providing classification/segmentation routines for improvement of their seafloor classification softwareproducts. This will meet market demand for a wide cross section of their clients using the software for MBESbackscatter classification, with follow-on benefits for improved thematic map production across a wide crosssection of ocean sector industries (i.e. benefits afforded by improved seafloor map production for applicationfor oil and gas exploration, seafloor cable routing, fisheries and conservation mapping).
Programme
Applied Research and Development Grants - Level 1
Bénéficiaire
Emplacement
Nova Scotia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
507074-2016
Name nom
Joseph, Alain
Department département
Waterfront Campus
Organization id
16240
Institution établissement
Nova Scotia Community College
Province en
Nova Scotia
Province fr
Nouvelle-Écosse
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2017
Competition year année de concours
2016
Award amount
25000
Program id
CARD1
Program name en
Applied Research and Development Grants - Level 1
Program name fr
Subventions de recherche et développement appliquée - niveau 1
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1561
Committee name en
Applied Research and Development Grants
Committee name fr
Subventions de recherche et développement appliquée
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
4600
Research subject group en
Oceanography
Research subject group fr
Océanographie
Research subject en
Oceanography
Research subject fr
Océanographie
Partie
1
Nb partie
1
Application title
Developing methods for automated multibeam backscatter classification
Keyword
NSERC
Application summary
Seabed classification involves the analysis of acoustic remote sensing data to characterize the physical,geological, and biological properties of ocean, lake, and river beds for production of thematic maps. Acousticremote sensing can be done using almost any sonar, but multibeam echo sounders (MBES) have become afavored and widely used technique in recent years for seafloor reconnaissance surveys in a wide range of oceansector industries. MBES record information relating to seafloor bathymetry (depth), and acoustic seafloorbackscatter strength (which can be used to infer seafloor geological and habitat characteristics). Automatedsoftware methods offer an objective and robust classification approach compared to conventional expert ""byeye"" interpretation of such data sets to produce interpreted maps of seafloor features (e.g. maps of seafloorsediments or seafloor habitats). Even though software classification methods have progressed over the pastdecade, there is still significant scope for innovation and improvement of software tools for semi-automatedclassification of the MBES data sets. In this collaborative project, NSCC will partner with Maritime WayScientific Ltd. to explore new and innovative segmentation routines for improved seafloor classification andcharacterization of MBES data sets. These routines will be tested on MBES data sets held by NSCC tovalidation performance compared against in situ ground-truthing of the seafloor geological and habitatcharacteristics. The anticipated scientific and technical advances offer direct value to the private sector partnerby providing classification/segmentation routines for improvement of their seafloor classification softwareproducts. This will meet market demand for a wide cross section of their clients using the software for MBESbackscatter classification, with follow-on benefits for improved thematic map production across a wide crosssection of ocean sector industries (i.e. benefits afforded by improved seafloor map production for applicationfor oil and gas exploration, seafloor cable routing, fisheries and conservation mapping).