{"refrec":{"BRefID":359150,"RR":"Lakshmi, M.D.; Santhanam, S.M. (2020). Underwater image recognition detector using deep ConvNet, in: 2020 National Conference on Communications (NCC). pp. 1-6. https://dx.doi.org/10.1109/NCC48643.2020.9056058","BEntID":356865,"PublicFlag":1,"CheckedFlag":0,"wosflag":0,"vabbflag":0,"RefStringPartII":", in: 2020 National Conference on Communications (NCC). pp. 1-6. https://dx.doi.org/10.1109/NCC48643.2020.9056058","DocTypID":17,"DocType":"Book chapters","MarineFlag":1,"FreshFlag":0,"BrackishFlag":0,"TerrestrialFlag":0,"Authorstring":"Lakshmi, M.D.; Santhanam, S.M.","OrigTitleTranslFlag":0,"Authorstringtrunc":"Lakshmi, M.D.; Santhanam, S.M.","Englishabstract":"Underwater navigation and intelligent object recognition require robust machine learning algorithms to operate in turbid water. Modern life created the man-made pollution in oceans, rivers, and lakes, which contaminate our water resources. Despite environmental regulations solid waste in the form of trash, litter and garbage are thrown directly into sea spoiling the existence of underwater living creatures. The underwater vehicle can be used for survey purposes. The key challenge of underwater image-based localization comes from the unstructured nature of the seabed terrain. So, there is a need for robust detection of the features in such environments is essential. Hence, this paper proposes the automated underwater image recognition detector for submersible imagery. We train a Convolutional neural Network (ConvNet) to classify input 64 × 64 images and considered the classifier as an object feature detector. The features of the image from underwater-bed can be extracted and forward into a network. The output of the three-layer ConvNet with deeply connected network results in a probability distribution over N classes. A Stochastic gradient descent with ADAM optimizer uses the squared gradients to scale the learning rate and reduces the difference between the actual and predicted output. The evaluations are done on the precision, recall, F-Score, macro and weighted Average accuracy for both the detectors. It is observed that our proposed network, achieved an overall accuracy of 93.9 % for correct detections with a binary detector and 90.1% with a multiclass detector compared to existing detectors.","AbstractOtherLang":null,"BibLvlCode":"AM","StandardTitle":"Underwater image recognition detector using deep ConvNet","OrigTitleLangCode":"en","OrigTitleLangCodeExtended":"eng","OrigTitleLangID":15,"DateLastModified":{"date":"2024-12-10 01:33:17.368041","timezone_type":1,"timezone":"+01:00"},"UserAccessRight":null,"UserAccID":null,"AuthorKeywords":null,"OtherDescriptors":null,"Notes":null,"AnaPub":2020,"MonPub":null,"DateUpdate":"2022-11-10","DateCreate":"2022-11-10","SecASFANote":null,"ConfID":null,"PeerRev":0,"VlizCoreFlag":1,"WoScode":"WOS:000853797500066","VABBcode":null,"OpenAcc":0,"DOI":"10.1109/NCC48643.2020.9056058"},"refs":null,"anarec":{"AnaID":359150,"PubliDate":2020,"Pagination":"1-6","XtraPublOfAnaID":null,"ISBN":"978-1-7281-5121-2","Volume":null,"Issue":null,"BRefMon":359149,"BRefMonRR":"(2020). 2020 National Conference on Communications (NCC). IEEE: Piscataway. ISBN 978-1-7281-5121-2; e-ISBN 978-1-7281-5120-5. 598 pp. https://dx.doi.org/10.1109/NCC48643.2020","BRefXtra":null,"BRefXtraRR":null,"SerBRefID":null,"SerRR":null,"StandardTitleSer":null,"ISSN":null,"AbbrevSer":null,"StandardTitleMon":"2020 National Conference on Communications (NCC)","StartPage":1,"Pages":6,"ToPubliDate":null,"BRefBibLvlCode":"M","SerNotes":null},"monrec":null,"serrec":null,"relations":null,"relationsRev":null,"addrec":null,"othpubs":null,"ownerships":null,"authors":[{"AutName":"Lakshmi","Firstname":"Dhana","Initials":"M.D.","Affiliation":null,"Discriminator":null,"CorporateFlag":0,"BEntID":356865,"AutID":508704,"OrderNr":1,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":null,"InsFSN":null,"ORCID":null,"PersID":null,"InsID":null},{"AutName":"Santhanam","Firstname":"Sakthivel Murugan","Initials":"S.M.","Affiliation":null,"Discriminator":null,"CorporateFlag":0,"BEntID":356865,"AutID":508705,"OrderNr":2,"DegrID":null,"EditorFlag":0,"CorrespFlag":0,"IllustratorFlag":0,"ReviserFlag":0,"TranslatorFlag":0,"InsAcronym":null,"InsFSN":null,"ORCID":null,"PersID":null,"InsID":null}],"mapdetails":null,"datasets":null,"monographs":null,"monparts":null,"serparts":null,"BEntOpen":null,"BEntPrivate":null,"availability":[{"BInstID":384863,"LibID":36,"BRefID":359150,"EmbargoDate":null,"FullEmbargoDate":null,"PhysMedID":16,"hasOCRd":null,"ShelfLocCode":"384863","RFID":null,"PaidValue":null,"Medium":"Server","Description":"Interne VLIZ documenten","Acronym":"VLIZ","Library":"Vlaams Instituut voor de Zee","DutchTerm":"Non-open access","URL":null,"ClassifID":228,"Classification":"Non-open access","ReqLink":1,"ClassifTypID":3,"URLLocation":"https://www.vliz.be/imisdocs/publications/","SubDir":1,"InternalReq":1,"LoggedInReq":1,"Disclaimer":"Disclaimer_VLIZ_Intern","DutchDisclaimer":"
Deze publicatie is enkel beschikbaar voor persoonlijk gebruik binnen de Innovocean site en mag op geen enkele manier verder worden verspreid.