Navegando por Autor "Pedroso, Ytalo Ribeiro da Silva"

Agora exibindo 1 - 1 de 1

Uso de redes neurais para identificação de embarcações
(2024-09-23) Pedroso, Ytalo Ribeiro da Silva; Santos, Alyson de Jesus dos Santos; http://lattes.cnpq.br/5998752909180697; Santos, Alyson de Jesus dos; http://lattes.cnpq.br/5998752909180697; Souza, Daniel Fonseca de; http://lattes.cnpq.br/4043793492782488; Rodrigues, Marlos André Silva; http://lattes.cnpq.br/0650250324042531
Due toitsuniquegeography,theriversoftheAmazonplayasignificant roleinthedailylife of theregion,includingbeingtheonlyaccessinmoreremotecommunities,andthelackof infrastructure inmuchofthiswaterwaynetworkmakesitconducivetothetransportofillegal goods duetothelackofsupervision. When comparedtourbanareas,itispossibletonoticethepotentialforpositiveassistanceto local authoritiesthroughtheuseofrecognitiontechnologies,butthelackofcommunication structures hinderstheimplementationofthesetechnologiesinthesamewayitisdoneincities. This projectproposesthedevelopmentofaneuralnetworkapplicationaimedatassistingin public securityissuesthroughthedetectionofvesselsinportregionslocatedintheStateof Amazonas, combiningArtificial IntelligencetechniquesandEmbeddedSystemsdevices,without the useofnetworkdatatransmission.Themethodologyconsistsof:(a)Acquisitionofvessel images atMarinadoDaviandtheportofManausModerna-StateofAmazonas;(b)Preparation of thedatasetintheexpectedformatforthemodel;(c)Installation,configuration, anduseofthe Jetson NanoBoardintrainingtheNeuralNetwork;(d)UseofTransferLearning,leveraginga pre-trained model(YOLOv4Tiny)formodelgenerationonthenewdataset;(e)Validationofthe obtained results. The resultsshowthatwiththeuseofversionsoptimizedforembeddeddevices,itwaspossible to executetheYOLOv4Tinyalgorithm,performingtheclassification ofvesselsandcontributing with newvesselimages,whichprovidegreaterregionalitytothepresenteddata.