Recognition of dynamic objects from UGVs using Interconnected Neural network-based Computer Vision system

Basit Öğe Kaydı
dc.contributor.authorGokce, Baris
dc.contributor.authorSonugur, Guray
dc.date.accessioned2024-02-23T14:17:10Z
dc.date.available2024-02-23T14:17:10Z
dc.date.issued2022
dc.departmentNEÜen_US
dc.description.abstractIn this study, moving object recognition is performed by using images from a camera mounted on an unmanned ground vehicle. A GPS coordinate-based algorithm has been developed to obtain moving object silhouettes. In order to classify these silhouettes, an interconnected artificial neural network (ICANN) architecture consisting of two stages has been developed. The method consists of two phases. In the first phase, real-time images are converted to binary images at the end of the GPS-assisted image registration process. Then, the silhouettes are extracted from the background of the images using connected component labelling. In the second phase, two interconnected neural networks are used. The first neural network classifies silhouettes as objects or noise. The second neural network divides objects into seven subclasses as pedestrians, potholes, cars, etc. Compared to CNN-based techniques, a simpler NN architecture was employed in the research, and better accuracy rates were achieved with fewer samples. Another contribution of the research is simultaneous localization and mapping (SLAM) applications can be performed in non-GPS environments using pre-recorded images containing GPS information. In experimental studies, maximum success rates of 96,1% in object classification were obtained. The results obtained were compared to YOLO, the recently popular algorithm for object recognition.en_US
dc.description.sponsorshipAfyon Kocatepe University, Scientific Research Projects Council [14, FEN.BL.37]en_US
dc.description.sponsorshipThis research was supported by Afyon Kocatepe University, Scientific Research Projects Council with Project Number 14.FEN.BL.37.en_US
dc.identifier.doi10.1080/00051144.2022.2031539
dc.identifier.endpage258en_US
dc.identifier.issn0005-1144
dc.identifier.issn1848-3380
dc.identifier.issue2en_US
dc.identifier.scopus2-s2.0-85123829405en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.startpage244en_US
dc.identifier.urihttps://doi.org/10.1080/00051144.2022.2031539
dc.identifier.urihttps://hdl.handle.net/20.500.12452/12956
dc.identifier.volume63en_US
dc.identifier.wosWOS:000748098200001en_US
dc.identifier.wosqualityQ3en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherTaylor & Francis Ltden_US
dc.relation.ispartofAutomatikaen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectMoving Object Recognitionen_US
dc.subjectGps Assisted Recognitionen_US
dc.subjectRobot Visionen_US
dc.subjectNeural Networksen_US
dc.subjectImage Registrationen_US
dc.titleRecognition of dynamic objects from UGVs using Interconnected Neural network-based Computer Vision systemen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu