Deep Learning-Based Vehicle Classification for Low Quality Images

dc.authorid Dalveren, Yaser/0000-0002-9459-0042
dc.authorid Derawi, Mohammad/0000-0003-0448-7613
dc.authorid Kara, Ali/0000-0002-9739-7619
dc.authorid SARI, Ozgen/0000-0002-5477-6387
dc.authorid Pazar, Senol/0000-0003-3807-6601
dc.authorscopusid 57754782800
dc.authorscopusid 57754453600
dc.authorscopusid 51763497600
dc.authorscopusid 6505962073
dc.authorscopusid 7102824862
dc.authorscopusid 35408917600
dc.contributor.author Tas, Sumeyra
dc.contributor.author Sari, Ozgen
dc.contributor.author Dalveren, Yaser
dc.contributor.author Pazar, Senol
dc.contributor.author Kara, Ali
dc.contributor.author Derawi, Mohammad
dc.contributor.other Department of Electrical & Electronics Engineering
dc.date.accessioned 2024-07-05T15:17:45Z
dc.date.available 2024-07-05T15:17:45Z
dc.date.issued 2022
dc.department Atılım University en_US
dc.department-temp [Tas, Sumeyra; Sari, Ozgen] Atilim Univ, Grad Sch Nat & Appl Sci, TR-06830 Ankara, Turkey; [Dalveren, Yaser] Atilim Univ, Dept Avion, TR-06830 Ankara, Turkey; [Pazar, Senol] Biruni Univ, Dept Comp Programming, TR-34010 Istanbul, Turkey; [Pazar, Senol] Yildiz Tech Univ Ikitelli Technopk, Ankageo Co Ltd, TR-34220 Istanbul, Turkey; [Kara, Ali] Gazi Univ, Dept Elect & Elect Engn, TR-06570 Ankara, Turkey; [Derawi, Mohammad] Norwegian Univ Sci & Technol, Dept Elect Syst, N-2815 Gjovik, Norway en_US
dc.description Dalveren, Yaser/0000-0002-9459-0042; Derawi, Mohammad/0000-0003-0448-7613; Kara, Ali/0000-0002-9739-7619; SARI, Ozgen/0000-0002-5477-6387; Pazar, Senol/0000-0003-3807-6601 en_US
dc.description.abstract This study proposes a simple convolutional neural network (CNN)-based model for vehicle classification in low resolution surveillance images collected by a standard security camera installed distant from a traffic scene. In order to evaluate its effectiveness, the proposed model is tested on a new dataset containing tiny (100 x 100 pixels) and low resolution (96 dpi) vehicle images. The proposed model is then compared with well-known VGG16-based CNN models in terms of accuracy and complexity. Results indicate that although the well-known models provide higher accuracy, the proposed method offers an acceptable accuracy (92.9%) as well as a simple and lightweight solution for vehicle classification in low quality images. Thus, it is believed that this study might provide useful perception and understanding for further research on the use of standard low-cost cameras to enhance the ability of the intelligent systems such as intelligent transportation system applications. en_US
dc.identifier.citationcount 6
dc.identifier.doi 10.3390/s22134740
dc.identifier.issn 1424-8220
dc.identifier.issue 13 en_US
dc.identifier.pmid 35808251
dc.identifier.scopus 2-s2.0-85132398746
dc.identifier.uri https://doi.org/10.3390/s22134740
dc.identifier.uri https://hdl.handle.net/20.500.14411/1785
dc.identifier.volume 22 en_US
dc.identifier.wos WOS:000824079100001
dc.identifier.wosquality Q2
dc.institutionauthor Dalveren, Yaser
dc.institutionauthor Kara, Ali
dc.language.iso en en_US
dc.publisher Mdpi en_US
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/openAccess en_US
dc.scopus.citedbyCount 19
dc.subject vehicle classification en_US
dc.subject convolutional neural network en_US
dc.subject deep learning en_US
dc.subject low resolution en_US
dc.subject low quality en_US
dc.title Deep Learning-Based Vehicle Classification for Low Quality Images en_US
dc.type Article en_US
dc.wos.citedbyCount 9
dspace.entity.type Publication
relation.isAuthorOfPublication 55e082ac-14c0-46a6-b8fa-50c5e40b59c8
relation.isAuthorOfPublication be728837-c599-49c1-8e8d-81b90219bb15
relation.isAuthorOfPublication.latestForDiscovery 55e082ac-14c0-46a6-b8fa-50c5e40b59c8
relation.isOrgUnitOfPublication c3c9b34a-b165-4cd6-8959-dc25e91e206b
relation.isOrgUnitOfPublication.latestForDiscovery c3c9b34a-b165-4cd6-8959-dc25e91e206b

Files

Collections