Tudor BARBU1, Silviu-Ioan BEJINARIU2, Ramona LUCA3
Abstract. The development of a voluminous database aimed at performance evaluation of the vehicle detection and tracking algorithms is described here. The vehicle database has been created using many recorded traffic videos and annotated automatically by applying some convolutional neural network (CNN) – based object detectors. It has been split into training, validation and testing datasets and then successfully used to train, validate and test deep learning-based vehicle detectors. Some multiple vehicle detection and tracking simulations are also described. A transfer learning-based vehicle classification solution using this database and those detection and counting results is also provided here.
Keywords: annotated vehicle database, multiple vehicle detection and tracking, transfer learning, training and validation datasets, CNN-based vehicle classification
DOI 10.56082/annalsarsciinfo.2024.2.22
1Habilitated PhD, Senior Researcher I, Institute of Computer Science of the Romanian Academy – Iasi Branch, Iasi, Romania, Corresponding member of The Academy of the Romanian Scientists, e-mail: tudor.barbu@iit.academiaromana-is.ro.
2 PhD, Senior Researcher II, Institute of Computer Science of the Romanian Academy – Iasi Branch, Iasi, Romania, e-mail: silviu.bejinariu@iit.academiaromana-is.ro.
3PhD, Senior Researcher, Institute of Computer Science of the Romanian Academy – Iasi Branch, Iasi, Romania, e-mail: ramona.luca@iit.academiaromana-is.ro.
PUBLISHED in Annals of the Academy of Romanian Scientists Series on Science and Technology of Information, Volume 17, No2
ISSN PRINT2066 – 2742 ISSN ONLINE 2066-8562 
Description | Editorial Board | Instructions for authors | Template 
| Archive