Detection and Classification of Moving Vehicle Based on YOLOv3 Model

Ridho Sholehurrohman*, Budi Setiyono

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

The development of computer vision and artificial intelligence has advanced in recent years. Object detection system based on deep learning have been extensively investigeted. In this paper, we proposed deep learning based method that will be used to detect and classify moving vehicles in complex traffic flows. The YOLO (You Only Look Once)-v3 network will be implemented to handle this case. This paper consist of saveral stages. In the first stage we collect vehicles dataset on one-way street in the form of a video. The second stage is converting video into frames and labelling frames. The third stage is to feed the labeled frames as input in training this model. The last stage is training and testing the model to detect and classify moving vehicles. The experimental was completed and the proposed method can classify moving vehicles using recorded data video appropriately. The results showed that 0.9648 average accuracies of moderate traffic condition and 0.9256 average accuracies of crowded traffic condition.

Original languageEnglish
Title of host publication3rd International Conference on Science, Mathematics, Environment, and Education
Subtitle of host publicationFlexibility in Research and Innovation on Science, Mathematics, Environment, and Education for Sustainable Development
EditorsNurma Yunita Indriyanti, Meida Wulan Sari
PublisherAmerican Institute of Physics Inc.
ISBN (Electronic)9780735443099
DOIs
Publication statusPublished - 27 Jan 2023
Event3rd International Conference on Science, Mathematics, Environment, and Education: Flexibility in Research and Innovation on Science, Mathematics, Environment, and Education for Sustainable Development, ICoSMEE 2021 - Surakarta, Indonesia
Duration: 27 Jul 202128 Jul 2021

Publication series

NameAIP Conference Proceedings
Volume2540
ISSN (Print)0094-243X
ISSN (Electronic)1551-7616

Conference

Conference3rd International Conference on Science, Mathematics, Environment, and Education: Flexibility in Research and Innovation on Science, Mathematics, Environment, and Education for Sustainable Development, ICoSMEE 2021
Country/TerritoryIndonesia
CitySurakarta
Period27/07/2128/07/21

Fingerprint

Dive into the research topics of 'Detection and Classification of Moving Vehicle Based on YOLOv3 Model'. Together they form a unique fingerprint.

Cite this