Citation

Mohd Tajudin, Muhammad Haziq and Mat Desa, Shahbe and Abdullah, Junaidi (2023) Traffic Density Identification From UAV Images Using Deep Learning: A Preliminary Study. In: 2023 15th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), 08-10 December 2023, Kuala Lumpur, Malaysia.

Text 21.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

This study presents a preliminary investigation into the application of deep learning techniques for the identification of traffic density from unmanned aerial vehicle (UAV) images. The primary objective is to categorize the traffic flows into three classes: low, moderate, and high. The study proposes a VGG16-based framework with the aim of achieving high classification rates. The experimental results, obtained from a curated dataset with a 70:30 data-splitting ratio, demonstrate a good accuracy at 95.67%. The initial findings regarding traffic density identification are notably satisfactory, especially considering the challenges posed by the UAV-based images utilized in the experiments.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Deep Learning, traffic density
Subjects:	H Social Sciences > HE Transportation and Communications > HE1-9990 Transportation and communications (General) > HE331-380 Traffic engineering. Roads and highways. Streets Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	22 Feb 2024 04:17
Last Modified:	22 Feb 2024 04:17
URII:	http://shdl.mmu.edu.my/id/eprint/12100

Downloads

Edit (login required)