Detection of Driver Distraction Using Deep Learning

Shetty, Aishwarya Ratnakar (2022) Detection of Driver Distraction Using Deep Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (873kB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Driver distraction is one of the core aspects that now regularly causes fatal car crashes and may impair traffic safety. Even though there are many rules and regulations, there is no development. To further identify these distractions, which may have been caused by a driver engaging in other activities like texting, chatting on the phone, eating, etc., several research have been undertaken and technologies have been created. Using deep learning, which is normally used for image categorization, this research aims to develop a system that aids in assessing whether the driver is distracted or not. CNN employs transfer learning, which aids in lowering costs and increasing productivity. In this study, the pre-trained models ResNet50, VGG16, and VGG19 are employed. In this study, the idea of data augmentation is applied. According to the results, CNN accurately predicted the distraction with a 94.5% accuracy rate with second best model ResNet50 with 93.90%. Computational time taken for ResNet50 was less compared to CNN.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TL Motor vehicles. Aeronautics. Astronautics Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	11 Mar 2023 11:30
Last Modified:	11 Mar 2023 11:30
URI:	https://norma.ncirl.ie/id/eprint/6302

Actions (login required)

View Item