Optimising Data Collection Process in Autonomous Driving Industry Using Machine Learning

Migrova, Maria (2023) Optimising Data Collection Process in Autonomous Driving Industry Using Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (25MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

This study presents an innovative solution for optimising data collection processes within the realm of autonomous driving. It introduces a high-performance multi-label Convolutional Neural Network (CNN) classification model designed to classify attributes like weather, lighting, and surface conditions. Notably, this model achieves an impressive 99.46% testing accuracy, accompanied by a minimal test loss of 0.0162 and a speedy training time of only 3.25 minutes per epoch. This exceptional performance renders it suitable for deployment within vehicles, enabling real-time driver alerts to prevent over-capturing various categories. This approach effectively mitigates potential human errors that can arise from pre-annotated data collected by drivers in the vehicle.

Furthermore, a unique and robust multi-class dataset comprising over 20,000 images, capturing diverse weather, lighting, and surface conditions, has been meticulously curated from various autonomous driving sources.

The findings of this research not only contribute a novel methodology but also pave the way for extensive future exploration in this field. The optimization of data collection in autonomous driving remains a fertile ground for further investigation, offering opportunities to enhance methodologies, refine datasets, train for additional classes, and unlock new avenues of innovation.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Basilio, Jorge UNSPECIFIED
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 > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence > Computer vision Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence > Computer vision 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:	29 Nov 2024 13:17
Last Modified:	29 Nov 2024 13:17
URI:	https://norma.ncirl.ie/id/eprint/7212

Actions (login required)

View Item