Vehicle Damage Detection using Semi-Supervised Object Detection

Raap, Maria (2021) Vehicle Damage Detection using Semi-Supervised Object Detection. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (6MB) | Preview
Preview	PDF (Configuration manual) Download (3MB) | Preview

Abstract

The visual inspection of vehicles for external damages is a major activity in many industries worldwide. Not only does the detection of abnormalities depend on the assessor’s expertise, this process is also time-intensive as it must be carried out manually. Recent developments in the area of object detection however provide the opportunity to provide a more automated solution to this problem. While fully supervised learning has already proven successful, this study investigates the potential use of semi-supervised learning-enabled with saliency propagation for vehicle damage detection. In a direct comparison, the semi-supervised learning was not able to achieve the same accuracy rates as fully supervised models, can however accomplish a precision of 56.3% when using labelled data.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software T Technology > TL Motor vehicles. Aeronautics. Astronautics H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Motor Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Clara Chan
Date Deposited:	14 Dec 2021 10:44
Last Modified:	14 Dec 2021 11:26
URI:	https://norma.ncirl.ie/id/eprint/5212

Actions (login required)

View Item