NORMA eResearch @NCI Library

Detecting Marine Waste and Classifying it into Recyclable and Non-recyclable Using YOLOv3

Shetty, Rishika (2020) Detecting Marine Waste and Classifying it into Recyclable and Non-recyclable Using YOLOv3. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[img]
Preview
PDF (Configuration manual)
Download (1MB) | Preview

Abstract

There has been a substantial amount of increase in environmental pollution all around the world since the birth of Industrial Revolution which is now unstoppable. The pollution that was harming the environment has found its way into the water bodies and has degraded the marine life as well. The man-made pollution such as Plastic, Metal and Rubber reach the water bodies and remain in there for years to come and are sometimes consumed by marine life such as fishes which leads to choking and sever injuries. This study is intended to deal with this issue by detection marine waste and also classifying it into Recyclable and Non-Recyclable waste using YOLOv3 object detection algorithm. There are 3 datasets namely Plastic, Metal and Rubber from JAMSTEC Deep-sea Debris Database that is used in this research. In this study, ParseHub is used for web scrapping and LabelImg tool is used for annotations. There are 3 experiments carried out, Experiment 1: Rubber, Experiment 2: Plastic and Experiment 3: Metal. For all the three experiments YOLOv3 object detection algorithm was used with IoU as an evaluation method. 5 samples from each dataset was chosen for evaluation and out of which 4 of the sample had an IoU > 0.75. With the evaluation and results of all the three experiments it was quite evident that using YOLOv3 gave the desired results.
Keywords: Marine Debris Detection, YOLOv3, Recyclable and Non-Recyclable Waste

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

G Geography. Anthropology. Recreation > GE Environmental Sciences > Environment
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 21 Jan 2021 11:07
Last Modified: 21 Jan 2021 11:07
URI: http://norma.ncirl.ie/id/eprint/4421

Actions (login required)

View Item View Item