Heterogenous Waste Detection using YOLO

Wadhwanwala, Aliasgar Abdulhusain (2023) Heterogenous Waste Detection using YOLO. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (5MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The rapid expansion of industries, cities, and the world’s population has caused a substantial surge in environmental damage, particularly in the form of waste buildup. This research project tackles the pressing issue of waste pollution by harnessing sophisticated computer vision methods, particularly aiming to identify and categorize diverse types of waste using the You Only Look Once (YOLO) algorithm, in particular the eighth version, YOLOv8 deep learning framework. Project’s overarching goal is to build powerful waste categorization system that can sift through complex combinations of garbage, which will increase recycling efficacy and decrease need for human labor. Examining YOLOv8’s mean average precision (mAP) on varied dataset of trash items photographed in their native environment while taking variety of environmental conditions into account is central to research subject. Research also delves into how YOLOv8 stacks up against its forerunners, illuminating its promise as a widespread, precise, effective alternative to labor-intensive manual waste management techniques. There were 5 steps to construct reliable model, each of involving tweaking model in turn as well as augmenting data at different levels. A high mAP50 of 84.1%, overall precision of 93%, and recall of 68.7% were all indicators of well-performing model following much iteration. The results and insights from this research could change how we handle waste, impacting the environment, public health, and the economy in a big way.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Menghwar, Teerath Kumar UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TD Environmental technology. Sanitary engineering 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:	Ciara O'Brien
Date Deposited:	26 May 2025 08:52
Last Modified:	26 May 2025 08:52
URI:	https://norma.ncirl.ie/id/eprint/7640

Actions (login required)

View Item