Marine Object Detection and Classification by Integrating MLH-CNN with YOLOV8

Kundu, Ishita (2024) Marine Object Detection and Classification by Integrating MLH-CNN with YOLOV8. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (6MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The rapid increase in environmental pollution across the globe has a significant impact on marine life. Marine life is particularly impacted by harmful substances, such as plastic, rubber, metal, and natural wastes. Detecting marine objects accurately can help to reduce underwater debris. Numerous studies use deep-learning models to detect and classify marine objects, however achieving accurate results remains a challenge. This paper tries to resolve this issue by detecting marine objects and classifying them into different classes. The research proposes a modified YOLOv8 model, enhanced by integrating a Multi-Level Convolutional Neural Network in the YOLO architecture’s backbone. The aim is to improve the efficiency of marine object detection. The model Proposed in this paper will be trained using the Seaclear Marine Debris Detection & Segmentation Dataset. This dataset has images of forty different classes of marine objects including marine debris. A comparative analysis will also be conducted between the YOLOv5, YOLOv8, and the proposed MLH-CNN YOLOv8 on the Seaclear Marine dataset. This comparative analysis will help determine the effectiveness of the proposed models and identify the best-performing model for object detection and classification. The ultimate goal of this research is to contribute to better marine debris management and reduction of marine pollutants through improved detection and categorization of waste materials.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Yaqoob, Abid UNSPECIFIED
Subjects:	G Geography. Anthropology. Recreation > GE Environmental Sciences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science 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:	20 Aug 2025 09:51
Last Modified:	20 Aug 2025 09:51
URI:	https://norma.ncirl.ie/id/eprint/8584

Actions (login required)

View Item