Underwater Plastic Detection using YOLO V8 and V10

Bogisam, Soma Sekhar (2024) Underwater Plastic Detection using YOLO V8 and V10. Masters thesis, Dublin, National College of Ireland.

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

Abstract

This research focuses on a comparative study of the performance of two versions, YOLOv8 and YOLOv10, in detecting small and medium-sized plastic litter underwater. The study experimented with 1,200 underwater images from the Deepsea Debris Database using four variants: YOLOv8-s, YOLOv8-l, YOLOv10-s, and YOLOv10-l. Comparisons have been focused on detection accuracy and computational efficiency. Results demonstrate that the best performance is by YOLOv10-s, which achieves the highest mean average precision, mAP50:0.772, at the least computational resources of 24.4 GFLOPs. Generally, the YOLOv10 variants were returns as performing better compared to the YOLOv8 ones in most of the experiments; small models would be performatively better than their larger alternatives under conditions of equal training epochs.

These results have important implications for underwater plastic detection systems, providing very clear evidence of the need for task-specific optimization. The limitations brought up by the authors concern the size of the dataset and real-world testing diversity, and they outline some future directions for underwater plastic detector development.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Horn, Christian 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 > 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
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	14 Aug 2025 15:35
Last Modified:	14 Aug 2025 15:39
URI:	https://norma.ncirl.ie/id/eprint/8542

Actions (login required)

View Item