0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Sign in to save

Deep Learning-Based Underwater Trash Detection System UsingYOLOv8

International Journal of Engineering Technology and Management Sciences 2026

Summary

Researchers trained a YOLOv8 deep learning model on underwater debris imagery to enable real-time detection and classification of submerged plastic trash, demonstrating substantially faster and more scalable performance than traditional manual survey or sonar-based methods.

Plastic pollution in aquatic environments poses a significant threat to marine ecosystems, biodiversity, and human health. Traditional methods for underwater waste detection, such as manual surveys and sonar imaging, are inefficient, time-consuming, and lack scalability. This paper presents a deep learning-based system for real-time detection and classification of underwater trash using the YOLOv8 model. The proposed system is trained on a dataset comprising underwater debris images, including plastic bottles, fishing nets, glass materials, electronic waste, and other pollutants. The model is integrated into a web-based application developed using Django, enabling users to upload images and videos for detection. The system processes inputs frame-by-frame and highlights detected objects with bounding boxes and classification labels. Experimental results demonstrate that the proposed system achieves high accuracy and real-time performance even in challenging underwater conditions such as low visibility and object distortion. The solution provides an efficient and scalable approach for environmental monitoring and supports marine conservation efforts.

Share this paper