Enhanced YOLOv8-Seg Instance Segmentation for Real-Time Submerged Debris Detection

Abstract

Segmenting images is one of the most essential problems in computer vision and finds use in many areas for example medical imaging, traffic analysis among others. The use of instance segmentation that brings together object detection and segmentation makes it more useful since it provides a holistic approach to recognizing and accurately outlining objects. In this paper, we concentrate on simple improved YOLOv8-Seg models for instance segmentation training with a focus on TrashCan dataset. The dataset being an instance-segmentation dataset specifically made for underwater environments addresses the problem of underwater garbage dumps. Two instance segmentation networks namely YOLOv8n-Seg and YOLOv8s-Seg are introduced and compared to detect underwater trash. The models were assessed based on their effectiveness in detecting and segmenting trash instances more so in difficult circumstances. These models can perform real-time instance segmentation of the TrashCan dataset with inference times of 2.3 ms and 2.4 ms with a precision of 75% and 70%, respectively. The results emphasize the contribution of improved YOLOv8-Seg towards environmental conservation across perfect identification of isolated marine undersea wastes through accurate instances' discrimination.