Deploying deep learning to estimate the abundance of marine debris from video footage

Cathy Teng, Kyriaki Kylili, Constantinos Hadjistassou

    Research output: Contribution to journalArticlepeer-review

    Abstract

    The insatiable desire of society for plastic goods has led to synthetic materials becoming omnipresent in the marine environment. In attempting to address the problem of plastic pollution, we propose an image classifier based on the YOLOv5 deep learning tool that is able to classify and localize marine debris and marine life in images and video recordings. Utilizing the region of interest line and the centroid tracking counting methods, the image classifier was able to count marine debris and fish displayed in video footage. Results revealed that, with a counting accuracy of 79 %, the centroid tracking method proved more efficient thanks to its ability to trace the geometric center of the bounding box of detected marine litter. Remarkably, the proposed method achieved a mean average precision of 89.4 % when validated on nine categories of objects. Finally, its impact can be enhanced substantially if integrated into other surveying methods or applications.

    Original languageEnglish
    Article number114049
    JournalMarine Pollution Bulletin
    Volume183
    DOIs
    Publication statusPublished - Oct 2022

    Keywords

    • Artificial intelligence
    • Centroid tracking
    • Image classification
    • Marine pollution
    • Plastic debris detection
    • Region of interest

    Fingerprint

    Dive into the research topics of 'Deploying deep learning to estimate the abundance of marine debris from video footage'. Together they form a unique fingerprint.

    Cite this