Skip to main content

ORIGINAL RESEARCH article

Front. Earth Sci.
Sec. Hydrosphere
Volume 12 - 2024 | doi: 10.3389/feart.2024.1427132
This article is part of the Research Topic Contributions to River Plastic Monitoring Across Scales - Volume II View all 6 articles

Instance Segmentation Models for Detecting Floating Macroplastic Debris from River Surface Images

Provisionally accepted
Tomoya Kataoka Tomoya Kataoka 1*Takushi Yoshida Takushi Yoshida 2Natsuki Yamamoto Natsuki Yamamoto 2
  • 1 Ehime University, Matsuyama, Japan
  • 2 Yachiyo Engineering Co., LTD., Tokyo, Japan

The final, formatted version of the article will be published soon.

    Quantifying the transport of floating macroplastic debris (FMPD) in waterways is essential for understanding the plastic emission from land. However, no robust tool has been developed to monitor FMPD. Here, to detect FMPD on river surfaces, we developed five instance segmentation models based on state-of-the-art YOLOv8 using 7,356 training images collected via fixed-camera monitoring of seven rivers. Our models could detect FMPD using object detection (OD) and image segmentation (IS) approaches with accuracies similar to those of the pretrained YOLOv8 model. Our model performances were tested using 3802 images generated from 107 frames obtained by a novel camera system embedded in an ultrasonic water level gauge (WLGCAM) installed in three rivers.Interestingly, the model with intermediate weight parameters most accurately detected FMPD, whereas the model with the most parameters exhibited poor performance due to overfitting. Additionally, we assessed the dependence of the detection performance on the ground sampling distance (GSD) and found that a smaller GSD for IS and larger GSD for OD are capable of accurately detecting FMPD. Based on the results from our study, more appropriate category selections need to be determined to improve the model performance and reduce the number of false positives. Our study can aid in the development of guidelines for monitoring FMPD and the establishment of an algorithm for quantifying the transport of FMPD.

    Keywords: Floating macroplastic debris, transport, YOLOv8, Instance segmentation, river surface, Fixed camera, Ultrasonic water level gauge

    Received: 03 May 2024; Accepted: 11 Oct 2024.

    Copyright: © 2024 Kataoka, Yoshida and Yamamoto. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Tomoya Kataoka, Ehime University, Matsuyama, Japan

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.