PLAS-Net: Pixel-Level Area Segmentation for UAV-Based Beach Litter Monitoring

TL;DR

PLAS-Net is a novel instance segmentation framework that accurately extracts pixel-level footprints of beach litter from UAV imagery, improving ecological risk assessments and environmental analysis.

Contribution

It introduces a pixel-level area segmentation method for coastal debris, surpassing bounding-box detection in accuracy and utility for ecological monitoring.

Findings

PLAS-Net achieves a mAP_50 of 58.7% on UAV beach litter imagery.

It outperforms eleven baseline models in mask fidelity under complex coastal conditions.

Pixel-level area extraction enhances ecological risk assessment and pollution hotspot mapping.

Abstract

Accurate quantification of the physical exposure area of beach litter, rather than simple item counts, is essential for credible ecological risk assessment of marine debris. However, automated UAV-based monitoring predominantly relies on bounding-box detection, which systematically overestimates the planar area of irregular litter objects. To address this geometric limitation, we develop PLAS-Net (Pixel-level Litter Area Segmentor), an instance segmentation framework that extracts pixel-accurate physical footprints of coastal debris. Evaluated on UAV imagery from a monsoon-driven pocket beach in Koh Tao, Thailand, PLAS-Net achieves a mAP_50 of 58.7% with higher precision than eleven baseline models, demonstrating improved mask fidelity under complex coastal conditions. To illustrate how the accuracy of the masking affects the conclusions of environmental analysis, we conducted three downstream demonstrations: (i) power-law fitting of normalized plastic density (NPD) to characterize fragmentation dynamics; (ii) area-weighted ecological risk index (ERI) to map spatial pollution hotspots; and (iii) source composition analysis revealing the abundance-area paradox: fishing gear constitutes a small proportion of the total number of items, but has the largest physical area per unit item. Pixel-level area extraction can provide more valuable information for coastal monitoring compared to methods based solely on counting.