Search papers, labs, and topics across Lattice.
The paper introduces PLAS-Net, an instance segmentation framework, to extract pixel-accurate physical footprints of coastal debris from UAV imagery, addressing the overestimation of litter area inherent in bounding-box detection methods. Evaluated on a challenging dataset from Koh Tao, Thailand, PLAS-Net achieves a mAP_50 of 58.7%, outperforming eleven baseline models and demonstrating improved mask fidelity. Downstream analyses using PLAS-Net's output reveal insights into fragmentation dynamics, pollution hotspots, and the abundance-area paradox of different litter types, highlighting the value of pixel-level area extraction for coastal monitoring.
Ditch the bounding boxes: PLAS-Net's pixel-perfect segmentation of beach litter reveals that fishing gear, though numerically scarce, dominates the total pollution area.
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.
