EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

WastePNOA: A Dataset for Waste Disposal Site Detection Using PNOA Imagery

Georgios Tsionkis, Konstantinos Gkountakos, Konstantinos Ioannidis, Theodora Tsikrika, Stefanos Vrochidis, Ioannis Kompatsiaris

Remote Sensing · 20.11.2026 · 18 (22) · 4003

DOI: 10.3390/rs18224003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 20.11.2026. Verfasst von Georgios Tsionkis und 5 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union’s Internal Security Fund Project FAUNOS.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Improper disposal of solid waste is a major source of environmental pollution, making timely detection essential for protecting environmental and human health. Although several remote sensing datasets have recently been proposed for solid waste detection, most are limited in terms of spatial coverage, temporal diversity, annotation quality, and resolution. In this work, we introduce WastePNOA, a publicly available dataset based on Very-High-Resolution (VHR) aircraft imagery from the Spanish National Aerial Orthophotography Plan, also known as PNOA. The dataset comprises 24,884 images from 132 landfill areas across Spain between 2013 and 2023. The dataset provides pixel-level annotations across three semantic classes: waste, leachate pond, and background. We introduce two dataset distributions, WastePNOA-Spatial and WastePNOA-Temporal, to investigate the presence of waste across geographically unseen areas and the temporal evolution of previously observed areas, respectively, while also assessing the effect of background-only images. SegFormer consistently achieves the strongest overall performance, reaching 58.59% and 67.30% foreground-only mIoU for spatial and temporal generalization, respectively. Results also highlight the importance of background-only images for robust performance under realistic background-dominant scenes, while indicating that retaining all such images may be redundant. Overall, WastePNOA provides a challenging benchmark for solid waste disposal site detection and supports future research in remote-sensing-based environmental monitoring.

Förderung

  • European Union’s Internal Security Fund Project FAUNOS

Zitieren

APA

Tsionkis, G., Gkountakos, K., Ioannidis, K., Tsikrika, T., Vrochidis, S., & Kompatsiaris, I. (2026). WastePNOA: A Dataset for Waste Disposal Site Detection Using PNOA Imagery. Remote Sensing, 18(22), 4003. https://doi.org/10.3390/rs18224003

Vancouver

Tsionkis G, Gkountakos K, Ioannidis K, Tsikrika T, Vrochidis S, Kompatsiaris I. WastePNOA: A Dataset for Waste Disposal Site Detection Using PNOA Imagery. Remote Sensing. 2026;18(22):4003. doi:10.3390/rs18224003

BibTeX
@article{Tsionkis2026,
  author = {Tsionkis, Georgios and Gkountakos, Konstantinos and Ioannidis, Konstantinos and Tsikrika, Theodora and Vrochidis, Stefanos and Kompatsiaris, Ioannis},
  title = {WastePNOA: A Dataset for Waste Disposal Site Detection Using PNOA Imagery},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {22},
  pages = {4003},
  doi = {10.3390/rs18224003}
}
Kostenlos starten →