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

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.

Authors

Institutions

Publication Details

Journal
Remote Sensing
Published
2026-11-20
DOI
https://doi.org/10.3390/rs18224003
Primary Topic
Remote-Sensing Image Classification
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

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

Konstantinos Gkountakos, Theodora Tsikrika, Stefanos Vrochidis, Ioannis Yiannis Kompatsiaris et al.
2 links
Remote Sensing
Remote-Sensing Image Classification
article

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

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

Abstract

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.

Remote SensingVol. 18(22)
Information Technologies Institute (GR), Centre for Research and Technology Hellas (GR)
Responsible consumption and production
Remote-Sensing Image Classification
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon