Learning to Identify Illegal Landfills through Scene Classification in Aerial Images

Illegal landfills are uncontrolled disposals of waste that cause severe environmental and health risk. Discovering them as early as possible is of prominent importance for preventing hazards, such as fire pollution and leakage. Before the digital era, the only means to detect illegal waste dumps was...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Rocio Nahime Torres, Piero Fraternali
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/21f083e58a4e412c939395e4bb1a8bd0
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:21f083e58a4e412c939395e4bb1a8bd0
record_format dspace
spelling oai:doaj.org-article:21f083e58a4e412c939395e4bb1a8bd02021-11-25T18:53:52ZLearning to Identify Illegal Landfills through Scene Classification in Aerial Images10.3390/rs132245202072-4292https://doaj.org/article/21f083e58a4e412c939395e4bb1a8bd02021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4520https://doaj.org/toc/2072-4292Illegal landfills are uncontrolled disposals of waste that cause severe environmental and health risk. Discovering them as early as possible is of prominent importance for preventing hazards, such as fire pollution and leakage. Before the digital era, the only means to detect illegal waste dumps was the on site inspection of potentially suspicious sites, a procedure extremely costly and impossible to scale to a vast territory. With the advent of Earth observation technology, scanning the territory via aerial images has become possible. However, manual image interpretation remains a complex and time-consuming task that requires expert skill. Photo interpretation can be partially automated by embedding the expert knowledge within a data driven classifier trained with samples provided by human annotators. In this paper, the detection of illegal landfills is formulated as a multi-scale scene classification problem. Scene elements positioning and spatial relations constitute hints of the presence of illegal waste dumps. A dataset of ≈3000 images (20 cm resolution per pixel) was created with the help of expert photo interpreters. A combination of ResNet50 and Feature Pyramid Network (FPN) elements accounting for different object scales achieves 88% precision with an 87% of recall in a test area. The results proved the feasibility of applying convolutional neural networks for scene classification in this scenario to optimize the process of waste dumps detection.Rocio Nahime TorresPiero FraternaliMDPI AGarticleillegal landfillscontaminationscene classificationdeep learningremote sensingcomputer visionScienceQENRemote Sensing, Vol 13, Iss 4520, p 4520 (2021)
institution DOAJ
collection DOAJ
language EN
topic illegal landfills
contamination
scene classification
deep learning
remote sensing
computer vision
Science
Q
spellingShingle illegal landfills
contamination
scene classification
deep learning
remote sensing
computer vision
Science
Q
Rocio Nahime Torres
Piero Fraternali
Learning to Identify Illegal Landfills through Scene Classification in Aerial Images
description Illegal landfills are uncontrolled disposals of waste that cause severe environmental and health risk. Discovering them as early as possible is of prominent importance for preventing hazards, such as fire pollution and leakage. Before the digital era, the only means to detect illegal waste dumps was the on site inspection of potentially suspicious sites, a procedure extremely costly and impossible to scale to a vast territory. With the advent of Earth observation technology, scanning the territory via aerial images has become possible. However, manual image interpretation remains a complex and time-consuming task that requires expert skill. Photo interpretation can be partially automated by embedding the expert knowledge within a data driven classifier trained with samples provided by human annotators. In this paper, the detection of illegal landfills is formulated as a multi-scale scene classification problem. Scene elements positioning and spatial relations constitute hints of the presence of illegal waste dumps. A dataset of ≈3000 images (20 cm resolution per pixel) was created with the help of expert photo interpreters. A combination of ResNet50 and Feature Pyramid Network (FPN) elements accounting for different object scales achieves 88% precision with an 87% of recall in a test area. The results proved the feasibility of applying convolutional neural networks for scene classification in this scenario to optimize the process of waste dumps detection.
format article
author Rocio Nahime Torres
Piero Fraternali
author_facet Rocio Nahime Torres
Piero Fraternali
author_sort Rocio Nahime Torres
title Learning to Identify Illegal Landfills through Scene Classification in Aerial Images
title_short Learning to Identify Illegal Landfills through Scene Classification in Aerial Images
title_full Learning to Identify Illegal Landfills through Scene Classification in Aerial Images
title_fullStr Learning to Identify Illegal Landfills through Scene Classification in Aerial Images
title_full_unstemmed Learning to Identify Illegal Landfills through Scene Classification in Aerial Images
title_sort learning to identify illegal landfills through scene classification in aerial images
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/21f083e58a4e412c939395e4bb1a8bd0
work_keys_str_mv AT rocionahimetorres learningtoidentifyillegallandfillsthroughsceneclassificationinaerialimages
AT pierofraternali learningtoidentifyillegallandfillsthroughsceneclassificationinaerialimages
_version_ 1718410575257534464