Targeting Plastics: Machine Learning Applied to Litter Detection in Aerial Multispectral Images
The occurrence of litter in natural areas is nowadays one of the major environmental challenges. The uncontrolled dumping of solid waste in nature not only threatens wildlife on land and in water, but also constitutes a serious threat to human health. The detection and monitoring of areas affected b...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/22/5820 |
| _version_ | 1797464054837542912 |
|---|---|
| author | Marian-Daniel Iordache Liesbeth De Keukelaere Robrecht Moelans Lisa Landuyt Mehrdad Moshtaghi Paolo Corradi Els Knaeps |
| author_facet | Marian-Daniel Iordache Liesbeth De Keukelaere Robrecht Moelans Lisa Landuyt Mehrdad Moshtaghi Paolo Corradi Els Knaeps |
| author_sort | Marian-Daniel Iordache |
| collection | DOAJ |
| description | The occurrence of litter in natural areas is nowadays one of the major environmental challenges. The uncontrolled dumping of solid waste in nature not only threatens wildlife on land and in water, but also constitutes a serious threat to human health. The detection and monitoring of areas affected by litter pollution is thus of utmost importance, as it allows for the cleaning of these areas and guides public authorities in defining mitigation measures. Among the methods used to spot littered areas, aerial surveillance stands out as a valuable alternative as it allows for the detection of relatively small such regions while covering a relatively large area in a short timeframe. In this study, remotely piloted aircraft systems equipped with multispectral cameras are deployed over littered areas with the ultimate goal of obtaining classification maps based on spectral characteristics. Our approach employs classification algorithms based on random forest approaches in order to distinguish between four classes of natural land cover types and five litter classes. The obtained results show that the detection of various litter types is feasible in the proposed scenario and the employed machine learning algorithms achieve accuracies superior to 85% for all classes in test data. The study further explores sources of errors, the effect of spatial resolution on the retrieved maps and the applicability of the designed algorithm to floating litter detection. |
| first_indexed | 2024-03-09T18:02:29Z |
| format | Article |
| id | doaj.art-e723c001120846c1ba1c1199692b8fd2 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T18:02:29Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-e723c001120846c1ba1c1199692b8fd22023-11-24T09:50:57ZengMDPI AGRemote Sensing2072-42922022-11-011422582010.3390/rs14225820Targeting Plastics: Machine Learning Applied to Litter Detection in Aerial Multispectral ImagesMarian-Daniel Iordache0Liesbeth De Keukelaere1Robrecht Moelans2Lisa Landuyt3Mehrdad Moshtaghi4Paolo Corradi5Els Knaeps6Flemish Institute for Technological Research, Center for Remote Sensing and Earth Observation Processes (VITO-TAP), Boeretang 200, B-2400 Mol, BelgiumFlemish Institute for Technological Research, Center for Remote Sensing and Earth Observation Processes (VITO-TAP), Boeretang 200, B-2400 Mol, BelgiumFlemish Institute for Technological Research, Center for Remote Sensing and Earth Observation Processes (VITO-TAP), Boeretang 200, B-2400 Mol, BelgiumFlemish Institute for Technological Research, Center for Remote Sensing and Earth Observation Processes (VITO-TAP), Boeretang 200, B-2400 Mol, BelgiumFlemish Institute for Technological Research, Center for Remote Sensing and Earth Observation Processes (VITO-TAP), Boeretang 200, B-2400 Mol, BelgiumEuropean Space Research and Technology Centre, European Space Agency, 2201 Noordwijk, The NetherlandsFlemish Institute for Technological Research, Center for Remote Sensing and Earth Observation Processes (VITO-TAP), Boeretang 200, B-2400 Mol, BelgiumThe occurrence of litter in natural areas is nowadays one of the major environmental challenges. The uncontrolled dumping of solid waste in nature not only threatens wildlife on land and in water, but also constitutes a serious threat to human health. The detection and monitoring of areas affected by litter pollution is thus of utmost importance, as it allows for the cleaning of these areas and guides public authorities in defining mitigation measures. Among the methods used to spot littered areas, aerial surveillance stands out as a valuable alternative as it allows for the detection of relatively small such regions while covering a relatively large area in a short timeframe. In this study, remotely piloted aircraft systems equipped with multispectral cameras are deployed over littered areas with the ultimate goal of obtaining classification maps based on spectral characteristics. Our approach employs classification algorithms based on random forest approaches in order to distinguish between four classes of natural land cover types and five litter classes. The obtained results show that the detection of various litter types is feasible in the proposed scenario and the employed machine learning algorithms achieve accuracies superior to 85% for all classes in test data. The study further explores sources of errors, the effect of spatial resolution on the retrieved maps and the applicability of the designed algorithm to floating litter detection.https://www.mdpi.com/2072-4292/14/22/5820litter detectionplastic pollutionmultispectral dataremotely piloted aircraft systemsmachine learningmulticlass classification |
| spellingShingle | Marian-Daniel Iordache Liesbeth De Keukelaere Robrecht Moelans Lisa Landuyt Mehrdad Moshtaghi Paolo Corradi Els Knaeps Targeting Plastics: Machine Learning Applied to Litter Detection in Aerial Multispectral Images Remote Sensing litter detection plastic pollution multispectral data remotely piloted aircraft systems machine learning multiclass classification |
| title | Targeting Plastics: Machine Learning Applied to Litter Detection in Aerial Multispectral Images |
| title_full | Targeting Plastics: Machine Learning Applied to Litter Detection in Aerial Multispectral Images |
| title_fullStr | Targeting Plastics: Machine Learning Applied to Litter Detection in Aerial Multispectral Images |
| title_full_unstemmed | Targeting Plastics: Machine Learning Applied to Litter Detection in Aerial Multispectral Images |
| title_short | Targeting Plastics: Machine Learning Applied to Litter Detection in Aerial Multispectral Images |
| title_sort | targeting plastics machine learning applied to litter detection in aerial multispectral images |
| topic | litter detection plastic pollution multispectral data remotely piloted aircraft systems machine learning multiclass classification |
| url | https://www.mdpi.com/2072-4292/14/22/5820 |
| work_keys_str_mv | AT mariandanieliordache targetingplasticsmachinelearningappliedtolitterdetectioninaerialmultispectralimages AT liesbethdekeukelaere targetingplasticsmachinelearningappliedtolitterdetectioninaerialmultispectralimages AT robrechtmoelans targetingplasticsmachinelearningappliedtolitterdetectioninaerialmultispectralimages AT lisalanduyt targetingplasticsmachinelearningappliedtolitterdetectioninaerialmultispectralimages AT mehrdadmoshtaghi targetingplasticsmachinelearningappliedtolitterdetectioninaerialmultispectralimages AT paolocorradi targetingplasticsmachinelearningappliedtolitterdetectioninaerialmultispectralimages AT elsknaeps targetingplasticsmachinelearningappliedtolitterdetectioninaerialmultispectralimages |