Land Cover Classification from Very High-Resolution UAS Data for Flood Risk Mapping
Monitoring the world’s areas that are more vulnerable to natural hazards has become crucial worldwide. In order to reduce disaster risk, effective tools and relevant land cover (LC) data are needed. This work aimed to generate a high-resolution LC map of flood-prone rural villages in southwest Niger...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/15/5622 |
| _version_ | 1797440706631958528 |
|---|---|
| author | Elena Belcore Marco Piras Alessandro Pezzoli |
| author_facet | Elena Belcore Marco Piras Alessandro Pezzoli |
| author_sort | Elena Belcore |
| collection | DOAJ |
| description | Monitoring the world’s areas that are more vulnerable to natural hazards has become crucial worldwide. In order to reduce disaster risk, effective tools and relevant land cover (LC) data are needed. This work aimed to generate a high-resolution LC map of flood-prone rural villages in southwest Niger using multispectral drone imagery. The LC was focused on highly thematically detailed classes. Two photogrammetric flights of fixed-wing unmanned aerial systems (UAS) using RGB and NIR optical sensors were realized. The LC input dataset was generated using structure from motion (SfM) standard workflow, resulting in two orthomosaics and a digital surface model (DSM). The LC system is composed of nine classes, which are relevant for estimating flood-induced potential damages, such as houses and production areas. The LC was generated through object-oriented supervised classification using a random forest (RF) classifier. Textural and elevation features were computed to overcome the mapping difficulties due to the high spectral homogeneity of cover types. The training-test dataset was manually defined. The segmentation resulted in an F1_score of 0.70 and a median Jaccard index of 0.88. The RF model performed with an overall accuracy of 0.94, with the grasslands and the rocky clustered areas classes the least performant. |
| first_indexed | 2024-03-09T12:12:11Z |
| format | Article |
| id | doaj.art-d64ee96657c94230ad35310391d6f911 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T12:12:11Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d64ee96657c94230ad35310391d6f9112023-11-30T22:50:55ZengMDPI AGSensors1424-82202022-07-012215562210.3390/s22155622Land Cover Classification from Very High-Resolution UAS Data for Flood Risk MappingElena Belcore0Marco Piras1Alessandro Pezzoli2DIATI, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Torino, ItalyDIATI, Politecnico di Torino, Corso Duca degli Abruzzi 24, 10129 Torino, ItalyDIST, Politecnico and Università degli Studi di Torino, Viale Mattioli 39, 10125 Torino, ItalyMonitoring the world’s areas that are more vulnerable to natural hazards has become crucial worldwide. In order to reduce disaster risk, effective tools and relevant land cover (LC) data are needed. This work aimed to generate a high-resolution LC map of flood-prone rural villages in southwest Niger using multispectral drone imagery. The LC was focused on highly thematically detailed classes. Two photogrammetric flights of fixed-wing unmanned aerial systems (UAS) using RGB and NIR optical sensors were realized. The LC input dataset was generated using structure from motion (SfM) standard workflow, resulting in two orthomosaics and a digital surface model (DSM). The LC system is composed of nine classes, which are relevant for estimating flood-induced potential damages, such as houses and production areas. The LC was generated through object-oriented supervised classification using a random forest (RF) classifier. Textural and elevation features were computed to overcome the mapping difficulties due to the high spectral homogeneity of cover types. The training-test dataset was manually defined. The segmentation resulted in an F1_score of 0.70 and a median Jaccard index of 0.88. The RF model performed with an overall accuracy of 0.94, with the grasslands and the rocky clustered areas classes the least performant.https://www.mdpi.com/1424-8220/22/15/5622UASland coververy high resolutionstructure from motionmachine learningclimate change |
| spellingShingle | Elena Belcore Marco Piras Alessandro Pezzoli Land Cover Classification from Very High-Resolution UAS Data for Flood Risk Mapping Sensors UAS land cover very high resolution structure from motion machine learning climate change |
| title | Land Cover Classification from Very High-Resolution UAS Data for Flood Risk Mapping |
| title_full | Land Cover Classification from Very High-Resolution UAS Data for Flood Risk Mapping |
| title_fullStr | Land Cover Classification from Very High-Resolution UAS Data for Flood Risk Mapping |
| title_full_unstemmed | Land Cover Classification from Very High-Resolution UAS Data for Flood Risk Mapping |
| title_short | Land Cover Classification from Very High-Resolution UAS Data for Flood Risk Mapping |
| title_sort | land cover classification from very high resolution uas data for flood risk mapping |
| topic | UAS land cover very high resolution structure from motion machine learning climate change |
| url | https://www.mdpi.com/1424-8220/22/15/5622 |
| work_keys_str_mv | AT elenabelcore landcoverclassificationfromveryhighresolutionuasdataforfloodriskmapping AT marcopiras landcoverclassificationfromveryhighresolutionuasdataforfloodriskmapping AT alessandropezzoli landcoverclassificationfromveryhighresolutionuasdataforfloodriskmapping |