Classification of Mediterranean Shrub Species from UAV Point Clouds
Modelling fire behaviour in forest fires is based on meteorological, topographical, and vegetation data, including species’ type. To accurately parameterise these models, an inventory of the area of analysis with the maximum spatial and temporal resolution is required. This study investigated the us...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/1/199 |
| _version_ | 1797497687118970880 |
|---|---|
| author | Juan Pedro Carbonell-Rivera Jesús Torralba Javier Estornell Luis Ángel Ruiz Pablo Crespo-Peremarch |
| author_facet | Juan Pedro Carbonell-Rivera Jesús Torralba Javier Estornell Luis Ángel Ruiz Pablo Crespo-Peremarch |
| author_sort | Juan Pedro Carbonell-Rivera |
| collection | DOAJ |
| description | Modelling fire behaviour in forest fires is based on meteorological, topographical, and vegetation data, including species’ type. To accurately parameterise these models, an inventory of the area of analysis with the maximum spatial and temporal resolution is required. This study investigated the use of UAV-based digital aerial photogrammetry (UAV-DAP) point clouds to classify tree and shrub species in Mediterranean forests, and this information is key for the correct generation of wildfire models. In July 2020, two test sites located in the Natural Park of Sierra Calderona (eastern Spain) were analysed, registering 1036 vegetation individuals as reference data, corresponding to 11 shrub and one tree species. Meanwhile, photogrammetric flights were carried out over the test sites, using a UAV DJI Inspire 2 equipped with a Micasense RedEdge multispectral camera. Geometrical, spectral, and neighbour-based features were obtained from the resulting point cloud generated. Using these features, points belonging to tree and shrub species were classified using several machine learning methods, i.e., Decision Trees, Extra Trees, Gradient Boosting, Random Forest, and MultiLayer Perceptron. The best results were obtained using Gradient Boosting, with a mean cross-validation accuracy of 81.7% and 91.5% for test sites 1 and 2, respectively. Once the best classifier was selected, classified points were clustered based on their geometry and tested with evaluation data, and overall accuracies of 81.9% and 96.4% were obtained for test sites 1 and 2, respectively. Results showed that the use of UAV-DAP allows the classification of Mediterranean tree and shrub species. This technique opens a wide range of possibilities, including the identification of species as a first step for further extraction of structure and fuel variables as input for wildfire behaviour models. |
| first_indexed | 2024-03-10T03:22:47Z |
| format | Article |
| id | doaj.art-1dc118a9208d4bc2b308a751d6526a28 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:22:47Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-1dc118a9208d4bc2b308a751d6526a282023-11-23T12:14:44ZengMDPI AGRemote Sensing2072-42922022-01-0114119910.3390/rs14010199Classification of Mediterranean Shrub Species from UAV Point CloudsJuan Pedro Carbonell-Rivera0Jesús Torralba1Javier Estornell2Luis Ángel Ruiz3Pablo Crespo-Peremarch4Geo-Environmental Cartography and Remote Sensing Group (CGAT), Universitat Politècnica de València, Camí de Vera s/n, 46022 Valencia, SpainGeo-Environmental Cartography and Remote Sensing Group (CGAT), Universitat Politècnica de València, Camí de Vera s/n, 46022 Valencia, SpainGeo-Environmental Cartography and Remote Sensing Group (CGAT), Universitat Politècnica de València, Camí de Vera s/n, 46022 Valencia, SpainGeo-Environmental Cartography and Remote Sensing Group (CGAT), Universitat Politècnica de València, Camí de Vera s/n, 46022 Valencia, SpainGeo-Environmental Cartography and Remote Sensing Group (CGAT), Universitat Politècnica de València, Camí de Vera s/n, 46022 Valencia, SpainModelling fire behaviour in forest fires is based on meteorological, topographical, and vegetation data, including species’ type. To accurately parameterise these models, an inventory of the area of analysis with the maximum spatial and temporal resolution is required. This study investigated the use of UAV-based digital aerial photogrammetry (UAV-DAP) point clouds to classify tree and shrub species in Mediterranean forests, and this information is key for the correct generation of wildfire models. In July 2020, two test sites located in the Natural Park of Sierra Calderona (eastern Spain) were analysed, registering 1036 vegetation individuals as reference data, corresponding to 11 shrub and one tree species. Meanwhile, photogrammetric flights were carried out over the test sites, using a UAV DJI Inspire 2 equipped with a Micasense RedEdge multispectral camera. Geometrical, spectral, and neighbour-based features were obtained from the resulting point cloud generated. Using these features, points belonging to tree and shrub species were classified using several machine learning methods, i.e., Decision Trees, Extra Trees, Gradient Boosting, Random Forest, and MultiLayer Perceptron. The best results were obtained using Gradient Boosting, with a mean cross-validation accuracy of 81.7% and 91.5% for test sites 1 and 2, respectively. Once the best classifier was selected, classified points were clustered based on their geometry and tested with evaluation data, and overall accuracies of 81.9% and 96.4% were obtained for test sites 1 and 2, respectively. Results showed that the use of UAV-DAP allows the classification of Mediterranean tree and shrub species. This technique opens a wide range of possibilities, including the identification of species as a first step for further extraction of structure and fuel variables as input for wildfire behaviour models.https://www.mdpi.com/2072-4292/14/1/199Unmanned Aerial Vehicles (UAV)Digital Aerial Photogrammetry (DAP)machine learningdeep learningpoint cloud labellingMediterranean forest |
| spellingShingle | Juan Pedro Carbonell-Rivera Jesús Torralba Javier Estornell Luis Ángel Ruiz Pablo Crespo-Peremarch Classification of Mediterranean Shrub Species from UAV Point Clouds Remote Sensing Unmanned Aerial Vehicles (UAV) Digital Aerial Photogrammetry (DAP) machine learning deep learning point cloud labelling Mediterranean forest |
| title | Classification of Mediterranean Shrub Species from UAV Point Clouds |
| title_full | Classification of Mediterranean Shrub Species from UAV Point Clouds |
| title_fullStr | Classification of Mediterranean Shrub Species from UAV Point Clouds |
| title_full_unstemmed | Classification of Mediterranean Shrub Species from UAV Point Clouds |
| title_short | Classification of Mediterranean Shrub Species from UAV Point Clouds |
| title_sort | classification of mediterranean shrub species from uav point clouds |
| topic | Unmanned Aerial Vehicles (UAV) Digital Aerial Photogrammetry (DAP) machine learning deep learning point cloud labelling Mediterranean forest |
| url | https://www.mdpi.com/2072-4292/14/1/199 |
| work_keys_str_mv | AT juanpedrocarbonellrivera classificationofmediterraneanshrubspeciesfromuavpointclouds AT jesustorralba classificationofmediterraneanshrubspeciesfromuavpointclouds AT javierestornell classificationofmediterraneanshrubspeciesfromuavpointclouds AT luisangelruiz classificationofmediterraneanshrubspeciesfromuavpointclouds AT pablocrespoperemarch classificationofmediterraneanshrubspeciesfromuavpointclouds |