Tree Species Classification in a Complex Brazilian Tropical Forest Using Hyperspectral and LiDAR Data
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Outros Autores: | , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.3390/f14050945 http://hdl.handle.net/11449/248926 |
Resumo: | This study experiments with different combinations of UAV hyperspectral data and LiDAR metrics for classifying eight tree species found in a Brazilian Atlantic Forest remnant, the most degraded Brazilian biome with high fragmentation but with huge structural complexity. The selection of the species was done based on the number of tree samples, which exist in the plot data and in the fact the UAV imagery does not acquire information below the forest canopy. Due to the complexity of the forest, only species that exist in the upper canopy of the remnant were included in the classification. A combination of hyperspectral UAV images and LiDAR point clouds were in the experiment. The hyperspectral images were photogrammetric and radiometric processed to obtain orthomosaics with reflectance factor values. Raw spectra were extracted from the trees, and vegetation indices (VIs) were calculated. Regarding the LiDAR data, both the point cloud—referred to as Peak Returns (PR)—and the full-waveform (FWF) LiDAR were included in this study. The point clouds were processed to normalize the intensities and heights, and different metrics for each data type (PR and FWF) were extracted. Segmentation was preformed semi-automatically using the superpixel algorithm, followed with manual correction to ensure precise tree crown delineation before tree species classification. Thirteen different classification scenarios were tested. The scenarios included spectral features and LiDAR metrics either combined or not. The best result was obtained with all features transformed with principal component analysis with an accuracy of 76%, which did not differ significantly from the scenarios using the raw spectra or VIs with PR or FWF LiDAR metrics. The combination of spectral data with geometric information from LiDAR improved the classification of tree species in a complex tropical forest, and these results can serve to inform management and conservation practices of these forest remnants. |
id |
UNSP_66c9ac7711fe47e3d494df79b9976b52 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/248926 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Tree Species Classification in a Complex Brazilian Tropical Forest Using Hyperspectral and LiDAR DataBrazilian Atlantic Foresthyperspectral imagingLiDARsuperpixel segmentationtree species mappingThis study experiments with different combinations of UAV hyperspectral data and LiDAR metrics for classifying eight tree species found in a Brazilian Atlantic Forest remnant, the most degraded Brazilian biome with high fragmentation but with huge structural complexity. The selection of the species was done based on the number of tree samples, which exist in the plot data and in the fact the UAV imagery does not acquire information below the forest canopy. Due to the complexity of the forest, only species that exist in the upper canopy of the remnant were included in the classification. A combination of hyperspectral UAV images and LiDAR point clouds were in the experiment. The hyperspectral images were photogrammetric and radiometric processed to obtain orthomosaics with reflectance factor values. Raw spectra were extracted from the trees, and vegetation indices (VIs) were calculated. Regarding the LiDAR data, both the point cloud—referred to as Peak Returns (PR)—and the full-waveform (FWF) LiDAR were included in this study. The point clouds were processed to normalize the intensities and heights, and different metrics for each data type (PR and FWF) were extracted. Segmentation was preformed semi-automatically using the superpixel algorithm, followed with manual correction to ensure precise tree crown delineation before tree species classification. Thirteen different classification scenarios were tested. The scenarios included spectral features and LiDAR metrics either combined or not. The best result was obtained with all features transformed with principal component analysis with an accuracy of 76%, which did not differ significantly from the scenarios using the raw spectra or VIs with PR or FWF LiDAR metrics. The combination of spectral data with geometric information from LiDAR improved the classification of tree species in a complex tropical forest, and these results can serve to inform management and conservation practices of these forest remnants.Academy of FinlandFaculty of Forestry and Wood Sciences Czech University of Life Sciences Prague (CULS), Kamýcká 129Department of Cartography São Paulo State University (FCT/UNSEP), Roberto Simonsen 305, SPDepartment of Remote Sensing and Photogrammetry Finnish Geospatial Research Institute (FGI) National Land Survey of Finland (NLS), Vuorimiehentie 5Department of Geography University of Cambridge, Downing Site, 20 Downing PlaceBrazilian Forest Service (SFB), SCEN Trecho 2, Sede do Ibama, DFDepartment of Cartography São Paulo State University (FCT/UNSEP), Roberto Simonsen 305, SPAcademy of Finland: 273806Czech University of Life Sciences Prague (CULS)Universidade Estadual Paulista (UNESP)National Land Survey of Finland (NLS)University of CambridgeBrazilian Forest Service (SFB)Pereira Martins-Neto, Rorai [UNESP]Garcia Tommaselli, Antonio Maria [UNESP]Imai, Nilton Nobuhiro [UNESP]Honkavaara, EijaMiltiadou, MiltoSaito Moriya, Erika Akemi [UNESP]David, Hassan Camil2023-07-29T13:57:33Z2023-07-29T13:57:33Z2023-05-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/f14050945Forests, v. 14, n. 5, 2023.1999-4907http://hdl.handle.net/11449/24892610.3390/f140509452-s2.0-85160791384Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengForestsinfo:eu-repo/semantics/openAccess2023-07-29T13:57:33Zoai:repositorio.unesp.br:11449/248926Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462023-07-29T13:57:33Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Tree Species Classification in a Complex Brazilian Tropical Forest Using Hyperspectral and LiDAR Data |
title |
Tree Species Classification in a Complex Brazilian Tropical Forest Using Hyperspectral and LiDAR Data |
spellingShingle |
Tree Species Classification in a Complex Brazilian Tropical Forest Using Hyperspectral and LiDAR Data Pereira Martins-Neto, Rorai [UNESP] Brazilian Atlantic Forest hyperspectral imaging LiDAR superpixel segmentation tree species mapping |
title_short |
Tree Species Classification in a Complex Brazilian Tropical Forest Using Hyperspectral and LiDAR Data |
title_full |
Tree Species Classification in a Complex Brazilian Tropical Forest Using Hyperspectral and LiDAR Data |
title_fullStr |
Tree Species Classification in a Complex Brazilian Tropical Forest Using Hyperspectral and LiDAR Data |
title_full_unstemmed |
Tree Species Classification in a Complex Brazilian Tropical Forest Using Hyperspectral and LiDAR Data |
title_sort |
Tree Species Classification in a Complex Brazilian Tropical Forest Using Hyperspectral and LiDAR Data |
author |
Pereira Martins-Neto, Rorai [UNESP] |
author_facet |
Pereira Martins-Neto, Rorai [UNESP] Garcia Tommaselli, Antonio Maria [UNESP] Imai, Nilton Nobuhiro [UNESP] Honkavaara, Eija Miltiadou, Milto Saito Moriya, Erika Akemi [UNESP] David, Hassan Camil |
author_role |
author |
author2 |
Garcia Tommaselli, Antonio Maria [UNESP] Imai, Nilton Nobuhiro [UNESP] Honkavaara, Eija Miltiadou, Milto Saito Moriya, Erika Akemi [UNESP] David, Hassan Camil |
author2_role |
author author author author author author |
dc.contributor.none.fl_str_mv |
Czech University of Life Sciences Prague (CULS) Universidade Estadual Paulista (UNESP) National Land Survey of Finland (NLS) University of Cambridge Brazilian Forest Service (SFB) |
dc.contributor.author.fl_str_mv |
Pereira Martins-Neto, Rorai [UNESP] Garcia Tommaselli, Antonio Maria [UNESP] Imai, Nilton Nobuhiro [UNESP] Honkavaara, Eija Miltiadou, Milto Saito Moriya, Erika Akemi [UNESP] David, Hassan Camil |
dc.subject.por.fl_str_mv |
Brazilian Atlantic Forest hyperspectral imaging LiDAR superpixel segmentation tree species mapping |
topic |
Brazilian Atlantic Forest hyperspectral imaging LiDAR superpixel segmentation tree species mapping |
description |
This study experiments with different combinations of UAV hyperspectral data and LiDAR metrics for classifying eight tree species found in a Brazilian Atlantic Forest remnant, the most degraded Brazilian biome with high fragmentation but with huge structural complexity. The selection of the species was done based on the number of tree samples, which exist in the plot data and in the fact the UAV imagery does not acquire information below the forest canopy. Due to the complexity of the forest, only species that exist in the upper canopy of the remnant were included in the classification. A combination of hyperspectral UAV images and LiDAR point clouds were in the experiment. The hyperspectral images were photogrammetric and radiometric processed to obtain orthomosaics with reflectance factor values. Raw spectra were extracted from the trees, and vegetation indices (VIs) were calculated. Regarding the LiDAR data, both the point cloud—referred to as Peak Returns (PR)—and the full-waveform (FWF) LiDAR were included in this study. The point clouds were processed to normalize the intensities and heights, and different metrics for each data type (PR and FWF) were extracted. Segmentation was preformed semi-automatically using the superpixel algorithm, followed with manual correction to ensure precise tree crown delineation before tree species classification. Thirteen different classification scenarios were tested. The scenarios included spectral features and LiDAR metrics either combined or not. The best result was obtained with all features transformed with principal component analysis with an accuracy of 76%, which did not differ significantly from the scenarios using the raw spectra or VIs with PR or FWF LiDAR metrics. The combination of spectral data with geometric information from LiDAR improved the classification of tree species in a complex tropical forest, and these results can serve to inform management and conservation practices of these forest remnants. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023-07-29T13:57:33Z 2023-07-29T13:57:33Z 2023-05-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.3390/f14050945 Forests, v. 14, n. 5, 2023. 1999-4907 http://hdl.handle.net/11449/248926 10.3390/f14050945 2-s2.0-85160791384 |
url |
http://dx.doi.org/10.3390/f14050945 http://hdl.handle.net/11449/248926 |
identifier_str_mv |
Forests, v. 14, n. 5, 2023. 1999-4907 10.3390/f14050945 2-s2.0-85160791384 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Forests |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1799964924202450944 |