Classification of tree species based on hyperspectral reflectance images of stem bark
ABSTRACTAutomatization of tree species identification in the field is crucial in improving forest-based bioeconomy, supporting forest management, and facilitating in situ data collection for remote sensing applications. However, tree species recognition has never been addressed with hyperspectral re...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | European Journal of Remote Sensing |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/22797254.2022.2161420 |
| _version_ | 1797975453559947264 |
|---|---|
| author | Jussi Juola Aarne Hovi Miina Rautiainen |
| author_facet | Jussi Juola Aarne Hovi Miina Rautiainen |
| author_sort | Jussi Juola |
| collection | DOAJ |
| description | ABSTRACTAutomatization of tree species identification in the field is crucial in improving forest-based bioeconomy, supporting forest management, and facilitating in situ data collection for remote sensing applications. However, tree species recognition has never been addressed with hyperspectral reflectance images of stem bark before. We investigated how stem bark texture differs between tree species using a hyperspectral camera set-up and gray level co-occurrence matrices and assessed the potential of using reflectance spectra and texture features of stem bark to identify tree species. The analyses were based on 200 hyperspectral reflectance data cubes (415–925 nm) representing ten tree species. There were subtle interspecific differences in bark texture. Using average spectral features in linear discriminant analysis classifier resulted in classification accuracy of 92–96.5%. Using spectral and texture features together resulted in accuracy of 93–97.5%. With a convolutional neural network, we obtained an accuracy of 94%. Our study showed that the spectral features of stem bark were robust for classifying tree species, but importantly, bark texture is beneficial when combined with spectral data. Our results suggest that in situ imaging spectroscopy is a promising sensor technology for developing accurate tree species identification applications to support remote sensing. |
| first_indexed | 2024-04-11T04:35:48Z |
| format | Article |
| id | doaj.art-5fe997f9528c46b098b1936dacb007bd |
| institution | Directory Open Access Journal |
| issn | 2279-7254 |
| language | English |
| last_indexed | 2024-04-11T04:35:48Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | European Journal of Remote Sensing |
| spelling | doaj.art-5fe997f9528c46b098b1936dacb007bd2022-12-28T12:19:51ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542022-12-0111510.1080/22797254.2022.2161420Classification of tree species based on hyperspectral reflectance images of stem barkJussi Juola0Aarne Hovi1Miina Rautiainen2Department of Built Environment, School of Engineering, Aalto University, Aalto, FinlandDepartment of Built Environment, School of Engineering, Aalto University, Aalto, FinlandDepartment of Built Environment, School of Engineering, Aalto University, Aalto, FinlandABSTRACTAutomatization of tree species identification in the field is crucial in improving forest-based bioeconomy, supporting forest management, and facilitating in situ data collection for remote sensing applications. However, tree species recognition has never been addressed with hyperspectral reflectance images of stem bark before. We investigated how stem bark texture differs between tree species using a hyperspectral camera set-up and gray level co-occurrence matrices and assessed the potential of using reflectance spectra and texture features of stem bark to identify tree species. The analyses were based on 200 hyperspectral reflectance data cubes (415–925 nm) representing ten tree species. There were subtle interspecific differences in bark texture. Using average spectral features in linear discriminant analysis classifier resulted in classification accuracy of 92–96.5%. Using spectral and texture features together resulted in accuracy of 93–97.5%. With a convolutional neural network, we obtained an accuracy of 94%. Our study showed that the spectral features of stem bark were robust for classifying tree species, but importantly, bark texture is beneficial when combined with spectral data. Our results suggest that in situ imaging spectroscopy is a promising sensor technology for developing accurate tree species identification applications to support remote sensing.https://www.tandfonline.com/doi/10.1080/22797254.2022.2161420Hyperspectralreflectance imagetexturestem barktree speciesforestry |
| spellingShingle | Jussi Juola Aarne Hovi Miina Rautiainen Classification of tree species based on hyperspectral reflectance images of stem bark European Journal of Remote Sensing Hyperspectral reflectance image texture stem bark tree species forestry |
| title | Classification of tree species based on hyperspectral reflectance images of stem bark |
| title_full | Classification of tree species based on hyperspectral reflectance images of stem bark |
| title_fullStr | Classification of tree species based on hyperspectral reflectance images of stem bark |
| title_full_unstemmed | Classification of tree species based on hyperspectral reflectance images of stem bark |
| title_short | Classification of tree species based on hyperspectral reflectance images of stem bark |
| title_sort | classification of tree species based on hyperspectral reflectance images of stem bark |
| topic | Hyperspectral reflectance image texture stem bark tree species forestry |
| url | https://www.tandfonline.com/doi/10.1080/22797254.2022.2161420 |
| work_keys_str_mv | AT jussijuola classificationoftreespeciesbasedonhyperspectralreflectanceimagesofstembark AT aarnehovi classificationoftreespeciesbasedonhyperspectralreflectanceimagesofstembark AT miinarautiainen classificationoftreespeciesbasedonhyperspectralreflectanceimagesofstembark |