Feature Extraction and Classification of Canopy Gaps Using GLCM- and MLBP-Based Rotation-Invariant Feature Descriptors Derived from WorldView-3 Imagery
Accurate mapping of selective logging (SL) serves as the foundation for additional research on forest restoration and regeneration, species diversification and distribution, and ecosystem dynamics, among other applications. This study aimed to model canopy gaps created by illegal logging of <i>...
| Auteurs principaux: | , , , |
|---|---|
| Format: | Article |
| Langue: | English |
| Publié: |
MDPI AG
2023-03-01
|
| Collection: | Geomatics |
| Sujets: | |
| Accès en ligne: | https://www.mdpi.com/2673-7418/3/1/14 |
| _version_ | 1827749651604832256 |
|---|---|
| author | Colbert M. Jackson Elhadi Adam Iqra Atif Muhammad A. Mahboob |
| author_facet | Colbert M. Jackson Elhadi Adam Iqra Atif Muhammad A. Mahboob |
| author_sort | Colbert M. Jackson |
| collection | DOAJ |
| description | Accurate mapping of selective logging (SL) serves as the foundation for additional research on forest restoration and regeneration, species diversification and distribution, and ecosystem dynamics, among other applications. This study aimed to model canopy gaps created by illegal logging of <i>Ocotea usambarensis</i> in Mt. Kenya Forest Reserve (MKFR). A texture-spectral analysis approach was applied to exploit the potential of WorldView-3 (WV-3) multispectral imagery. First, texture properties were explored in the sub-band images using fused grey-level co-occurrence matrix (GLCM)- and local binary pattern (LBP)-based texture feature extraction. Second, the texture features were fused with colour using the multivariate local binary pattern (MLBP) model. The G-statistic and Euclidean distance similarity measures were applied to increase accuracy. The random forest (RF) and support vector machine (SVM) were used to identify and classify distinctive features in the texture and spectral domains of the WV-3 dataset. The variable importance measurement in RF ranked the relative influence of sets of variables in the classification models. Overall accuracy (OA) scores for the respective MLBP models were in the range of 80–95.1%. The respective user’s accuracy (UA) and producer’s accuracy (PA) for the univariate LBP and MLBP models were in the range of 67–75% and 77–100%, respectively. |
| first_indexed | 2024-03-11T06:29:38Z |
| format | Article |
| id | doaj.art-fe7cff35be7a43378e2fb34ba223a877 |
| institution | Directory Open Access Journal |
| issn | 2673-7418 |
| language | English |
| last_indexed | 2024-03-11T06:29:38Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Geomatics |
| spelling | doaj.art-fe7cff35be7a43378e2fb34ba223a8772023-11-17T11:19:39ZengMDPI AGGeomatics2673-74182023-03-013125026510.3390/geomatics3010014Feature Extraction and Classification of Canopy Gaps Using GLCM- and MLBP-Based Rotation-Invariant Feature Descriptors Derived from WorldView-3 ImageryColbert M. Jackson0Elhadi Adam1Iqra Atif2Muhammad A. Mahboob3School of Geography, Archaeology and Environmental Studies, University of the Witwatersrand, Johannesburg 2050, South AfricaSchool of Geography, Archaeology and Environmental Studies, University of the Witwatersrand, Johannesburg 2050, South AfricaSchool of Geography, Archaeology and Environmental Studies, University of the Witwatersrand, Johannesburg 2050, South AfricaSibanye-Stillwater Digital Mining Laboratory, Wits Mining Institute, University of the Witwatersrand, Johannesburg 2050, South AfricaAccurate mapping of selective logging (SL) serves as the foundation for additional research on forest restoration and regeneration, species diversification and distribution, and ecosystem dynamics, among other applications. This study aimed to model canopy gaps created by illegal logging of <i>Ocotea usambarensis</i> in Mt. Kenya Forest Reserve (MKFR). A texture-spectral analysis approach was applied to exploit the potential of WorldView-3 (WV-3) multispectral imagery. First, texture properties were explored in the sub-band images using fused grey-level co-occurrence matrix (GLCM)- and local binary pattern (LBP)-based texture feature extraction. Second, the texture features were fused with colour using the multivariate local binary pattern (MLBP) model. The G-statistic and Euclidean distance similarity measures were applied to increase accuracy. The random forest (RF) and support vector machine (SVM) were used to identify and classify distinctive features in the texture and spectral domains of the WV-3 dataset. The variable importance measurement in RF ranked the relative influence of sets of variables in the classification models. Overall accuracy (OA) scores for the respective MLBP models were in the range of 80–95.1%. The respective user’s accuracy (UA) and producer’s accuracy (PA) for the univariate LBP and MLBP models were in the range of 67–75% and 77–100%, respectively.https://www.mdpi.com/2673-7418/3/1/14tropical forestsWorldView-3selective loggingcanopy gaps<i>Ocotea usambarensis</i>texture-spectral analysis |
| spellingShingle | Colbert M. Jackson Elhadi Adam Iqra Atif Muhammad A. Mahboob Feature Extraction and Classification of Canopy Gaps Using GLCM- and MLBP-Based Rotation-Invariant Feature Descriptors Derived from WorldView-3 Imagery Geomatics tropical forests WorldView-3 selective logging canopy gaps <i>Ocotea usambarensis</i> texture-spectral analysis |
| title | Feature Extraction and Classification of Canopy Gaps Using GLCM- and MLBP-Based Rotation-Invariant Feature Descriptors Derived from WorldView-3 Imagery |
| title_full | Feature Extraction and Classification of Canopy Gaps Using GLCM- and MLBP-Based Rotation-Invariant Feature Descriptors Derived from WorldView-3 Imagery |
| title_fullStr | Feature Extraction and Classification of Canopy Gaps Using GLCM- and MLBP-Based Rotation-Invariant Feature Descriptors Derived from WorldView-3 Imagery |
| title_full_unstemmed | Feature Extraction and Classification of Canopy Gaps Using GLCM- and MLBP-Based Rotation-Invariant Feature Descriptors Derived from WorldView-3 Imagery |
| title_short | Feature Extraction and Classification of Canopy Gaps Using GLCM- and MLBP-Based Rotation-Invariant Feature Descriptors Derived from WorldView-3 Imagery |
| title_sort | feature extraction and classification of canopy gaps using glcm and mlbp based rotation invariant feature descriptors derived from worldview 3 imagery |
| topic | tropical forests WorldView-3 selective logging canopy gaps <i>Ocotea usambarensis</i> texture-spectral analysis |
| url | https://www.mdpi.com/2673-7418/3/1/14 |
| work_keys_str_mv | AT colbertmjackson featureextractionandclassificationofcanopygapsusingglcmandmlbpbasedrotationinvariantfeaturedescriptorsderivedfromworldview3imagery AT elhadiadam featureextractionandclassificationofcanopygapsusingglcmandmlbpbasedrotationinvariantfeaturedescriptorsderivedfromworldview3imagery AT iqraatif featureextractionandclassificationofcanopygapsusingglcmandmlbpbasedrotationinvariantfeaturedescriptorsderivedfromworldview3imagery AT muhammadamahboob featureextractionandclassificationofcanopygapsusingglcmandmlbpbasedrotationinvariantfeaturedescriptorsderivedfromworldview3imagery |