Centre dedocumentation
scientifique

Improving the unsupervised mapping of riparian bugweed in commercial forest plantations using hyperspectral data and LiDAR / Kabir Peerbhay in Geocarto international, vol 36 n° 4 ([01/03/2021])  

Public [article]  inGeocarto international > vol 36 n° 4 [01/03/2021] . - pp 465 - 480 Titre : Improving the unsupervised mapping of riparian bugweed in commercial forest plantations using hyperspectral data and LiDAR Type de document : Article/Communication Auteurs : Kabir Peerbhay, Auteur ; Onisimo Mutanga, Auteur ; Romano Lottering, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 465 - 480 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes descripteurs IGN] carte de la végétation [Termes descripteurs IGN] classification non dirigée [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] détection d'objet [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] espèce exotique envahissante [Termes descripteurs IGN] forêt ripicole [Termes descripteurs IGN] image AISA+ [Termes descripteurs IGN] image hyperspectrale [Termes descripteurs IGN] précision cartographique [Termes descripteurs IGN] semis de points Résumé : (auteur) Accurate spatial information on the location of invasive alien plants (IAPs) in riparian environments is critical to fulfilling a comprehensive weed management regime. This study aimed to automatically map the occurrence of riparian bugweed (Solanum mauritianum) using airborne AISA Eagle hyperspectral data (393 nm–994 nm) in conjunction with LiDAR derived height. Utilising an unsupervised random forest (RF) classification approach and Anselin local Moran’s I clustering, results indicate that the integration of LiDAR with minimum noise fraction (MNF) produce the best detection rate (DR) of 88%, the lowest false positive rate (FPR) of 7.14% and an overall mapping accuracy of 83% for riparian bugweed. In comparison, utilising the original hyperspectral wavebands with and without LiDAR produced lower DRs and higher FPRs with overall accuracies of 79% and 68% respectively. This research demonstrates the potential of combining spectral information with LiDAR to accurately map IAPs using an automated unsupervised RF anomaly detection framework. Numéro de notice : A2021-163 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1614101 date de publication en ligne : 10/06/2019 En ligne : https://doi.org/10.1080/10106049.2019.1614101 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97084 [article]

Optimizing the spatial resolution of WorldView-2 imagery for discriminating forest vegetation at subspecies level in KwaZulu-Natal, South Africa / Romano Lottering in Geocarto international, vol 31 n° 7 - 8 (July - August 2016)  

Public [article]  inGeocarto international > vol 31 n° 7 - 8 (July - August 2016) . - pp 870 - 880 Titre : Optimizing the spatial resolution of WorldView-2 imagery for discriminating forest vegetation at subspecies level in KwaZulu-Natal, South Africa Type de document : Article/Communication Auteurs : Romano Lottering, Auteur ; Onisimo Mutanga, Auteur Année de publication : 2016 Article en page(s) : pp 870 - 880 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] Afrique du sud (état) [Termes descripteurs IGN] classification dirigée [Termes descripteurs IGN] espèce végétale [Termes descripteurs IGN] image Worldview [Termes descripteurs IGN] pouvoir de résolution géométrique [Termes descripteurs IGN] rééchantillonnage [Termes descripteurs IGN] sous-étage [Termes descripteurs IGN] surface forestière [Termes descripteurs IGN] variance Résumé : (Auteur) The objective of this study was to identify an appropriate spatial resolution for discriminating forest vegetation at subspecies level. WorldView-2 imagery was progressively resampled to coarser spatial resolutions. At a compartment level, 30 × 30-m subsets were generated across forest compartments to represent the five forest subspecies investigated in this study. From the centre of each subset, the spatial resolution of the original WorldView-2 image was resampled from 6 to 34-m, with increments of 4-m. The variance was then calculated at every resampled spatial resolution using each of the eight WorldView-2 bands. Based on the sampling theorem, the 3-m spatial resolution provided an appropriate resolution for all subspecies investigated. The WorldView-2 image was subsequently classified using the partial least squares linear discriminant analysis algorithm and the appropriate spatial resolution. An overall classification accuracy of 90% was established with an allocation disagreement of 9 and a quantity disagreement of 1. Numéro de notice : A2016-458 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2015.1094519 date de publication en ligne : 26/10/2015 En ligne : http://dx.doi.org/10.1080/10106049.2015.1094519 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81382 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
059-2016041	SL	Revue	Centre de documentation	Revues en salle	Disponible

Optimising the spatial resolution of WorldView-2 pan-sharpened imagery for predicting levels of Gonipterus scutellatus defoliation in KwaZulu-Natal, South Africa / Romano Lottering in ISPRS Journal of photogrammetry and remote sensing, vol 112 (February 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 112 (February 2016) . - pp 13–22 Titre : Optimising the spatial resolution of WorldView-2 pan-sharpened imagery for predicting levels of Gonipterus scutellatus defoliation in KwaZulu-Natal, South Africa Type de document : Article/Communication Auteurs : Romano Lottering, Auteur ; Onisimo Mutanga, Auteur Année de publication : 2016 Article en page(s) : pp 13–22 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] Afrique du sud (état) [Termes descripteurs IGN] Eucalyptus (genre) [Termes descripteurs IGN] image Worldview [Termes descripteurs IGN] indice de végétation [Termes descripteurs IGN] insecte phyllophage [Termes descripteurs IGN] optimisation (mathématiques) [Termes descripteurs IGN] pouvoir de résolution spectrale [Termes descripteurs IGN] prévention des risques Résumé : (auteur) Gonipterus scutellatus Gyllenhal is a leaf feeding weevil that is a major defoliator of the genus Eucalyptus. Understanding the relationship between levels of weevil induced vegetation defoliation and the optimal spatial resolution of satellite images is essential for effective management of plantation resources. The objective of this study was to identify appropriate spatial resolutions for predicting levels of weevil induced defoliation. We resampled the Normalized Difference Vegetation Index (NDVI), Simple Ratio (SR) and Enhanced Vegetation Index (EVI) images computed from a WorldView-2 pan-sharpened image, which is characterised with a 0.5 m spatial resolution and 8 spectral bands. Within each plantation compartment 30 × 30 m plots were established, representing different levels of defoliation. From the centre of each plot, the spatial resolution of the original image was progressively resampled from 1.5 to 8.5 m, with 1 m increments. The minimal variance for each level of defoliation was then established and used as an indicator for quantitatively selecting the optimal spatial resolution. Results indicate that an appropriate spatial resolution was established at 1.25, 1.25, 1.75 and 2.25 m for low, medium, high and severe levels of defoliation, respectively. In addition, an Artificial Neural Network was run to determine the relationship between the appropriate spatial resolution and levels of Gonipterus scutellatus induced defoliation. The model yielded an R2 of 0.80, with an RMSE of 1.28 (2.45% of the mean measured defoliation) based on an independent test dataset. We then compared this model to a model developed using the original 0.5 m image spatial resolution. Our results suggest that optimising the spatial resolution of remotely sensed imagery essentially improves the prediction of vegetation defoliation. In essence, this study provides the foundation for multi-scale defoliation mapping using high spatial resolution imagery. Numéro de notice : A2016-136 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern En ligne : http://www.sciencedirect.com/science/article/pii/S0924271615002622 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=80307 [article]