Centre de documentation
scientifique

Evaluating tree detection and segmentation routines on very high resolution UAV LiDAR data / Luke Wallace in IEEE Transactions on geoscience and remote sensing, vol 52 n° 12 (December 2014)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 52 n° 12 (December 2014) . - pp 7619 - 7628 Titre : Evaluating tree detection and segmentation routines on very high resolution UAV LiDAR data Type de document : Article/Communication Auteurs : Luke Wallace, Auteur ; Arko Lucieer, Auteur ; Christopher S. Watson, Auteur Année de publication : 2014 Article en page(s) : pp 7619 - 7628 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] arbre (flore) [Termes IGN] canopée [Termes IGN] contour [Termes IGN] détection de cible [Termes IGN] données lidar [Termes IGN] drone [Termes IGN] Eucalyptus globulus [Termes IGN] hauteur des arbres [Termes IGN] image à très haute résolution [Termes IGN] implémentation (informatique) [Termes IGN] prise de vue aérienne [Termes IGN] semis de points Résumé : (Auteur) Light detection and Ranging (LiDAR) is becoming an increasingly used tool to support decision-making processes within forest operations. Area-based methods that derive information on the condition of a forest based on the distribution of points within the canopy have been proven to produce reliable and consistent results. Individual tree-based methods, however, are not yet used operationally in the industry. This is due to problems in detecting and delineating individual trees under varying forest conditions resulting in an underestimation of the stem count and biases toward larger trees. The aim of this paper is to use high-resolution LiDAR data captured from a small multirotor unmanned aerial vehicle platform to determine the influence of the detection algorithm and point density on the accuracy of tree detection and delineation. The study was conducted in a four-year-old Eucalyptus globulus stand representing an important stage of growth for forest management decision-making process. Five different tree detection routines were implemented, which delineate trees directly from the point cloud, voxel space, and the canopy height model (CHM). The results suggest that both algorithm and point density are important considerations in the accuracy of the detection and delineation of individual trees. The best performing method that utilized both the CHM and the original point cloud was able to correctly detect 98% of the trees in the study area. Increases in point density (from 5 to 50 points/m2) lead to significant improvements (of up to 8%) in the rate of omission for algorithms that made use of the high density of the data. Numéro de notice : A2014-640 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2315649 En ligne : https://doi.org/10.1109/TGRS.2014.2315649 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=75077 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2014121	RAB	Revue	Centre de documentation	En réserve L003	Disponible

An assessment of the repeatability of automatic forest inventory metrics derived from UAV-borne laser scanning data / Luke Wallace in IEEE Transactions on geoscience and remote sensing, vol 52 n° 11 tome 1 (November 2014)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 52 n° 11 tome 1 (November 2014) . - pp 7160 - 7169 Titre : An assessment of the repeatability of automatic forest inventory metrics derived from UAV-borne laser scanning data Type de document : Article/Communication Auteurs : Luke Wallace, Auteur ; Robert Musk, Auteur ; Arko Lucieer, Auteur Année de publication : 2014 Article en page(s) : pp 7160 - 7169 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] détection de cible [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] hauteur des arbres [Termes IGN] inventaire forestier (techniques et méthodes) [Termes IGN] semis de points Résumé : (Auteur) We assessed the reproducibility of forest inventory metrics derived from an unmanned aerial vehicle (UAV) laser scanning (UAVLS) system. A total of 82 merged point clouds were captured over six 500-m2 plots within a Eucalyptus globulus plantation forest in Tasmania, Australia. Terrain and understory height, together with plot- and tree-level metrics, were extracted from the UAVLS point clouds using automated methods and compared across the multiple point clouds. The results show that measurements of terrain and understory height and plot-level metrics can be reproduced with adequate repeatability for change detection purposes. At the tree level, the high-density data collected by the UAV provided estimates of tree location (mean deviation (MD) of less than 0.48 m) and tree height (MD of 0.35 m) with high precision. This precision is comparable to that of ground-based field measurement techniques. The estimates of crown area and crown volume were found to be dependent on the segmentation routine and, as such, were measured with lower repeatability. The precision of the metrics found within this paper demonstrates the applicability of UAVs as a platform for performing sample-based forest inventories. Numéro de notice : A2014-539 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2308208 En ligne : https://doi.org/10.1109/TGRS.2014.2308208 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=74156 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2014111A	RAB	Revue	Centre de documentation	En réserve L003	Disponible