A benchmark of single tree detection methods using data from alpine forests - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

A benchmark of single tree detection methods using data from alpine forests

Une comparaison de méthodes de détection d'arbres sur des forêts alpines

Résumé

This study presents a new open-access dataset of 18 plots from alpine forests of the Alpine Space. Eight detection algorithms were tested and evaluated against forest inventory data using a novel, automated matching procedure. Forest structure remains a key issue limiting tree detection, and algorithms would probably benefit from an adaptive tuning in order to achieve a better trade-off between omission and commission errors.
Fichier principal
Vignette du fichier
gr2015-pub00045340.pdf (692.44 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01255904 , version 1 (14-01-2016)

Identifiants

Citer

L. Eysn, J.M. Monnet, M. Hollaus. A benchmark of single tree detection methods using data from alpine forests. Silvilaser 2015, Sep 2015, La Grande Motte, France. 3 p. ⟨hal-01255904⟩

Collections

IRSTEA INRAE
66 Consultations
90 Téléchargements

Partager

Gmail Facebook X LinkedIn More