A benchmark of single tree detection methods using data from alpine forests | Une comparaison de méthodes de détection d'arbres sur des forêts alpines
2015
Eysn, L. | Monnet, J.M. | Hollaus, M. | Institute of Geodesy and Geophysics [Vienna] ; Vienna University of Technology = Technische Universität Wien (TU Wien) | Ecosystèmes montagnards (UR EMGR) ; Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (IRSTEA)
[Departement_IRSTEA]Territoires [TR1_IRSTEA]SEDYVIN<br/>Silvilaser 2015, La Grande Motte, FRA, 28-/09/2015 - 30/09/2015
Показать больше [+] Меньше [-]International audience
Показать больше [+] Меньше [-]Английский. 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.
Показать больше [+] Меньше [-]Ключевые слова АГРОВОК
Библиографическая информация
Эту запись предоставил Institut national de la recherche agronomique