Article (Scientific journals)
Discrimination of deciduous tree species from time series of unmanned aerial system imagery
Lisein, Jonathan; Michez, Adrien; Claessens, Hugues et al.
2015In PLoS ONE, 10 (11)
Peer Reviewed verified by ORBi
 

Files


Full Text
Lisein_2015_UAStimeseries_TreeSpeciesDiscrimination.pdf
Publisher postprint (11.06 MB)
Download
Annexes
S1Appendix.zip
Publisher postprint (122.6 MB)
S1 Appendix: Replication data for the discrimination of tree species based on UAS imagery. The supplementary material includes the 10 Red-Green-Blue orthophotomosaics of the time series, the delineated tree crowns, a tutorial and the [R] source code required to replicate the classification approach.
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
UAS; drone; phenology; forestry; remote sensing; time series
Abstract :
[en] Technology advances can revolutionize Precision Forestry by providing accurate and fine forest information at tree level. This paper addresses the question of how and particularly when Unmanned Aerial System (UAS) should be used in order to efficiently discriminate deciduous tree species. A time series of high resolution UAS imagery was collected to cover the growing season from leaf flush to leaf fall. Full benefit was taken of the temporal resolution of UAS acquisition, one of the most promising features of small drones. The disparity in forest tree phenology is at the maximum during early spring and late autumn. But the phenology state that optimized the classification result is the one that minimizes the spectral variation within tree species groups and, at the same time, maximizes the phenologic differences between species. Sunlit tree crowns (5 deciduous species groups) were classified using a Random Forest approach for monotemporal, two-date and three-date combinations. The end of leaf flushing was the most efficient single-date time window. Multitemporal datasets definitely improve the overall classification accuracy. But single-date high resolution orthophotomosaics, acquired on optimal time-windows, result in a very good classification accuracy (overall out of bag error of 16%).
Disciplines :
Life sciences: Multidisciplinary, general & others
Author, co-author :
Lisein, Jonathan ;  Université de Liège > Forêts, Nature et Paysage > Gestion des ressources forestières et des milieux naturels
Michez, Adrien  ;  Université de Liège > Forêts, Nature et Paysage > Gestion des ressources forestières et des milieux naturels
Claessens, Hugues ;  Université de Liège > Forêts, Nature et Paysage > Gestion des ressources forestières et des milieux naturels
Lejeune, Philippe  ;  Université de Liège > Forêts, Nature et Paysage > Gestion des ressources forestières et des milieux naturels
Language :
English
Title :
Discrimination of deciduous tree species from time series of unmanned aerial system imagery
Publication date :
24 November 2015
Journal title :
PLoS ONE
eISSN :
1932-6203
Publisher :
Public Library of Science, San Franscisco, United States - California
Volume :
10
Issue :
11
Peer reviewed :
Peer Reviewed verified by ORBi
Available on ORBi :
since 25 April 2015

Statistics


Number of views
388 (83 by ULiège)
Number of downloads
435 (31 by ULiège)

Scopus citations®
 
93
Scopus citations®
without self-citations
88
OpenCitations
 
70
OpenAlex citations
 
105

Bibliography


Similar publications



Contact ORBi