KIT | KIT-Bibliothek | Impressum | Datenschutz

Convolutional Neural Networks accurately predict cover fractions of plant species and communities in Unmanned Aerial Vehicle imagery

Kattenborn, Teja 1; Eichel, Jana; Wiser, Susan; Burrows, Larry; Fassnacht, Fabian E. ORCID iD icon 1; Schmidtlein, Sebastian ORCID iD icon 1
1 Institut für Geographie und Geoökologie (IFGG), Karlsruher Institut für Technologie (KIT)

Abstract:

Unmanned Aerial Vehicles (UAV) greatly extended our possibilities to acquire high resolution remote sensing data for assessing the spatial distribution of species composition and vegetation characteristics. Yet, current pixel‐ or texture‐based mapping approaches do not fully exploit the information content provided by the high spatial resolution. Here, to fully harness this spatial detail, we apply deep learning techniques, that is, Convolutional Neural Networks (CNNs), on regular tiles of UAV‐orthoimagery (here 2–5 m) to identify the cover of target plant species and plant communities. The approach was tested with UAV‐based orthomosaics and photogrammetric 3D information in three case studies, that is, (1) mapping tree species cover in primary forests, (2) mapping plant invasions by woody species into forests and open land and (3) mapping vegetation succession in a glacier foreland. All three case studies resulted in high predictive accuracies. The accuracy increased with increasing tile size (2–5 m) reflecting the increased spatial context captured by a tile. The inclusion of 3D information derived from the photogrammetric workflow did not significantly improve the models. ... mehr


Verlagsausgabe §
DOI: 10.5445/IR/1000105803
Veröffentlicht am 23.11.2021
Originalveröffentlichung
DOI: 10.1002/rse2.146
Scopus
Zitationen: 81
Web of Science
Zitationen: 75
Dimensions
Zitationen: 91
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Geographie und Geoökologie (IFGG)
KIT-Zentrum Klima und Umwelt (ZKU)
Publikationstyp Zeitschriftenaufsatz
Publikationsmonat/-jahr 12.2020
Sprache Englisch
Identifikator ISSN: 2056-3485, 2056-3485
KITopen-ID: 1000105803
Erschienen in Remote sensing in ecology and conservation
Verlag Wiley Open Access
Band 6
Heft 4
Seiten 472-486
Bemerkung zur Veröffentlichung Gefördert durch den KIT-Publikationsfonds
Gefördert vom Ministerium für Wissenschaft, Forschung und Kunst Baden-Württemberg (MWK) im Rahmen des Open-Access-Förderprogramms "BW BigDIWA"
Vorab online veröffentlicht am 05.02.2020
Nachgewiesen in Web of Science
Dimensions
Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page