KIT | KIT-Bibliothek | Impressum | Datenschutz

Consumer-grade UAV imagery facilitates semantic segmentation of species-rich savanna tree layers

Popp, Manuel R. 1; Kalwij, Jesse M. 1
1 Institut für Geographie und Geoökologie (IFGG), Karlsruher Institut für Technologie (KIT)


Conventional forest inventories are labour-intensive. This limits the spatial extent and temporal frequency at which woody vegetation is usually monitored. Remote sensing provides cost-effective solutions that enable extensive spatial coverage and high sampling frequency. Recent studies indicate that convolutional neural networks (CNNs) can classify woody forests, plantations, and urban vegetation at the species level using consumer-grade unmanned aerial vehicle (UAV) imagery. However, whether such an approach is feasible in species-rich savanna ecosystems remains unclear. Here, we tested whether small data sets of high-resolution RGB orthomosaics suffice to train U-Net, FC-DenseNet, and DeepLabv3 + in semantic segmentation of savanna tree species. We trained these models on an 18-ha training area and explored whether models could be transferred across space and time. These models could recognise trees in adjacent (mean F1-Score = 0.68) and distant areas (mean F1-Score = 0.61) alike. Over time, a change in plant morphology resulted in a decrease of model accuracy. Our results show that CNN-based tree mapping using consumer-grade UAV imagery is possible in savanna ecosystems. ... mehr

Verlagsausgabe §
DOI: 10.5445/IR/1000161973
Veröffentlicht am 13.09.2023
DOI: 10.1038/s41598-023-40989-7
Zitationen: 1
Zitationen: 1
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Geographie und Geoökologie (IFGG)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2023
Sprache Englisch
Identifikator ISSN: 2045-2322
KITopen-ID: 1000161973
Erschienen in Scientific Reports
Verlag Nature Research
Band 13
Seiten Art.-Nr.: 13892
Bemerkung zur Veröffentlichung Gefördert durch den KIT-Publikationsfonds
Vorab online veröffentlicht am 24.08.2023
Schlagwörter Ecological modelling, Image processing, Machine learning, Tropical ecology
Nachgewiesen in Web of Science
Globale Ziele für nachhaltige Entwicklung Ziel 11 – Nachhaltige Städte und GemeindenZiel 15 – Leben an Land
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page