Available via license: CC BY
Content may be subject to copyright.
Proceedings 2019, 30, 34; doi:10.3390/proceedings2019030034 www.mdpi.com/journal/proceedings
Abstract
Mapping Invasive Rumex obtusifolius in Grassland
Using Unmanned Aerial Vehicle †
Olee Hoi Ying Lam 1,*, Bethany Melville 1, Marcel Dogotari 1, Moritz Prüm 1,
Hemang Narendra Vithlani 1, Corinna Roers 2, Rolf Becker 1 and Frank Zimmer 1
1 Faculty of Communication and Environment, Rhine-Waal University of Applied Sciences,
47475 Kamp-Lintfort, Germany; BME@hsrw.eu (B.M.); DOM@hsrw.eu (M.D.); MPR@hsrw.eu (M.P.);
HNV@hsrw.eu (H.N.V.); RB@hsrw.eu (R.B.); FZ@hsrw.eu (F.Z.)
2 Naturschutzzentrum im Kreis Kleve e.V., 46459 Rees, Germany; roers@nz-kleve.de
* Correspondence: LH@hsrw.eu
† Presented at TERRAenVISION 2019, Barcelona, Spain, 2–7 September 2019.
Published: 23 December 2019
Abstract: Rumex obtusifolius (R. obtusifolius) is one of the most common non-cultivated weed in
European grasslands. Its broad-leaved and wide-spread nature make this weed competitive with
the native pasture species reducing grass yield (van Evert et al. 2010), while its oxalic acid content
makes this species poisonous for livestock if large doses are consumed (Hejduk and Doležal 2004).
Therefore, early removal is preferred especially in organic dairy farms or conservation areas where
mass spraying is prohibited. Remote sensing and airborne technologies offer fast and efficient
support in environmental monitoring allowing early detection of invasive species, yet current
studies mostly rely on object-based image analysis (OBIA) and proprietary software to perform
weed classification that require substantial human inputs. In this work, an open source workflow
for automatic weed detection using unmanned aerial vehicle (UAV) RGB-imagery of native
grassland had been developed using deep learning techniques, based on a previously developed
OBIA approach (Lam et al. 2019). During the study, DJI Phantom 3 and 4 Pro were used for data
acquisition throughout the vegetation period in 2018 and early 2019 at a nature conversation area
in North Rhine-Westphalia, Germany. Images were processed using OpenDroneMap to produce
orthomosaics. OBIA methods were then performed using Python and QGIS to assist the data
labelling process for training a convolutional neural network (CNN), which was later used as an
image classifier. Preliminary results of the proposed workflow achieved an overall accuracy of
93.8% and had demonstrated the capability in mapping R. obtusifolius in datasets collected at various
flight altitudes, camera settings and light conditions. This shows the potential of developing a
repeatable and robust system for semi- or fully-automated early weed detection in grassland using
UAV-imagery.
Keywords: weed mapping; image segmentation; neural network; UAV; RGB-imagery
Acknowledgments: This work is part of the SPECTORS project with project number 143081, which is funded by
the cooperation program INTERREG Deutschland-Nederland. The authors would like to acknowledge the
support of Wageningen University & Research in the collection of field data.
References
1. Hejduk, S.; Dolezal, P. Nutritive value of broad-leaved dock (Rumex obtusifolius L.) and its effect on the
quality of grass silages. Czech J. Anim. Sci. 2011, 49, 144–150.
Proceedings 2019, 30, 34 2 of 2
2. Lam, O.H.Y.; Melville, B.; Dogotari, M.; Prüm, M.; Vithlani, H.N.; Roers, C.; Becker, R.; Zimmer, F. Mapping
of Rumex obtusifolius in Native Grassland using Unmanned Aerial Vehicle: From Object-Based Image
Analysis to Deep Learning. In Proceedings of the 39th Annual EARSeL Symposium Book of Abstracts.
DIGITAL | EARTH | OBSERVATION. 39th Annual EARSeL Symposium， Salzburg, Austria, 1
–
4 July
2019. Available online: http://symposium.earsel.org/39th-symposium-Salzburg/wp-
content/uploads/2019/07/EARSeL-2019-Book-of-Abstracts-Print.pdf (accessed on 12 August 2019).
3. Van Evert, F.K.; Samsom, J.; Polder, G.; Vijn, M.; Van Dooren, H.-J.; Lamaker, A.; Van Der Heijden, G.W.;
Kempenaar, C.; Van Der Zalm, T.; Lotz, L.A. A robot to detect and control broad-leaved dock (Rumex
obtusifolius L.) in grassland. J. Field Robot. 2010, 28, 264–277.
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons Attribution
(CC BY) license (http://creativecommons.org/licenses/by/4.0/).
