ArticlePDF Available

Abstract

Rumex obtusifolius (R. obtusifolius) is one of the most common non-cultivated. [...]
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/).
Article
Full-text available
Weed control is one of the biggest challenges in organic farms or nature reserve areas where mass spraying is prohibited. Recent advancements in remote sensing and airborne technologies provide a fast and efficient means to support environmental monitoring and management, allowing early detection of invasive species. However, in order to perform weed classification, current studies mostly relied on object-based image analysis (OBIA) and proprietary software which required substantial human inputs. This paper proposes an open-source workflow for automated weed mapping using a commercially available unmanned aerial vehicle (UAV). The UAV was flown at a low altitude between 10 m and 20 m, and collected true-colour RGB imagery over a weed-infested nature reserve. The aim of this study is to develop a repeatable and robust system for early weed detection, with minimum human intervention, for classification of Rumex obtusifolius (R. obtusifolius). Preliminary results of the proposed workflow achieved an overall accuracy of 92.1% with an F1 score of 78.7%. The approach also demonstrated the capability to map R. obtusifolius in datasets collected at various flight altitudes, camera settings and light conditions. This shows the potential to perform semi- or fully automated early weed detection system in grasslands using UAV-imagery.
Article
Full-text available
The effect of broad-leaved dock (Rumex obtusifolius L.) on the impaired nutritive value of grassland herbages was studied together with the effect of dock and addition of microbial inoculant on the fermentation process in grass silages. The herbage of broad-leaved dock exhibits low DM content, CP and fibre contents comparable with red clover, yet its NEL concentration is low. Quality of silages made of dock at DM content over 300 g/kg is good but the silages show significantly lower contents of lactic acid (35.9%), acetic acid (70.0%) and higher pH values (4.69 vs. 4.35) as compared with the grass silage. Silages made of dock do not contain butyric acid and exhibit lower rates of proteolysis. The presence of broad-leaved dock in herbage poses a danger of slow wilting and low production of fermentation acids. The addition of lactic acid bacteria (LAB) showed in the studied set of silages and in dock silages by an increased content of lactic acid (+18.9% and +27.0%, resp.) and by a significant reduction of pH value (-0.17 and -0.14, resp.).
Article
Broad-leaved dock is a common and troublesome grassland weed with a wide geographic distribution. In conventional farming the weed is normally controlled by using a selective herbicide, but in organic farming manual removal is the best option to control this weed. The objective of our work was to develop a robot that can navigate a pasture, detect broad-leaved dock, and remove any weeds found. A prototype robot was constructed that navigates by following a predefined path using centimeter-precision global positioning system (GPS). Broad-leaved dock is detected using a camera and image processing. Once detected, weeds are destroyed by a cutting device. Tests of aspects of the system showed that path following accuracy is adequate but could be improved through tuning of the controller or adoption of a dynamic vehicle model, that the success rate of weed detection is highest when the grass is short and when the broad-leaved dock plants are in rosette form, and that 75% of weeds removed did not grow back. An on-farm field test of the complete system resulted in detection of 124 weeds of 134 encountered (93%), while a weed removal action was performed eight times without a weed being present. Effective weed control is considered to be achieved when the center of the weeder is positioned within 0.1 m of the taproot of the weed—this occurred in 73% of the cases. We conclude that the robot is an effective instrument to detect and control broad-leaved dock under the conditions encountered on a commercial farm. © 2010 Wiley Periodicals, Inc.
Mapping of Rumex obtusifolius in Native Grassland using Unmanned Aerial Vehicle: From Object-Based Image Analysis to Deep Learning
  • O H Y Lam
  • B Melville
  • M Dogotari
  • M Prüm
  • H N Vithlani
  • C Roers
  • R Becker
  • F Zimmer
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/wpcontent/uploads/2019/07/EARSeL-2019-Book-of-Abstracts-Print.pdf (accessed on 12 August 2019).