Detecting Rumex Obtusifolius weed plants in grasslands from UAV RGB imagery using deep learning

J. Valente, M. Doldersum, C. Roers, L. Kooistra

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Broad-leaved dock (Rumex obtusifolius) is a fast growing and spreading weed and is one of the most common weeds in production grasslands in the Netherlands. The heavy occurrence, fast growth and negative environmental-agricultural impact makes Rumex a species important to control. Current control is done directly in the field by mechanical or chemical actuation methods as soon as the plants are found in situ by the farmer. In nature conservation areas control is much more difficult because spraying is not allowed. This reduces the amount of grass and its quality. Rumex could be rapidly detected using high-resolution RGB images obtained from a UAV and optimize the plant control practices in wide nature conservation areas. In this paper, a novel approach for Rumex detection from orthomosaics obtained using a commercial available quadrotor (DJI Phantom 3 PRO) is proposed. The results obtained shown that Rumex can be detected up to 90% from a 6 mm/pixel ortho-mosaic generated from an aerial survey and using deep learning.

LanguageEnglish
Title of host publicationISPRS Geospatial Week 2019, 10–14 June 2019, Enschede, The Netherlands
PublisherISPRS
Pages179-185
Number of pages7
DOIs
Publication statusPublished - 29 May 2019
Event4th ISPRS Geospatial Week 2019 - Enschede, Netherlands
Duration: 10 Jun 201914 Jun 2019

Publication series

NameISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
VolumeIV-2/W5
ISSN (Print)2194-9042

Conference

Conference4th ISPRS Geospatial Week 2019
CountryNetherlands
CityEnschede
Period10/06/1914/06/19

Fingerprint

grasslands
Unmanned aerial vehicles (UAV)
nature conservation
imagery
learning
weed
protected area
grassland
aerial survey
Conservation
chemical method
image resolution
conservation
pixel
Docks
grass
Electric current control
Spraying
Image resolution
grasses

Keywords

  • Aerial surveying
  • Deep learning
  • DJI Phantom
  • Grasslands
  • Machine vision
  • Plant detection
  • Rumex
  • Weeding

Cite this

Valente, J., Doldersum, M., Roers, C., & Kooistra, L. (2019). Detecting Rumex Obtusifolius weed plants in grasslands from UAV RGB imagery using deep learning. In ISPRS Geospatial Week 2019, 10–14 June 2019, Enschede, The Netherlands (pp. 179-185). (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences; Vol. IV-2/W5). ISPRS. https://doi.org/10.5194/isprs-annals-IV-2-W5-179-2019
Valente, J. ; Doldersum, M. ; Roers, C. ; Kooistra, L. / Detecting Rumex Obtusifolius weed plants in grasslands from UAV RGB imagery using deep learning. ISPRS Geospatial Week 2019, 10–14 June 2019, Enschede, The Netherlands. ISPRS, 2019. pp. 179-185 (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences).
@inproceedings{d7f63d6d4b2c44f3961f9967396d6df3,
title = "Detecting Rumex Obtusifolius weed plants in grasslands from UAV RGB imagery using deep learning",
abstract = "Broad-leaved dock (Rumex obtusifolius) is a fast growing and spreading weed and is one of the most common weeds in production grasslands in the Netherlands. The heavy occurrence, fast growth and negative environmental-agricultural impact makes Rumex a species important to control. Current control is done directly in the field by mechanical or chemical actuation methods as soon as the plants are found in situ by the farmer. In nature conservation areas control is much more difficult because spraying is not allowed. This reduces the amount of grass and its quality. Rumex could be rapidly detected using high-resolution RGB images obtained from a UAV and optimize the plant control practices in wide nature conservation areas. In this paper, a novel approach for Rumex detection from orthomosaics obtained using a commercial available quadrotor (DJI Phantom 3 PRO) is proposed. The results obtained shown that Rumex can be detected up to 90{\%} from a 6 mm/pixel ortho-mosaic generated from an aerial survey and using deep learning.",
keywords = "Aerial surveying, Deep learning, DJI Phantom, Grasslands, Machine vision, Plant detection, Rumex, Weeding",
author = "J. Valente and M. Doldersum and C. Roers and L. Kooistra",
year = "2019",
month = "5",
day = "29",
doi = "10.5194/isprs-annals-IV-2-W5-179-2019",
language = "English",
series = "ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences",
publisher = "ISPRS",
pages = "179--185",
booktitle = "ISPRS Geospatial Week 2019, 10–14 June 2019, Enschede, The Netherlands",

}

Valente, J, Doldersum, M, Roers, C & Kooistra, L 2019, Detecting Rumex Obtusifolius weed plants in grasslands from UAV RGB imagery using deep learning. in ISPRS Geospatial Week 2019, 10–14 June 2019, Enschede, The Netherlands. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. IV-2/W5, ISPRS, pp. 179-185, 4th ISPRS Geospatial Week 2019, Enschede, Netherlands, 10/06/19. https://doi.org/10.5194/isprs-annals-IV-2-W5-179-2019

Detecting Rumex Obtusifolius weed plants in grasslands from UAV RGB imagery using deep learning. / Valente, J.; Doldersum, M.; Roers, C.; Kooistra, L.

ISPRS Geospatial Week 2019, 10–14 June 2019, Enschede, The Netherlands. ISPRS, 2019. p. 179-185 (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences; Vol. IV-2/W5).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Detecting Rumex Obtusifolius weed plants in grasslands from UAV RGB imagery using deep learning

AU - Valente, J.

AU - Doldersum, M.

AU - Roers, C.

AU - Kooistra, L.

PY - 2019/5/29

Y1 - 2019/5/29

N2 - Broad-leaved dock (Rumex obtusifolius) is a fast growing and spreading weed and is one of the most common weeds in production grasslands in the Netherlands. The heavy occurrence, fast growth and negative environmental-agricultural impact makes Rumex a species important to control. Current control is done directly in the field by mechanical or chemical actuation methods as soon as the plants are found in situ by the farmer. In nature conservation areas control is much more difficult because spraying is not allowed. This reduces the amount of grass and its quality. Rumex could be rapidly detected using high-resolution RGB images obtained from a UAV and optimize the plant control practices in wide nature conservation areas. In this paper, a novel approach for Rumex detection from orthomosaics obtained using a commercial available quadrotor (DJI Phantom 3 PRO) is proposed. The results obtained shown that Rumex can be detected up to 90% from a 6 mm/pixel ortho-mosaic generated from an aerial survey and using deep learning.

AB - Broad-leaved dock (Rumex obtusifolius) is a fast growing and spreading weed and is one of the most common weeds in production grasslands in the Netherlands. The heavy occurrence, fast growth and negative environmental-agricultural impact makes Rumex a species important to control. Current control is done directly in the field by mechanical or chemical actuation methods as soon as the plants are found in situ by the farmer. In nature conservation areas control is much more difficult because spraying is not allowed. This reduces the amount of grass and its quality. Rumex could be rapidly detected using high-resolution RGB images obtained from a UAV and optimize the plant control practices in wide nature conservation areas. In this paper, a novel approach for Rumex detection from orthomosaics obtained using a commercial available quadrotor (DJI Phantom 3 PRO) is proposed. The results obtained shown that Rumex can be detected up to 90% from a 6 mm/pixel ortho-mosaic generated from an aerial survey and using deep learning.

KW - Aerial surveying

KW - Deep learning

KW - DJI Phantom

KW - Grasslands

KW - Machine vision

KW - Plant detection

KW - Rumex

KW - Weeding

U2 - 10.5194/isprs-annals-IV-2-W5-179-2019

DO - 10.5194/isprs-annals-IV-2-W5-179-2019

M3 - Conference contribution

T3 - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

SP - 179

EP - 185

BT - ISPRS Geospatial Week 2019, 10–14 June 2019, Enschede, The Netherlands

PB - ISPRS

ER -

Valente J, Doldersum M, Roers C, Kooistra L. Detecting Rumex Obtusifolius weed plants in grasslands from UAV RGB imagery using deep learning. In ISPRS Geospatial Week 2019, 10–14 June 2019, Enschede, The Netherlands. ISPRS. 2019. p. 179-185. (ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences). https://doi.org/10.5194/isprs-annals-IV-2-W5-179-2019