Crop signalling: A novel crop recognition technique for robotic weed control

Rekha Raja, David C. Slaughter, Steven A. Fennimore, Thuy T. Nguyen, Vivian L. Vuong, Neelima Sinha, Laura Tourte, Richard F. Smith, Mark C. Siemens

Research output: Contribution to journalArticle

Abstract

Weed control is a significant cost for speciality crop producers, especially on organic farms. Agricultural operations are still largely dependent on hand weeding that is labour intensive and labour shortages and rising wages have led to a surge in food production costs. Thus, there is an inherent need to automate weed control and contain both labour costs and demands. Automatically distinguishing weeds from the crop plant is a complex problem since weeds come in a wide variety of colours, shapes, and sizes, and crop plant foliage is often overlapped with itself or occluded by the weeds. Current technology in commercial use, cannot reliably and effectively perform the differentiation task in such complex scenarios in real-time. As a solution to this problem, our team at the University of California, Davis has developed a novel concept called crop signalling, a technology to make crop plants machine readable and reliably distinguishable from weeds for automatic weed control. Four different techniques have been investigated and developed to make smart crop marking systems such as a) systemic markers, b) fluorescent proteins, c) plant labels and d) topical markers. Indoor experiments have been conducted for each method. Field experiments, using plant labels and the topical markers methods, have been successfully conducted for real-time weed control in tomato and lettuce. The results demonstrated that robots could automatically detect and distinguish 99.7% of the crop plants with no false positive errors in dense complex outdoor scenes with high weed densities. The crop/weed differentiation was thus effective, fast, reliable, and commercialisation of robotic weed control using the technique may be feasible.

Original languageEnglish (US)
Pages (from-to)278-291
Number of pages14
JournalBiosystems Engineering
Volume187
DOIs
StatePublished - Nov 2019

Fingerprint

Weed control
Weed Control
weed control
Robotics
robotics
Crops
weed
crop plant
crop
weeds
crops
Costs and Cost Analysis
labor
Plant Weeds
Organic Agriculture
Technology
Personnel
Lettuce
methodology
Plant Proteins

Keywords

  • Automatic weed control
  • Crop signalling
  • Image processing
  • Robotics

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Food Science
  • Animal Science and Zoology
  • Agronomy and Crop Science
  • Soil Science

Cite this

Crop signalling : A novel crop recognition technique for robotic weed control. / Raja, Rekha; Slaughter, David C.; Fennimore, Steven A.; Nguyen, Thuy T.; Vuong, Vivian L.; Sinha, Neelima; Tourte, Laura; Smith, Richard F.; Siemens, Mark C.

In: Biosystems Engineering, Vol. 187, 11.2019, p. 278-291.

Research output: Contribution to journalArticle

Raja, R, Slaughter, DC, Fennimore, SA, Nguyen, TT, Vuong, VL, Sinha, N, Tourte, L, Smith, RF & Siemens, MC 2019, 'Crop signalling: A novel crop recognition technique for robotic weed control', Biosystems Engineering, vol. 187, pp. 278-291. https://doi.org/10.1016/j.biosystemseng.2019.09.011
Raja, Rekha ; Slaughter, David C. ; Fennimore, Steven A. ; Nguyen, Thuy T. ; Vuong, Vivian L. ; Sinha, Neelima ; Tourte, Laura ; Smith, Richard F. ; Siemens, Mark C. / Crop signalling : A novel crop recognition technique for robotic weed control. In: Biosystems Engineering. 2019 ; Vol. 187. pp. 278-291.
@article{bca50220326a45578be391c6f0518230,
title = "Crop signalling: A novel crop recognition technique for robotic weed control",
abstract = "Weed control is a significant cost for speciality crop producers, especially on organic farms. Agricultural operations are still largely dependent on hand weeding that is labour intensive and labour shortages and rising wages have led to a surge in food production costs. Thus, there is an inherent need to automate weed control and contain both labour costs and demands. Automatically distinguishing weeds from the crop plant is a complex problem since weeds come in a wide variety of colours, shapes, and sizes, and crop plant foliage is often overlapped with itself or occluded by the weeds. Current technology in commercial use, cannot reliably and effectively perform the differentiation task in such complex scenarios in real-time. As a solution to this problem, our team at the University of California, Davis has developed a novel concept called crop signalling, a technology to make crop plants machine readable and reliably distinguishable from weeds for automatic weed control. Four different techniques have been investigated and developed to make smart crop marking systems such as a) systemic markers, b) fluorescent proteins, c) plant labels and d) topical markers. Indoor experiments have been conducted for each method. Field experiments, using plant labels and the topical markers methods, have been successfully conducted for real-time weed control in tomato and lettuce. The results demonstrated that robots could automatically detect and distinguish 99.7{\%} of the crop plants with no false positive errors in dense complex outdoor scenes with high weed densities. The crop/weed differentiation was thus effective, fast, reliable, and commercialisation of robotic weed control using the technique may be feasible.",
keywords = "Automatic weed control, Crop signalling, Image processing, Robotics",
author = "Rekha Raja and Slaughter, {David C.} and Fennimore, {Steven A.} and Nguyen, {Thuy T.} and Vuong, {Vivian L.} and Neelima Sinha and Laura Tourte and Smith, {Richard F.} and Siemens, {Mark C.}",
year = "2019",
month = "11",
doi = "10.1016/j.biosystemseng.2019.09.011",
language = "English (US)",
volume = "187",
pages = "278--291",
journal = "Biosystems Engineering",
issn = "1537-5110",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Crop signalling

T2 - A novel crop recognition technique for robotic weed control

AU - Raja, Rekha

AU - Slaughter, David C.

AU - Fennimore, Steven A.

AU - Nguyen, Thuy T.

AU - Vuong, Vivian L.

AU - Sinha, Neelima

AU - Tourte, Laura

AU - Smith, Richard F.

AU - Siemens, Mark C.

PY - 2019/11

Y1 - 2019/11

N2 - Weed control is a significant cost for speciality crop producers, especially on organic farms. Agricultural operations are still largely dependent on hand weeding that is labour intensive and labour shortages and rising wages have led to a surge in food production costs. Thus, there is an inherent need to automate weed control and contain both labour costs and demands. Automatically distinguishing weeds from the crop plant is a complex problem since weeds come in a wide variety of colours, shapes, and sizes, and crop plant foliage is often overlapped with itself or occluded by the weeds. Current technology in commercial use, cannot reliably and effectively perform the differentiation task in such complex scenarios in real-time. As a solution to this problem, our team at the University of California, Davis has developed a novel concept called crop signalling, a technology to make crop plants machine readable and reliably distinguishable from weeds for automatic weed control. Four different techniques have been investigated and developed to make smart crop marking systems such as a) systemic markers, b) fluorescent proteins, c) plant labels and d) topical markers. Indoor experiments have been conducted for each method. Field experiments, using plant labels and the topical markers methods, have been successfully conducted for real-time weed control in tomato and lettuce. The results demonstrated that robots could automatically detect and distinguish 99.7% of the crop plants with no false positive errors in dense complex outdoor scenes with high weed densities. The crop/weed differentiation was thus effective, fast, reliable, and commercialisation of robotic weed control using the technique may be feasible.

AB - Weed control is a significant cost for speciality crop producers, especially on organic farms. Agricultural operations are still largely dependent on hand weeding that is labour intensive and labour shortages and rising wages have led to a surge in food production costs. Thus, there is an inherent need to automate weed control and contain both labour costs and demands. Automatically distinguishing weeds from the crop plant is a complex problem since weeds come in a wide variety of colours, shapes, and sizes, and crop plant foliage is often overlapped with itself or occluded by the weeds. Current technology in commercial use, cannot reliably and effectively perform the differentiation task in such complex scenarios in real-time. As a solution to this problem, our team at the University of California, Davis has developed a novel concept called crop signalling, a technology to make crop plants machine readable and reliably distinguishable from weeds for automatic weed control. Four different techniques have been investigated and developed to make smart crop marking systems such as a) systemic markers, b) fluorescent proteins, c) plant labels and d) topical markers. Indoor experiments have been conducted for each method. Field experiments, using plant labels and the topical markers methods, have been successfully conducted for real-time weed control in tomato and lettuce. The results demonstrated that robots could automatically detect and distinguish 99.7% of the crop plants with no false positive errors in dense complex outdoor scenes with high weed densities. The crop/weed differentiation was thus effective, fast, reliable, and commercialisation of robotic weed control using the technique may be feasible.

KW - Automatic weed control

KW - Crop signalling

KW - Image processing

KW - Robotics

UR - http://www.scopus.com/inward/record.url?scp=85073000131&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073000131&partnerID=8YFLogxK

U2 - 10.1016/j.biosystemseng.2019.09.011

DO - 10.1016/j.biosystemseng.2019.09.011

M3 - Article

AN - SCOPUS:85073000131

VL - 187

SP - 278

EP - 291

JO - Biosystems Engineering

JF - Biosystems Engineering

SN - 1537-5110

ER -