Automatic Detection of Tulip Breaking Virus (TBV) Using a Deep Convolutional Neural Network

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Tulip crop production in the Netherlands suffers from severe economic losses caused by virus diseases such as the Tulip Breaking Virus (TBV). Infected plants which can spread the disease by aphids must be removed from the field as soon as possible. As the availability of human experts for visual inspection in the field is limited, there is an urgent need for a rapid, automated and objective method of screening. From 2009-2012, we developed an automatic machine-vision-based system, using classical machine-learning algorithms. In 2012, the experiment conducted a tulip field planted at production density of 100 and 125 plants per square meter, resulting in images with overlapping plants. Experiments based on multispectral images resulted in scores that approached results obtained by experienced crop experts. The method, however, needed to be tuned specifically for each of the data trails, and a NIR band was needed for background segmentation. Recent developments in artificial intelligence and specifically in the area of convolutional neural networks, allow the development of more generic solutions for the detection of TBV. In this study, a Faster R-CNN network is applied on part of the data from the 2012 experiment. The outcomes show that the results are almost the same compared to the previous method using only RGB data.
Original languageEnglish
Pages (from-to)12-17
JournalIFAC-PapersOnLine
Volume52
Issue number30
DOIs
Publication statusPublished - Dec 2019

Fingerprint

Viruses
Neural networks
Crops
Experiments
Learning algorithms
Computer vision
Artificial intelligence
Learning systems
Screening
Inspection
Availability
Economics

Cite this

@article{51968b32bf3c4e36b2ec6a151c42ace9,
title = "Automatic Detection of Tulip Breaking Virus (TBV) Using a Deep Convolutional Neural Network",
abstract = "Tulip crop production in the Netherlands suffers from severe economic losses caused by virus diseases such as the Tulip Breaking Virus (TBV). Infected plants which can spread the disease by aphids must be removed from the field as soon as possible. As the availability of human experts for visual inspection in the field is limited, there is an urgent need for a rapid, automated and objective method of screening. From 2009-2012, we developed an automatic machine-vision-based system, using classical machine-learning algorithms. In 2012, the experiment conducted a tulip field planted at production density of 100 and 125 plants per square meter, resulting in images with overlapping plants. Experiments based on multispectral images resulted in scores that approached results obtained by experienced crop experts. The method, however, needed to be tuned specifically for each of the data trails, and a NIR band was needed for background segmentation. Recent developments in artificial intelligence and specifically in the area of convolutional neural networks, allow the development of more generic solutions for the detection of TBV. In this study, a Faster R-CNN network is applied on part of the data from the 2012 experiment. The outcomes show that the results are almost the same compared to the previous method using only RGB data.",
author = "Gerrit Polder and Westeringh, {Nick Van De} and Janne Kool and Khan, {Haris Ahmad} and Gert Kootstra and Ard Nieuwenhuizen",
year = "2019",
month = "12",
doi = "10.1016/j.ifacol.2019.12.482",
language = "English",
volume = "52",
pages = "12--17",
journal = "IFAC-PapersOnLine",
issn = "2405-8963",
publisher = "Elsevier",
number = "30",

}

Automatic Detection of Tulip Breaking Virus (TBV) Using a Deep Convolutional Neural Network. / Polder, Gerrit; Westeringh, Nick Van De; Kool, Janne; Khan, Haris Ahmad; Kootstra, Gert; Nieuwenhuizen, Ard.

In: IFAC-PapersOnLine, Vol. 52, No. 30, 12.2019, p. 12-17.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Automatic Detection of Tulip Breaking Virus (TBV) Using a Deep Convolutional Neural Network

AU - Polder, Gerrit

AU - Westeringh, Nick Van De

AU - Kool, Janne

AU - Khan, Haris Ahmad

AU - Kootstra, Gert

AU - Nieuwenhuizen, Ard

PY - 2019/12

Y1 - 2019/12

N2 - Tulip crop production in the Netherlands suffers from severe economic losses caused by virus diseases such as the Tulip Breaking Virus (TBV). Infected plants which can spread the disease by aphids must be removed from the field as soon as possible. As the availability of human experts for visual inspection in the field is limited, there is an urgent need for a rapid, automated and objective method of screening. From 2009-2012, we developed an automatic machine-vision-based system, using classical machine-learning algorithms. In 2012, the experiment conducted a tulip field planted at production density of 100 and 125 plants per square meter, resulting in images with overlapping plants. Experiments based on multispectral images resulted in scores that approached results obtained by experienced crop experts. The method, however, needed to be tuned specifically for each of the data trails, and a NIR band was needed for background segmentation. Recent developments in artificial intelligence and specifically in the area of convolutional neural networks, allow the development of more generic solutions for the detection of TBV. In this study, a Faster R-CNN network is applied on part of the data from the 2012 experiment. The outcomes show that the results are almost the same compared to the previous method using only RGB data.

AB - Tulip crop production in the Netherlands suffers from severe economic losses caused by virus diseases such as the Tulip Breaking Virus (TBV). Infected plants which can spread the disease by aphids must be removed from the field as soon as possible. As the availability of human experts for visual inspection in the field is limited, there is an urgent need for a rapid, automated and objective method of screening. From 2009-2012, we developed an automatic machine-vision-based system, using classical machine-learning algorithms. In 2012, the experiment conducted a tulip field planted at production density of 100 and 125 plants per square meter, resulting in images with overlapping plants. Experiments based on multispectral images resulted in scores that approached results obtained by experienced crop experts. The method, however, needed to be tuned specifically for each of the data trails, and a NIR band was needed for background segmentation. Recent developments in artificial intelligence and specifically in the area of convolutional neural networks, allow the development of more generic solutions for the detection of TBV. In this study, a Faster R-CNN network is applied on part of the data from the 2012 experiment. The outcomes show that the results are almost the same compared to the previous method using only RGB data.

U2 - 10.1016/j.ifacol.2019.12.482

DO - 10.1016/j.ifacol.2019.12.482

M3 - Article

VL - 52

SP - 12

EP - 17

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8963

IS - 30

ER -