Object-Based Image Analysis Applied to Low Altitude Aerial Imagery for Potato Plant Trait Retrieval and Pathogen Detection

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

There is a growing demand in both food quality and quantity, but as of now, one-third of all food produced for human consumption is lost due to pests and other pathogens accounting for roughly 40% of pre-harvest loss in potatoes. Pathogens in potato plants, like the Erwinia bacteria and the PVYNTN virus for example, exhibit symptoms of varying severity that are not easily captured by pixel-based classes (as these ignore shape, texture, and context in general). The aim of this research is to develop an object-based image analysis (OBIA) method for trait retrieval of individual potato plants that maximizes information output from Unmanned Aerial Vehicle (UAV) RGB very high resolution (VHR) imagery and its derivatives, to be used for disease detection of the Solanum tuberosum. The approach proposed can be split in two steps: (1) object-based mapping of potato plants using an optimized implementation of large scale mean-shift segmentation (LSMSS), and (2) classification of disease using a random forest (RF) model for a set of morphological traits computed from their associative objects. The approach was proven viable as the associative RF model detected presence of Erwinia and PVY pathogens with a maximum F1 score of 0.75 and an average Matthews Correlation Coefficient (MCC) score of 0.47. It also shows that low-altitude imagery acquired with a commercial UAV is a viable off-the-shelf tool for precision farming, and potato pathogen detection.
Original languageEnglish
Article number5477
Number of pages15
JournalSensors
Volume19
Issue number24
DOIs
Publication statusPublished - 12 Dec 2019

Fingerprint

aerial photography
potatoes
pathogens
Imagery (Psychotherapy)
low altitude
Pathogens
Solanum tuberosum
image analysis
Image analysis
retrieval
Antennas
Unmanned aerial vehicles (UAV)
pilotless aircraft
Erwinia
food
imagery
Viruses
viruses
Food Quality
Bacteria

Cite this

@article{cca8f0985ece48838e3f781988547027,
title = "Object-Based Image Analysis Applied to Low Altitude Aerial Imagery for Potato Plant Trait Retrieval and Pathogen Detection",
abstract = "There is a growing demand in both food quality and quantity, but as of now, one-third of all food produced for human consumption is lost due to pests and other pathogens accounting for roughly 40{\%} of pre-harvest loss in potatoes. Pathogens in potato plants, like the Erwinia bacteria and the PVYNTN virus for example, exhibit symptoms of varying severity that are not easily captured by pixel-based classes (as these ignore shape, texture, and context in general). The aim of this research is to develop an object-based image analysis (OBIA) method for trait retrieval of individual potato plants that maximizes information output from Unmanned Aerial Vehicle (UAV) RGB very high resolution (VHR) imagery and its derivatives, to be used for disease detection of the Solanum tuberosum. The approach proposed can be split in two steps: (1) object-based mapping of potato plants using an optimized implementation of large scale mean-shift segmentation (LSMSS), and (2) classification of disease using a random forest (RF) model for a set of morphological traits computed from their associative objects. The approach was proven viable as the associative RF model detected presence of Erwinia and PVY pathogens with a maximum F1 score of 0.75 and an average Matthews Correlation Coefficient (MCC) score of 0.47. It also shows that low-altitude imagery acquired with a commercial UAV is a viable off-the-shelf tool for precision farming, and potato pathogen detection.",
author = "Jasper Siebring and Jo{\~a}o Valente and {Domingues Franceschini}, {Marston Heracles} and Jan Kamp and Lammert Kooistra",
year = "2019",
month = "12",
day = "12",
doi = "10.3390/s19245477",
language = "English",
volume = "19",
journal = "Sensors",
issn = "1424-8220",
publisher = "MDPI",
number = "24",

}

TY - JOUR

T1 - Object-Based Image Analysis Applied to Low Altitude Aerial Imagery for Potato Plant Trait Retrieval and Pathogen Detection

AU - Siebring, Jasper

AU - Valente, João

AU - Domingues Franceschini, Marston Heracles

AU - Kamp, Jan

AU - Kooistra, Lammert

PY - 2019/12/12

Y1 - 2019/12/12

N2 - There is a growing demand in both food quality and quantity, but as of now, one-third of all food produced for human consumption is lost due to pests and other pathogens accounting for roughly 40% of pre-harvest loss in potatoes. Pathogens in potato plants, like the Erwinia bacteria and the PVYNTN virus for example, exhibit symptoms of varying severity that are not easily captured by pixel-based classes (as these ignore shape, texture, and context in general). The aim of this research is to develop an object-based image analysis (OBIA) method for trait retrieval of individual potato plants that maximizes information output from Unmanned Aerial Vehicle (UAV) RGB very high resolution (VHR) imagery and its derivatives, to be used for disease detection of the Solanum tuberosum. The approach proposed can be split in two steps: (1) object-based mapping of potato plants using an optimized implementation of large scale mean-shift segmentation (LSMSS), and (2) classification of disease using a random forest (RF) model for a set of morphological traits computed from their associative objects. The approach was proven viable as the associative RF model detected presence of Erwinia and PVY pathogens with a maximum F1 score of 0.75 and an average Matthews Correlation Coefficient (MCC) score of 0.47. It also shows that low-altitude imagery acquired with a commercial UAV is a viable off-the-shelf tool for precision farming, and potato pathogen detection.

AB - There is a growing demand in both food quality and quantity, but as of now, one-third of all food produced for human consumption is lost due to pests and other pathogens accounting for roughly 40% of pre-harvest loss in potatoes. Pathogens in potato plants, like the Erwinia bacteria and the PVYNTN virus for example, exhibit symptoms of varying severity that are not easily captured by pixel-based classes (as these ignore shape, texture, and context in general). The aim of this research is to develop an object-based image analysis (OBIA) method for trait retrieval of individual potato plants that maximizes information output from Unmanned Aerial Vehicle (UAV) RGB very high resolution (VHR) imagery and its derivatives, to be used for disease detection of the Solanum tuberosum. The approach proposed can be split in two steps: (1) object-based mapping of potato plants using an optimized implementation of large scale mean-shift segmentation (LSMSS), and (2) classification of disease using a random forest (RF) model for a set of morphological traits computed from their associative objects. The approach was proven viable as the associative RF model detected presence of Erwinia and PVY pathogens with a maximum F1 score of 0.75 and an average Matthews Correlation Coefficient (MCC) score of 0.47. It also shows that low-altitude imagery acquired with a commercial UAV is a viable off-the-shelf tool for precision farming, and potato pathogen detection.

U2 - 10.3390/s19245477

DO - 10.3390/s19245477

M3 - Article

VL - 19

JO - Sensors

JF - Sensors

SN - 1424-8220

IS - 24

M1 - 5477

ER -