Low-cost hyper-spectral imaging system using a linear variable bandpass filter for agritech applications

Shigeng Song, Des Gibson*, Sam Ahmadzadeh, Hin On Chu, Barry Warden, Russell Overend, Fraser MacFarlane, Paul Murray, Stephen Marshall, Matt Aitkenhead, Damian Bienkowski, Russell Allison

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

Hyperspectral imaging for agricultural applications provides a solution for non-destructive, large-area crop monitoring. However, current products are bulky and expensive due to complicated optics and electronics. A linear variable filter was developed for implementation into a prototype hyperspectral imaging camera that demonstrates good spectral performance between 450 and 900 nm. Equipped with a feature extraction and classification algorithm, the proposed system can be used to determine potato plant health with ∼88% accuracy. This algorithm was also capable of species identification and is demonstrated as being capable of differentiating between rocket, lettuce, and spinach. Results are promising for an entry-level, low-cost hyperspectral imaging solution for agriculture applications.
Original languageEnglish
Pages (from-to)A167-A175
Number of pages9
JournalApplied Optics
Volume59
Issue number5
DOIs
Publication statusPublished - 27 Jan 2020

Fingerprint

Bandpass filters
bandpass filters
Imaging systems
spinach
potatoes
Agriculture
agriculture
crops
rockets
entry
pattern recognition
health
Costs
cameras
prototypes
optics
Rockets
filters
Crops
Feature extraction

Cite this

Song, Shigeng ; Gibson, Des ; Ahmadzadeh, Sam ; Chu, Hin On ; Warden, Barry ; Overend, Russell ; MacFarlane, Fraser ; Murray, Paul ; Marshall, Stephen ; Aitkenhead, Matt ; Bienkowski, Damian ; Allison, Russell. / Low-cost hyper-spectral imaging system using a linear variable bandpass filter for agritech applications. In: Applied Optics. 2020 ; Vol. 59, No. 5. pp. A167-A175.
@article{b8d38e7da4a5465fa519fa5806b008a7,
title = "Low-cost hyper-spectral imaging system using a linear variable bandpass filter for agritech applications",
abstract = "Hyperspectral imaging for agricultural applications provides a solution for non-destructive, large-area crop monitoring. However, current products are bulky and expensive due to complicated optics and electronics. A linear variable filter was developed for implementation into a prototype hyperspectral imaging camera that demonstrates good spectral performance between 450 and 900 nm. Equipped with a feature extraction and classification algorithm, the proposed system can be used to determine potato plant health with ∼88{\%} accuracy. This algorithm was also capable of species identification and is demonstrated as being capable of differentiating between rocket, lettuce, and spinach. Results are promising for an entry-level, low-cost hyperspectral imaging solution for agriculture applications.",
author = "Shigeng Song and Des Gibson and Sam Ahmadzadeh and Chu, {Hin On} and Barry Warden and Russell Overend and Fraser MacFarlane and Paul Murray and Stephen Marshall and Matt Aitkenhead and Damian Bienkowski and Russell Allison",
year = "2020",
month = "1",
day = "27",
doi = "10.1364/AO.378269",
language = "English",
volume = "59",
pages = "A167--A175",
journal = "Applied Optics",
issn = "1559-128X",
publisher = "The Optical Society",
number = "5",

}

Song, S, Gibson, D, Ahmadzadeh, S, Chu, HO, Warden, B, Overend, R, MacFarlane, F, Murray, P, Marshall, S, Aitkenhead, M, Bienkowski, D & Allison, R 2020, 'Low-cost hyper-spectral imaging system using a linear variable bandpass filter for agritech applications', Applied Optics, vol. 59, no. 5, pp. A167-A175. https://doi.org/10.1364/AO.378269

Low-cost hyper-spectral imaging system using a linear variable bandpass filter for agritech applications. / Song, Shigeng; Gibson, Des; Ahmadzadeh, Sam; Chu, Hin On; Warden, Barry; Overend, Russell; MacFarlane, Fraser; Murray, Paul; Marshall, Stephen; Aitkenhead, Matt; Bienkowski, Damian; Allison, Russell.

In: Applied Optics, Vol. 59, No. 5, 27.01.2020, p. A167-A175.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Low-cost hyper-spectral imaging system using a linear variable bandpass filter for agritech applications

AU - Song, Shigeng

AU - Gibson, Des

AU - Ahmadzadeh, Sam

AU - Chu, Hin On

AU - Warden, Barry

AU - Overend, Russell

AU - MacFarlane, Fraser

AU - Murray, Paul

AU - Marshall, Stephen

AU - Aitkenhead, Matt

AU - Bienkowski, Damian

AU - Allison, Russell

PY - 2020/1/27

Y1 - 2020/1/27

N2 - Hyperspectral imaging for agricultural applications provides a solution for non-destructive, large-area crop monitoring. However, current products are bulky and expensive due to complicated optics and electronics. A linear variable filter was developed for implementation into a prototype hyperspectral imaging camera that demonstrates good spectral performance between 450 and 900 nm. Equipped with a feature extraction and classification algorithm, the proposed system can be used to determine potato plant health with ∼88% accuracy. This algorithm was also capable of species identification and is demonstrated as being capable of differentiating between rocket, lettuce, and spinach. Results are promising for an entry-level, low-cost hyperspectral imaging solution for agriculture applications.

AB - Hyperspectral imaging for agricultural applications provides a solution for non-destructive, large-area crop monitoring. However, current products are bulky and expensive due to complicated optics and electronics. A linear variable filter was developed for implementation into a prototype hyperspectral imaging camera that demonstrates good spectral performance between 450 and 900 nm. Equipped with a feature extraction and classification algorithm, the proposed system can be used to determine potato plant health with ∼88% accuracy. This algorithm was also capable of species identification and is demonstrated as being capable of differentiating between rocket, lettuce, and spinach. Results are promising for an entry-level, low-cost hyperspectral imaging solution for agriculture applications.

U2 - 10.1364/AO.378269

DO - 10.1364/AO.378269

M3 - Article

VL - 59

SP - A167-A175

JO - Applied Optics

JF - Applied Optics

SN - 1559-128X

IS - 5

ER -