Articles
Detection of the spectral signature of Phytophthora root rot (PRR) symptoms using hyperspectral imaging
Article number
1360_10
Pages
77 – 84
Language
English
Abstract
Phytophthora root rot (PRR) caused by Phytophthora cinnamomi, is a serious disease and an important constraint to avocado production.
The current method of PRR detection in avocado trees is based on a visual assessment of canopy health performed by trained expert personnel with substantial experience.
This method is time-consuming if large areas need to be monitored and can be inaccurate in practice due to gradual visual change and spatial variation in the orchards.
Additionally, it is important that the infection ratings are consistent and comparable across orchards and growing seasons thereby increasing the complexity of the method.
This study aimed to identify the spectral bands that are specific to PRR declining trees when hyperspectral imaging technology is used.
Hyperspectral imaging combines digital imaging with spectroscopy, recording contiguous spectral information for each pixel in the image.
In the field experiment, avocado trees with varying levels of PRR severity were identified (low, medium, and high levels of infection) whereby the leaves were collected and analysed using hyperspectral imaging in the visible near-infrared VNIR (400-1000 nm) and short-wave infrared SWIR (950-2500 nm) spectral range.
The identification of relevant bands using hyperspectral image analysis is an important first step for implementing the PRR scouting at block scale an even larger scale, entire orchard.
This information can be complemented with remote sensing platforms (satellites or unmanned aerial vehicles) and associated computer vision techniques to present a beneficial alternative to the human vision for the management of PRR infections.
Additionally, this will allow for cost-effective and time-saving processes for monitoring large areas of cultivated land enabling the grower to make better PRR infection management decisions.
The current method of PRR detection in avocado trees is based on a visual assessment of canopy health performed by trained expert personnel with substantial experience.
This method is time-consuming if large areas need to be monitored and can be inaccurate in practice due to gradual visual change and spatial variation in the orchards.
Additionally, it is important that the infection ratings are consistent and comparable across orchards and growing seasons thereby increasing the complexity of the method.
This study aimed to identify the spectral bands that are specific to PRR declining trees when hyperspectral imaging technology is used.
Hyperspectral imaging combines digital imaging with spectroscopy, recording contiguous spectral information for each pixel in the image.
In the field experiment, avocado trees with varying levels of PRR severity were identified (low, medium, and high levels of infection) whereby the leaves were collected and analysed using hyperspectral imaging in the visible near-infrared VNIR (400-1000 nm) and short-wave infrared SWIR (950-2500 nm) spectral range.
The identification of relevant bands using hyperspectral image analysis is an important first step for implementing the PRR scouting at block scale an even larger scale, entire orchard.
This information can be complemented with remote sensing platforms (satellites or unmanned aerial vehicles) and associated computer vision techniques to present a beneficial alternative to the human vision for the management of PRR infections.
Additionally, this will allow for cost-effective and time-saving processes for monitoring large areas of cultivated land enabling the grower to make better PRR infection management decisions.
Authors
C. Poblete-Echeverría, S.J. Duncan, A. McLeod
Keywords
remote sensing, avocado, severity detection, hyperspectral imaging
Groups involved
- Division Precision Horticulture and Engineering
- Division Plant-Environment Interactions in Field Systems
- Division Vine and Berry Fruits
- Division Tropical and Subtropical Fruit and Nuts
- Division Plant Genetic Resources, Breeding and Biotechnology
- Division Temperate Tree Nuts
- Division Temperate Tree Fruits
- Division Vegetables, Roots and Tubers
- Division Sustaining Horticulture in a Changing World
- Working Group Mechanization, Digitization, Sensing and Robotics
Online Articles (45)