Review of mapping early-stage pathogen fungal colonization through spectral imaging
Pathogen fungal colonisation typically causes morphological changes in host plant tissue. Using a hyperspectral camera, a pixel-wise mapping of spectral reflectance in the visible and near-infrared range can be performed to describe an early-stage diseased tissue on the leaf or canopy level. Leaf structure anomalies are linked to leaf spectral reflectance patterns. Depending on the interaction with the host tissue, disease-specific spectral signatures are available.
The pixel-wise spectral extraction of plant signatures helps better understand leaf reflectance changes caused by plant disease dynamics. Proximal spectral imaging technology considerably improves the sensitivity and specificity of disease monitoring. In Fig. 1. it can be seen that much more information is available looking at a hot-spot or a pathogen location when using a hyperspectral imaging sensor (400-1000 nm).
Hyperspectral Imaging
Working with the spatial distribution of plant physiological information (reflectance) a new dimension of information content is opened and a novel disease management and monitoring tool is available. Some aspects might be important to consider.
Recent fungal pathogen detection user experiences
(using Cubert hyperspectral cameras (400-1000 nm))
References
Khairunniza-Bejo, S., Shahibullah, M. S., Azmi, A. N. N., & Jahari, M. (2021). Non-Destructive Detection of Asymptomatic Ganoderma boninense Infection of Oil Palm Seedlings Using NIR-Hyperspectral Data and Support Vector Machine. Applied Sciences, 11(22), 10878.
Ma, H., Huang, W., Dong, Y., Liu, L., & Guo, A. (2021). Using UAV-Based Hyperspectral Imagery to Detect Winter Wheat Fusarium Head Blight. Remote Sensing, 13(15), 3024.
Mahlein, Anne-Katrin, Ulrike Steiner, Christian Hillnhütter, Heinz-Wilhelm Dehne, and Erich-Christian Oerke. Hyperspectral imaging for small-scale analysis of symptoms caused by different sugar beet diseases. Plant methods 8, no. 1 (2012): 1-13.
Ren, Y., Huang, W., Ye, H., Zhou, X., Ma, H., Dong, Y., Shi, Y., Geng, Y., Huang, Y., Jiao, Q. and Xie, Q., 2021. Quantitative identification of yellow rust in winter wheat with a new spectral index: Development and validation using simulated and experimental data. International Journal of Applied Earth Observation and Geoinformation, 102, p.102384.
Shi, Y., Han, L., Kleerekoper, A., Chang, S., & Hu, T. (2021). A Novel CropdocNet for Automated Potato Late Blight Disease Detection from the Unmanned Aerial Vehicle-based Hyperspectral Imagery. arXiv preprint arXiv:2107.13277.
Zhang, J., Tian, Y., Yan, L., Wang, B., Wang, L., Xu, J., & Wu, K. (2021). Diagnosing the symptoms of sheath blight disease on rice stalk with an in-situ hyperspectral imaging technique. Biosystems Engineering, 209, 94-105.
About the Author
András Jung is an Associate Professor at the Faculty of Informatics at Eötvös Loránd University in Budapest and a Co-founder of Cubert GmbH. With over a decade of experience in hyperspectral imaging, András has played a crucial role in the development of Cubert’s applications. His academic background and involvement with the German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF) highlight his deep commitment to advancing geospatial and imaging technologies, both in academia and industry.