Journal of Forest and Environmental Science

Institute of Forest Science, kangwon National University (강원대학교 산림과학연구소)
권호 표지
DOI QR코드

DOI QR Code

A Review of Hyperspectral Imaging Analysis Techniques for Onset Crop Disease Detection, Identification and Classification

  • Received : 2023.08.22
  • Accepted : 2024.02.19
  • Published : 2024.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, intensive research has been conducted to develop innovative methods for diagnosing plant diseases based on hyperspectral technologies. Hyperspectral analysis is a new subject that combines optical spectroscopy and image analysis methods, which makes it possible to simultaneously evaluate both physiological and morphological parameters. Among the physiological and morphological parameters are classifying healthy and diseased plants, assessing the severity of the disease, differentiating the types of pathogens, and identifying the symptoms of biotic stresses at early stages, including during the incubation period, when the symptoms are not visible to the human eye. Plant diseases cause significant economic losses in agriculture around the world as the symptoms of diseases usually appear when the plants are infected severely. Early detection, quantification, and identification of plant diseases are crucial for the targeted application of plant protection measures in crop production. Hence, this can be done by possible applications of hyperspectral sensors and platforms on different scales for disease diagnosis. Further, the main areas of application of hyperspectral sensors in the diagnosis of plant diseases are considered, such as detection, differentiation, and identification of diseases, estimation of disease severity, and phenotyping of disease resistance of genotypes. This review provides a deeper understanding, of basic principles and implementation of hyperspectral sensors that can measure pathogen-induced changes in plant physiology. Hence, it brings together critically assessed reports and evaluations of researchers who have adopted the use of this application. This review concluded with an overview that hyperspectral sensors, as a non-invasive system of measurement can be adopted in early detection, identification, and possible solutions to farmers as it would empower prior intervention to help moderate against decrease in yield and/or total crop loss.

Keywords

References

  1. Agrios GN. 2005. Plant pathology. 5th ed. Elsevier Academic Press, Amsterdam.
  2. Altieri MA. 2018. Agroecology: the science of sustainable agriculture. 2nd ed. CRC Press, Boca Raton, FL.
  3. Arens N, Backhaus A, Doll S, Fischer S, Seiffert U, Mock HP. 2016. Non-invasive presymptomatic detection of Cercospora beticola infection and identification of early metabolic responses in sugar beet. Front Plant Sci 7: 1377.
  4. Avinash P, Ramathilaga A, Valarmathi P. 2022. Hyperspectral remote sensing for discrimination for plant disease forecasting: Review. J Pharmacogn Phytochem 11: 208-215.
  5. Balasundaram D, Burks TF, Bulanon DM, Schubert T, Lee WS. 2009. Spectral reflectance characteristics of citrus canker and other peel conditions of grapefruit. Postharvest Biol Technol 51: 220-226. https://doi.org/10.1016/j.postharvbio.2008.07.014
  6. Bauriegel E, Giebel A, Herppich WB. 2011. Hyperspectral and chlorophyll fluorescence imaging to analyse the impact of Fusarium culmorum on the photosynthetic integrity of infected wheat ears. Sensors (Basel) 11: 3765-3779. https://doi.org/10.3390/s110403765
  7. Benhura C, Benhura MA, Muchuweti M, Gombiro PE. 2013. Assessment of the colour of Parinari curatellifolia fruit using an image processing computer software package. Int J Agric Food Res 2: 41-48.
  8. Berdugo CA, Mahlein AK, Steiner U, Dehne HW, Oerke EC. 2013. Sensors and imaging techniques for the assessment of the delay of wheat senescence induced by fungicides. Funct Plant Biol 40: 677-689. https://doi.org/10.1071/FP12351
  9. Berdugo CA, Zito R, Paulus S, Mahlein AK. 2014. Fusion of sensor data for the detection and differentiation of plant diseases in cucumber. Plant Pathol 63: 1344-1356. https://doi.org/10.1111/ppa.12219
  10. Bergstrasser S, Fanourakis D, Schmittgen S, Cendrero-Mateo MP, Jansen M, Scharr H, Rascher U. 2015. HyperART: non-invasive quantification of leaf traits using hyperspectral absorption-reflectance-transmittance imaging. Plant Methods 11: 1.
  11. Bock CH, Poole GH, Parker PE, Gottwald TR. 2010. Plant disease severity estimated visually, by digital photography and image analysis, and by hyperspectral imaging. Crit Rev Plant Sci 29: 59-107. https://doi.org/10.1080/07352681003617285
  12. Brading PA, Verstappen EC, Kema GH, Brown JK. 2002. A gene-for-gene relationship between wheat and Mycosphaerella graminicola, the Septoria tritici blotch pathogen. Phytopathology 92: 439-445. https://doi.org/10.1094/PHYTO.2002.92.4.439
  13. Bravo C, Moshou D, West J, McCartney A, Ramon H. 2003. Early disease detection in wheat fields using spectral reflectance. Biosyst Eng 84: 137-145. https://doi.org/10.1016/S1537-5110(02)00269-6
  14. Carocho M, Ferreira IC. 2013. A review on antioxidants, prooxidants and related controversy: natural and synthetic compounds, screening and analysis methodologies and future perspectives. Food Chem Toxicol 51: 15-25. https://doi.org/10.1016/j.fct.2012.09.021
  15. Carvalho FP. 2006. Agriculture, pesticides, food security and food safety. Environ Sci Policy 9: 685-692. https://doi.org/10.1016/j.envsci.2006.08.002
  16. De Silva AL, Trueman SJ, Kamper W, Wallace HM, Nichols J, Hosseini Bai S. 2023. Hyperspectral imaging of adaxial and abaxial leaf surfaces as a predictor of macadamia crop nutrition. Plants (Basel) 12: 558.
  17. Ding Y, Ma Y. 2020. Hyper spectral image characteristics of Aronia melanocarpa leaves under saline alkali stress. Glob NEST J 22: 603-612.
  18. Fitzgerald GJ, Maas SJ, Detar WR. 2004. Spider mite detection and canopy component mapping in cotton using hyperspectral imagery and spectral mixture analysis. Precis Agric 5: 275-289. https://doi.org/10.1023/B:PRAG.0000032766.88787.5f
  19. Geladi P, Burger J, Lestander T. 2004. Hyperspectral imaging: calibration problems and solutions. Chemom Intell Lab Syst 72: 209-217. https://doi.org/10.1016/j.chemolab.2004.01.023
  20. Gerhards M, Schlerf M, Mallick K, Udelhoven T. 2019. Challenges and Future Perspectives of Multi-/Hyperspectral Thermal Infrared Remote Sensing for Crop Water-Stress Detection: A Review. Remote Sens 11: 1240.
  21. Ghamisi P, Yokoya N, Li J, Liao W, Liu S, Plaza J, Rasti B, Plaza A. 2017. Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art. IEEE Geosci Remote Sens Mag 5: 37-78. https://doi.org/10.1109/MGRS.2017.2762087
  22. Grosskinsky DK, Svensgaard J, Christensen S, Roitsch T. 2015. Plant phenomics and the need for physiological phenotyping across scales to narrow the genotype-to-phenotype knowledge gap. J Exp Bot 66: 5429-5440. https://doi.org/10.1093/jxb/erv345
  23. Hbirkou C, Patzold S, Mahlein AK, Welp G. 2012. Airborne hyperspectral imaging of spatial soil organic carbon heterogeneity at the field-scale. Geoderma 175-176: 21-28. https://doi.org/10.1016/j.geoderma.2012.01.017
  24. Hillnhutter C, Mahlein AK, Sikora RA, Oerke EC. 2012. Use of imaging spectroscopy to discriminate symptoms caused by Heterodera schachtii and Rhizoctonia solani on sugar beet. Precis Agric 13: 17-32. https://doi.org/10.1007/s11119-011-9237-2
  25. Jaiswal G, Rani R, Mangotra H, Sharma A. 2023. Integration of hyperspectral imaging and autoencoders: Benefits, applications, hyperparameter tunning and challenges. Comput Sci Rev 50: 100584.
  26. Kim DM, Zhang H, Zhou H, Du T, Wu Q, Mockler TC, Berezin MY. 2015. Highly sensitive image-derived indices of water-stressed plants using hyperspectral imaging in SWIR and histogram analysis. Sci Rep 5: 15919.
  27. Kuska M, Wahabzada M, Leucker M, Dehne HW, Kersting K, Oerke EC, Steiner U, Mahlein AK. 2015. Hyperspectral phenotyping on the microscopic scale: towards automated characterization of plant-pathogen interactions. Plant Methods 11: 28.
  28. Leucker M, Wahabzada M, Kersting K, Peter M, Beyer W, Steiner U, Mahlein AK, Oerke EC. 2016. Hyperspectral imaging reveals the effect of sugar beet quantitative trait loci on Cercospora leaf spot resistance. Funct Plant Biol 44: 1-9.
  29. Lowe A, Harrison N, French AP. 2017. Hyperspectral image analysis techniques for the detection and classification of the early onset of plant disease and stress. Plant Methods 13: 80.
  30. Mahlein AK, Steiner U, Dehne HW, Oerke EC. 2010. Spectral signatures of sugar beet leaves for the detection and differentiation of diseases. Precision Agric 11: 413-431. https://doi.org/10.1007/s11119-010-9180-7
  31. Mahlein AK, Steiner U, Hillnhutter C, Dehne HW, Oerke EC. 2012. Hyperspectral imaging for small-scale analysis of symptoms caused by different sugar beet diseases. Plant Methods 8: 3.
  32. Mahlein AK. 2016. Plant Disease Detection by Imaging Sensors - Parallels and Specific Demands for Precision Agriculture and Plant Phenotyping. Plant Dis 100: 241-251. https://doi.org/10.1094/PDIS-03-15-0340-FE
  33. Martinelli F, Scalenghe R, Davino S, Panno S, Scuderi G, Ruisi P, Villa P, Stroppiana D, Boschetti M, Goulart LR, Davis CE, Dandekar AM. 2015. Advanced methods of plant disease detection. A review. Agron Sustain Dev 35: 1-25. https://doi.org/10.1007/s13593-014-0246-1
  34. Miedaner T, Zhao Y, Gowda M, Longin CF, Korzun V, Ebmeyer E, Kazman E, Reif JC. 2013. Genetic architecture of resistance to Septoria tritici blotch in European wheat. BMC Genomics. 14: 858.
  35. Misman N, Samsulrizal NH, Noh AL, Wahab MA, Ahmad K, Azmi NSA. 2022. Host Range and Control Strategies of Phytophthora palmivora in Southeast Asia Perennial Crops. Pertanika J Trop Agric Sci 45: 991-1019. https://doi.org/10.47836/pjtas.45.4.09
  36. Moghadam P, Ward D, Goan E, Jayawardena S, Sikka P, Hernandez E. 2017. Plant disease detection using hyperspectral imaging. In: 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA); Sydney, Australia; November 29-December 1, 2017.
  37. Moshou D, Bravo C, Oberti R, West J, Bodria L, McCartney A, Ramon H. 2005. Plant disease detection based on data fusion of hyper-spectral and multi-spectral fluorescence imaging using Kohonen maps. Real Time Imag 11: 75-83. https://doi.org/10.1016/j.rti.2005.03.003
  38. Mutka AM, Bart RS. 2015. Image-based phenotyping of plant disease symptoms. Front Plant Sci 5: 734.
  39. Nansen C, Macedo T, Swanson R, Weaver DK. 2009. Use of spatial structure analysis of hyperspectral data cubes for detection of insect-induced stress in wheat plants. Int J Remote Sens 30: 2447-2464. https://doi.org/10.1080/01431160802552710
  40. Polder G, van der Heijden GW, van Doorn J, Baltissen, TA. 2014. Automatic detection of tulip breaking virus (TBV) in tulip fields using machine vision. Biosyst Eng 117: 35-42. https://doi.org/10.1016/j.biosystemseng.2013.05.010
  41. Prabhakar M, Prasad Y.G, Thirupathi M, Sreedevi G, Dharajothi B, Venkateswarlu B. 2011. Use of ground based hyperspectral remote sensing for detection of stress in cotton caused by leafhopper (Hemiptera: Cicadellidae). Comput Electron Agric 79: 189-198. https://doi.org/10.1016/j.compag.2011.09.012
  42. Qin J, Burks TF, Ritenour MA, Bonn WG. 2009. Detection of citrus canker using hyperspectral reflectance imaging with spectral information divergence. J Food Eng 93: 183-191. https://doi.org/10.1016/j.jfoodeng.2009.01.014
  43. Rastogi V, Srivastava S, Jaiswal G, Sharma A. 2022. Detecting document forgery using hyperspectral imaging and machine learning. In: Computer vision and image processing. CVIP 2021. Communications in computer and information science. Vol. 1568 (Raman B, Murala S, Chowdhury A, Dhall A, Goyal P, eds). Springer, Cham, pp 14-25.
  44. Rumpf T, Mahlein AK, Steiner U, Oerke EC, Dehne HW, Plumer L. 2010. Early detection and classification of plant diseases with Support Vector Machines based on hyperspectral reflectance. Comput Electron Agric 74: 91-99. https://doi.org/10.1016/j.compag.2010.06.009
  45. Savary S, Ficke A, Aubertot JN, Hollier C. 2012. Crop losses due to diseases and their implications for global food production losses and food security. Food Sec 4: 519-537. https://doi.org/10.1007/s12571-012-0200-5
  46. Shurtleff MC, Pelczar MJ, Kelman A, Pelczar RM. 2021. Plant disease: plant pathology. https://www.britannica.com/science/plant-disease. Accessed 28 Dec 2023.
  47. Sibiya M, Sumbwanyambe M. 2019. An Algorithm for Severity Estimation of Plant Leaf Diseases by the Use of Colour Threshold Image Segmentation and Fuzzy Logic Inference: A Proposed Algorithm to Update a "Leaf Doctor" Application. AgriEngineering 1: 205-219. https://doi.org/10.3390/agriengineering1020015
  48. Simko I, Jimenez-Berni JA, Sirault XR. 2017. Phenomic Approaches and Tools for Phytopathologists. Phytopathology 107: 6-17. https://doi.org/10.1094/PHYTO-02-16-0082-RVW
  49. Thomas S, Kuska MT, Bohnenkamp D, Brugger A, Alisaac E, Wahabzada M, Behmann J, Mahlein AK. 2017. Benefits of hyperspectral imaging for plant disease detection and plant protection: a technical perspective. J Plant Dis Prot 125: 5-20.
  50. Thomas S, Wahabzada M, Kuska MT, Rascher U, Mahlein AK. 2016. Observation of plant-pathogen interaction by simultaneous hyperspectral imaging reflection and transmission measurements. Funct Plant Biol 44: 23-34.
  51. Vigneau N, Ecarnot M, Rabatel G, Roumet P. 2011. Potential of field hyperspectral imaging as a non destructive method to assess leaf nitrogen content in Wheat. Field Crops Res 122: 25-31. https://doi.org/10.1016/j.fcr.2011.02.003
  52. Wahabzada M, Mahlein AK, Bauckhage C, Steiner U, Oerke EC, Kersting K. 2015. Metro maps of plant disease dynamics - automated mining of differences using hyperspectral images. PLoS One 10: e0116902.