Detection and Discrimination of Tea Plant Stresses Based on Hyperspectral Imaging Technique at a Canopy Level
Authors:
- Lihan CuiLCLihan Cui
- Lijie YanLYLijie Yan
- Xiaohu ZhaoXZXiaohu Zhao
- Lin YuanLYLin Yuan
- Jing JinJJJing Jin
- Jingcheng ZhangJingcheng Zhang
Open Access
- 1 January 2021
- journal article
- research article
- Published by Tech Science Press in Phyton
- Vol. 90 (2) , 621-634
Abstract
Tea plant stresses threaten the quality of tea seriously. The technology corresponding to the fast detection and differentiation of stresses is of great significance for plant protection in tea plantation. In recent years, hyperspectral imaging technology has shown great potential in detecting and differentiating plant diseases, pests and some other stresses at the leaf level. However, the lack of studies at canopy level hampers the detection of tea plant stresses at a larger scale. In this study, based on the canopy-level hyperspectral imaging data, the methods for identifying and differentiating the three commonly occurred tea stresses (i.e., the tea leafhopper, anthrax and sun burn) were studied. To account for the complexity of the canopy scenario, a stepwise detecting strategy was proposed that includes the process of background removal, identification of damaged areas and discrimination of stresses. Firstly, combining the successive projection algorithm (SPA) spectral analysis and K-means cluster analysis, the background and overexposed non-plant regions were removed from the image. Then, a rigorous sensitivity analysis and optimization were performed on various forms of spectral features, which yielded optimal features for detecting damaged areas (i.e., YSV, Area, GI, CARI and NBNDVI) and optimal features for stresses discrimination (i.e., MCARI, CI, LCI, RARS, TCI and VOG). Based on this information, the models for identifying damaged areas and those models for discriminating different stresses were established using K-nearest neighbor (KNN), Random Forest (RF) and Fisher discriminant analysis. The identification model achieved an accuracy over 95%, and the discrimination model achieved an accuracy over 93% for all stresses. The results suggested the feasibility of stress detection and differentiation using canopy-level hyperspectral imaging techniques, and indicated the potential for its extension over large areas.Keywords
This publication has 23 references indexed in Scilit:
- Diagnosis of bacterial spot of tomato using spectral signaturesComputers and Electronics in Agriculture, 2010
- Detection of biotic stress (Venturia inaequalis) in apple trees using hyperspectral data: Non-parametric statistical approaches and physiological implicationsEuropean Journal of Agronomy, 2007
- Assessing vineyard condition with hyperspectral indices: Leaf and canopy reflectance simulation in a row-structured discontinuous canopyRemote Sensing of Environment, 2005
- Remote estimation of canopy chlorophyll content in cropsGeophysical Research Letters, 2005
- Novel algorithms for remote estimation of vegetation fractionRemote Sensing of Environment, 2002
- Estimating Corn Leaf Chlorophyll Concentration from Leaf and Canopy ReflectanceRemote Sensing of Environment, 2000
- Non‐destructive optical detection of pigment changes during leaf senescence and fruit ripeningPhysiologia Plantarum, 1999
- Optimization of soil-adjusted vegetation indicesRemote Sensing of Environment, 1996
- A narrow-waveband spectral index that tracks diurnal changes in photosynthetic efficiencyRemote Sensing of Environment, 1992
- Potentials and limits of vegetation indices for LAI and APAR assessmentRemote Sensing of Environment, 1991