Monitoring Model of Winter Wheat Take-all Based on UAV Hyperspectral Imaging

被引：0
|
作者：
Guo W. [1 ]
Zhu Y. [1 ]
Wang H. [2 ]
Zhang J. [1 ]
Dong P. [1 ]
Qiao H. [1 ]
机构：
[1] College of Information and Management Science, Henan Agricultural University, Zhengzhou
[2] Beijing Municipal Climate Center, Beijing Meteorological Bureau, Beijing
来源：
Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2019年 / 50卷 / 09期
关键词：
Hyperspectral; Remote sensing; Spectral indices; Take-all; Unmanned aerial vehicle; Winter wheat;
D O I：
10.6041/j.issn.1000-1298.2019.09.018
中图分类号：
学科分类号：
摘要：
Winter wheat take-all is a quarantine disease that causes wheat to be significantly reduced or even rejected. Rapid and non-destructive monitoring of the spatial distribution of winter wheat take-all is of great significance for its prevention and control. The UAV-equipped imaging hyperspectral sensor was used as the remote sensing platform. The imaging hyperspectral image combined with the ground disease survey data was used to try to map the distribution of wheat take-all in the field scale. The quality of UHD185 spectral data was evaluated by synchronously acquired terrestrial ASD hyperspectral data. The statistical analysis and remote sensing inversion mapping techniques were used to calculate the differential spectral index (DSI) and ratio spectral index (RSI). Normalized difference spectral index (NDSI) and disease index (DI) were constructed to determine the coefficient equipotential map, and the optimal spectral index and DI were constructed to construct a linear regression model, and the partial least squares constructed with three indices were constructed. The accuracy and robustness of the prediction model constructed by regression method were compared. Finally, the model was tested with independent data. The results showed that the ASD spectral data of winter wheat canopy was significantly correlated with UHD185 spectral data, R2 was above 0.97, and the three spectral indices were compared with DI to construct a partial least squares regression model and the model verification results were obtained (R2=0.629 2, RMSE is 10.2%, MAE is 16.6%). The results showed that DSI(R818, R534) had the highest contribution to the model with the formula for linear regression model of DSI (R818, R534) and DI as y=-6.490 1x+1.461 3 (R2=0.860 5, RMSE is 7.3%, MAE is 19.1%), which was verified by independent samples for model accuracy (R2=0.76, RMSE is 14.9%, MAE is 11.7%, n=20). Finally, the model was used to invert the DI of the plot, and the spatial distribution map of winter wheat take-all was made. The research provided a technical basis for UAV hyperspectral remote sensing in the accurate monitoring and application of winter wheat take-all. It provided a theoretical basis for the future satellite remote sensing to explore large-scale monitoring of winter wheat take-all. © 2019, Chinese Society of Agricultural Machinery. All right reserved.
引用
收藏
页码：162 / 169
页数：7
相关论文
共 19 条
  • [1] Xu L., Nie Z., Zhan K., Occurrence and integrated control of wheat take-all in Henan Province, Anhui Agricultural Science Bulletin, 15, 12, pp. 115-117, (2009)
  • [2] Qiao H., Shi Y., Si H., Et al., Monitoring and classification of wheat take-all in field based on imaging spectrometer, Transactions of the CSAE, 30, 20, pp. 172-178, (2014)
  • [3] Zhang J., Yuan L., Wang J., Et al., Research progress of crop diseases and pests monitoring based on remote sensing, Transactions of the CSAE, 28, 20, pp. 1-11, (2012)
  • [4] Qiao H., Shi Y., Si H., Et al., Fast multi-classification of wheat take-all levels based on the fusion of unmanned aerial vehicle digital images and spectral data, Plant Protection, 41, 6, pp. 157-162, (2015)
  • [5] Bareth G., Low-weight and UAV-based hyperspectral full-frame cameras for monitoring crops: spectral comparison with portable spectroradiometer measurements, Photogrammetrie-Fernerkundung-Geoinformation, 1, pp. 69-79, (2015)
  • [6] Liu F., Liu S., Xiang Y., Study on monitoring fractional vegetation cover of garden plots by unmanned aerial vehicles, Transactions of the Chinese Society for Agricultural Machinery, 45, 11, pp. 250-257, (2014)
  • [7] Qiao H., Shi Y., Guo W., Et al., In-situ wheat take-all monitoring based on imaging spectrometer, Journal of Plant Protection, 42, 3, pp. 475-476, (2015)
  • [8] Zhu J., Chen Z., Shi Y., Et al., Diagnoses of rice nitrogen status based on spectral characteristics of leaf and canopy, Journal of Zhejiang University(Agriculture and Life Sciences), 36, 1, pp. 78-83, (2010)
  • [9] Gao L., Yang G., Yu H., Et al., Retrieving winter wheat leaf area index based on unmanned Jaerial vehicle hyperspectral remote sensing, Transactions of the CSAE, 32, 22, pp. 113-120, (2016)
  • [10] Aasen H., Generating 3D hyperspectral information with lightweight UAV snapshot cameras for vegetation monitoring: from camera calibration to quality assurance, ISPRS Journal of Photogrammetry and Remote Sensing, 108, pp. 245-259, (2015)
12