高光谱成像的柑橘病虫害叶片识别方法

doi:10.3964/j.issn.1000-0593(2021)12-3837-07

Abstract
References
Related Citation (15)

Download: PDF (3027 KB)
Export: BibTeX | EndNote (RIS)

Abstract To monitor citrus growth and realize nondestructive identification of pests and diseases, the leaf classification of citrus diseases was studied using hyperspectral imaging technology and machine learning method. Using hyperspectral imager to collect hyperspectral images of 46 normal citrus leaves, 46 canker leaves, 80 herbicide-damaged leaves, 51 red spider diseased leaves, and 98 soot diseased leaves. A 5×5 regions of interest (ROI) were extracted from one or more diseased areas of each leaf in the 478~900 nm spectral range. Taking the reflectance value of each pixel in the ROI as the spectral information, one ROI would get 25 spectral information samples, and finally the five types of leaves get a total of 13 250 spectral samples. The samples were divided into 9938 training sets and 3 312 test sets by random method. The first derivative (1^st Der), multiple scattering correction (MSC) and standard normal transformation (SNV) were used to preprocess the original spectral information, and principal component analysis (PCA) was used to extract the characteristic wavelength of the data after different preprocessing methods. After 1st Der pretreatment, 7 characteristic wavelengths were obtained, which were 520.2, 689,704.83, 715.38, 731.2, 741.75 and 757.58nm respectively. After MSC and SNV pretreatment, 7 identical characteristic wavelengths were obtained, which were 551.85, 678.45, 704.83, 710.1, 725.93, 731.2 and 757.58 nm, respectively. The original spectrum obtained seven characteristic wavelengths, which were 525.48, 678.45, 710.1, 720.65, 725.93, 757.58 and 762.85 nm, respectively. The scatter plot of sample distribution after PCA analysis showed that there was a certain degree of clustering of normal leaves, canker leaves and starscream leaves, and a large amount of overlap between herbicide leaves and soot leaves, so the identification of pest and disease leaves could not be completed only based on PCA. Support vector machine (SVM) and random forest (RF) were used to model the all-band spectrum (FS) and PCA characteristic wavelength data under different pretreatment methods, and the results showed that: The OA of 1^st Der-FS-SVM model was 95.98%, the Kappa coefficient was 0.948 2, the OA of 1^st Der-FS-RF model was 91.42%, the Kappa coefficient was 0.889 2, the OA of 1^st Der-FS-SVM model was 90.82%, and the Kappa coefficient was 0.881 6, OA and Kappa coefficient in 1^st Der-PA-RF model was 91.79% and 0.894 respectively. For PCA characteristic wavelength data modeling, the recognition rate of SVM and RF models reached 84%, and the recognition rate of the full-band spectrum model was above 88%. The FS data modeling effect was better than that of PCA characteristic wavelength. The results show that it is feasible and effective to classify citrus leaves by hyperspectral imaging technique combined with machine learning method, which provides a theoretical basis for the accurate and nondestructive identification of citrus pests and diseases.

Key words：Hyperspectral imaging; Principal component analysis; Support vector machines; Random forest

Received: 2020-10-26 Accepted: 2021-01-18

ZTFLH:

O433.4

Cite this article:

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2021)12-3837-07 OR https://www.gpxygpfx.com/EN/Y2021/V41/I12/3837

[1] YUE Xue-jun, LING kang-jie, WANG Lin-hui, et al(岳学军，凌康杰，王林惠，等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2019, 50(3): 186.
[2] Gu Q, Sheng L, Zhang T H, et al. Computers and Electronics in Agriculture, 2019, 167: 105066.
[3] Wang K J, Guo D M, Zhang Y, et al. Frontiers of Agricultural Science and Engineering, 2019, 6(2): 172.
[4] LIU Yan-de, XIAO Huai-chun, SUN Xu-dong, et al(刘燕德，肖怀春，孙旭东，等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2016, 47(11): 231.
[5] MEI Hui-lan, DENG Xiao-ling, HONG Tian-sheng, et al(梅慧兰，邓小玲，洪添胜，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2014, 30(9): 140.
[6] LAN Yu-bin, ZHU Zi-hao, DENG Xiao-ling, et al(兰玉彬，朱梓豪，邓小玲，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2019, 35(3): 92.
[7] DENG Xiao-ling, ZENG Guo-liang, ZHU Zi-hao, et al(邓小玲，曾国亮，朱梓豪，等). Journal of South China Agricultural University(华南农业大学学报)，2020，41(6)：100.
[8] Abdulridha J, Batuman O, Ampatzidis Y. Remote Sensing, 2019, 11(11): 1373.
[9] CHU Bing-quan, ZHANG Hai-liang, LUO Wei, et al(楚秉泉，章海亮，罗微，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2017, 37(8): 2551.
[10] HUO Ying-qiu, ZHANG Chen, LI Yu-hao, et al(霍迎秋，张晨，李宇豪，等). Chinese Journal of Agricultural Mechanization(中国农机化学报), 2019, 40(4): 71.
[11] Tian X, Fan S X, Huang W Q, et al. Postharvest Biology and Technology, 2020, 161: 111071.
[12] DU Pei-jun, XIA Jun-shi, XUE Chao-hui, et al(杜培军，夏俊士，薛朝辉，等). Journal of Remote Sensing (遥感学报), 2016, 20(2): 236.
[13] Guo A T, Huang W J, Ye H C, et al. Remote Sensing, 2020, 12(9): 1419.
[14] Lauwers M, Cauwer D B, Nuyttens D, et al. Sensors, 2020, 20(9): 2504.
[15] LI Lei, REN Yue-mei(李垒，任越美). Computer Engineering and Applications(计算机工程与应用), 2016, 52(24): 189.