Tobacco Disease Detection Model Based on Band Selection
PAN Zhao-jie1, SUN Gen-yun1, 2*, ZHANG Ai-zhu1, FU Hang1, WANG Xin-wei3, REN Guang-wei3
1. College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, China
2. Laboratory for Marine Resources Qingdao National Laboratory for Marine Science and Technology, Qingdao 266237, China
3. Tobacco Research Institute of Chinese Academy of Agricultural Sciences, Qingdao 266101, China
Abstract:Tobacco is an important economic crop and source of tax revenue in our country. It makes a huge contribution to the country’s economic development. However, tobacco diseases affect the yield and quality of tobacco leaves seriously. Therefore, It is important that the use spectral analysis technology for early prevention and control of tobacco diseases. Objects of research are tobaccos inoculated with tobacco mosaic virus (TMV) and potato Y virus (PVY). The hyperspectral data of infected tobacco cultivated indoors and outdoors are collected respectively. In order to improve the detection accuracy of tobacco diseases, spectral data of two kinds of diseased tobacco are collected every two days, each disease data is divided into five severity levels in detail, and finally, 1 697 spectral data in the 350~2 500 nm band are obtained. In order to make effective use of hyperspectral tobacco data, this paper is based on a support vector machine (SVM), combined with a fast nearest neighbor band selection algorithm (FNGBS) and normalized matched filtering (NMFW), and proposes a combination of clustering and sorting Band selection algorithm (FNG-NMFW). Firstly, FNG-NMFW uses the FNGBS to group the tobacco spectrum finely and then sorts the groups of bands based on the NMFW algorithm to select the characteristic spectrum and realize the extraction and dimensionality of the tobacco spectrum. After completing the band selection, this paper uses SVM to classify tobacco characteristic spectra and achieves high-precision tobacco disease detection. The research results show that the model has stable performance and high accuracy. When the proportion of training samples is only 40%, an overall accuracy (OA) is better than 80%; when the number of feature bands is selected as 40, OA can be better than 85%. The algorithm can achieve higher accuracy for both TMV and PVY diseases, but the recognition accuracy of TMV is slightly lower than that of PVY. For the monitoring of TMV1 and TMV3, the algorithm can achieve monitoring with an accuracy better than 94%, and for the monitoring of PVY1 and PVY3, the accuracy of the algorithm is close to 90%, which shows that the algorithm can realize the early identification and prevention of two diseases. Compared with the model that uses full-band spectral data for disease detection, the FNG-NMFW model has obvious advantages. The accuracy of tobacco disease detection results is 94.46%, the accuracy is improved by more than 1.5%, and the modeling time is shortened from 12.9 seconds to 1.1 seconds.
Key words:Tobacco disease; Precise identification; Hyperspectral; Band selection; Support vector machine
潘兆杰,孙根云,张爱竹,付 航,王新伟,任广伟. 基于波段选择的烟草病害检测模型[J]. 光谱学与光谱分析, 2023, 43(04): 1023-1029.
PAN Zhao-jie, SUN Gen-yun, ZHANG Ai-zhu, FU Hang, WANG Xin-wei, REN Guang-wei. Tobacco Disease Detection Model Based on Band Selection. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(04): 1023-1029.
[1] SHEN Xue-ting, LING Ping, PENG Tao-jun, et al(沈雪婷, 凌 平, 彭桃军, 等). Acta Agriculturae Jiangxi(江西农业学报), 2016, 28(7): 78.
[2] LÜ Xiao-yao, JING Xia, XUE Lin, et al(吕小艳, 竞 霞, 薛 琳, 等). Chinese Agricultural Science Bulletin(中国农学通报), 2020, 36(25): 137.
[3] SUN Jun, CONG Sun-li, MAO Han-ping, et al(孙 俊, 丛孙丽, 毛罕平, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2017, 33(5): 178.
[4] LEI Yu, HAN De-jun, ZENG Qing-dong, et al(雷 雨, 韩德俊, 曾庆东, 等). Transactions of The Chinese Society of Agricultural Machinery(农业机械学报), 2018, 49(5): 226.
[5] WANG Xiao-long, DENG Ji-zhong, HUANG Hua-sheng, et al(王小龙, 邓继忠, 黄华盛, 等). Journal of South China Agricultural University(华南农业大学学报), 2019, 40(3): 97.
[6] LÜ Xiao-yan, XUE Lin, JING Xia, et al(吕小艳, 薛 琳, 竞 霞, 等). Chinese Agricultural Science Bulletin(中国农业通报), 2021, 37(24): 54.
[7] LIU Yong-chang, GENG Li, GAO Qiang, et al(刘勇昌, 耿 丽, 高 强, 等). Tobacco Science & Technology(烟草科技), 2021, 54(7): 23.
[8] LI Meng-zhu, YE Hong-chao, WANG Hui, et al(李梦竹, 叶红朝, 王 惠, 等). Acta Tabacaria Sinica(中国烟草学报), 2020, 26(4): 86.
[9] WANG Shuai, GUO Zhi-xing, LIANG Xue-ying, et al(王 帅, 郭治兴, 梁雪映, 等). Journal of Shanxi Agricultural Sciences(山西农业科学), 2021, 49(2): 195.
[10] YANG Yan-dong, JIA Fang-fang, LIU Xin-yuan, et al(杨艳东, 贾方方, 刘新源, 等). Journal of Henan Agricultural Sciences(河南农业科学), 2019, 48(5): 155.
[11] CHEN Nan, FENG Hui-lin, YANG Yan-dong, et al(陈 楠, 冯慧琳, 杨艳东, 等). Journal of Agricultural Resources and Environment(农业资源与环境学报), 2021, 38(4): 570.
[12] ZHU Yang, XU Shuai-tao, LI Yi-jia, et al(朱 洋, 许帅涛, 李艺嘉, 等). Grain Science and Technology and Economy(粮食科技与经济), 2019, 44(5): 114.
[13] XIE Yu-rui, MIAO Sheng, ZHANG Shuo, et al(谢裕睿, 苗 晟, 张 铄, 等). Modern Computer(现代计算机), 2020,(30): 27.
[14] Wang Q, Li Q, Li X. Transactions on Geoscience and Remote Sensing, 2020, (99): 1.
[15] Ji L Y, Wang L, Geng X R, et al. Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(12): 4985.
[16] Xia J S, Chanussot J, Du P J, et al. Transactions on Geoscience and Remote Sensing, 2016, 54(3): 1519.
[17] Wu K P, Wang S D. Pattern Recognition, 2009, 42(5): 710.