Abstract：Tomato is rich in nutrition, which most people love. It has a long growth cycle and requires a lot of water, and water content is the main factor influencing the tomato plant’s growth and development. It is of great significance to find out the water deficit state of tomato plants quickly for scientific and effective irrigation management of tomatoes, guaranteeing and improving the yield and quality of tomatoes. In this study, hyperspectral imaging technology was used to identify the degree of drought stress on tomato leaves in real-time, and a recognition method of drought stress on tomato leaves based on hyperspectral imaging technology was proposed. Firstly, a red cherry tomato was selected as the experimental variety, and 12 POTS of tomato seedlings were cultured in the laboratory. On the basis of ensuring the same as other management measures, the stress state of the tomato was controlled by controlling the amount of water applied. Then, three treatments (suitablewater, moderate and severe stress) were designed for the degree of drought stress. The hyperspectral images in the 400~1000nm range of young leaves of tomato seedlings with different drought degrees were collected in batches, and each sample’s spectral, texture characteristics were extracted. The spectral features were pre-processed using four methods, namely normalization (Norm), multiple scattering correction (MSC), first derivative (1st) and standard normalized variate (SNV) to remove noise from spectral data. The important feature bands of the spectral features were selected using the successive projections algorithm (SPA), competitive adaptive reweighting algorithm (CARS) and the competitive adaptive reweighting algorithm combined with the continuous projection algorithm (CARS-SPA). The texture features of tomato leaves were extracted by the Gray Level-Gradient Co-occurrence Matrix (GLGCM), and the important variables of texture features were selected by SPA. Finally, a support vector machine (SVM) was applied to fuse the above-mentioned various features to build a tomato drought stress recognition model, and Adaptive boosting (AdaBoost), and K-Nearest Neighbor (KNN) were used to compare and analyze with SVM model. The results showed that the SNV-SVM model based on CARS-SPA wavelength selection has the best classification effect after the fusion of important spectral features and texture features. The classification accuracy of the training set (ACCT) is 94.5%, and the classification accuracy of the prediction set (ACCP) is 95%. The adaBoost model had the second highest classification effect, ACCT 86.5%, and ACCP 87%. KNN model had the worst classification effect, with ACCT 81.5%, and ACCP 79%. Therefore, the method presented in this paper has a good effect on the real-time recognition of the drought stress degree of tomato leaves and can provide a reference for the construction of intelligent drought stress analysis technology.
Key words：Hyperspectral imaging; Tomato; Drought stress; Image and spectral features
贺 露，万 莉，高会议. 基于高光谱成像技术识别番茄干旱胁迫[J]. 光谱学与光谱分析, 2023, 43(03): 724-730.
HE Lu, WAN Li, GAO Hui-yi. Recognition of Drought Stress in Tomato Based on Hyperspectral Imaging. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(03): 724-730.
[1] ZHAO Hong, DENG Shan, ZHANG Yi-ying, et al(赵 洪，邓 姗，章毅颖，等). Jiangsu Agricultural Sciences(江苏农业科学), 2020, 48(12): 24.
[2] GONG Yi-dan, WANG Wei-hua, GUAN Neng-han, et al(龚一丹，王卫华，管能翰，等). China Cucurbits and Vegetables(中国瓜菜), 2020, 33(7): 7.
[3] Gu Q, Sheng L, Zhang T H, et al. Computers and Electronics in Agriculture, 2019, 167: 105066.
[4] Zhang Hailiang, Zhan Baishao, Pan Fan, et al. Postharvest Biology and Technology, 2020, 163: 111148.
[5] Xu Yunfei, Zhang Haijun, Zhang Chi, et al. Infrared Physics and Technology, 2019, 102: 103034.
[6] Nigon T J, Mulla D J, Rosen C J, et al. Computers & Electronics in Agriculture, 2015, 112: 36.
[7] Zhang C, Zhao Y Y, Yan T Y, et al. Infrared Physics & Technology, 2020, 111: 103550.
[8] Xia Jian, Zhang Wenyu, Zhang Weixin, et al. Computers and Electronics in Agriculture, 2021, 181: 105966.
[9] WANG Song-lei, WU Long-guo, WANG Cai-xia, et al(王松磊，吴龙国，王彩霞，等). Journal of Optoelectronics·Laser(光电子·激光), 2019, (9): 941.
[10] HUANG Yu-ping, Renfu Lu, QI Chao, et al(黄玉萍，Renfu Lu，戚 超，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2018, 38(7): 2183.
[11] FENG Bing, LI Zhi-tang, HUA Guang-lu(冯 兵，李芝棠，花广路). Journal of Communications(通信学报), 2013, 34(Z2): 1.
[12] HUO Ying-qiu, ZHANG Chen, LI Yu-hao, et al(霍迎秋，张 晨，李宇豪，等). Journal of Chinese Agricultural Mechanization(中国农机化学报), 2019, (4): 71.
[13] Li Jiayi, Yu Mei, Li Shangke, et al. Food Science & Nutrition, 2021, 9(8): 4176.
[14] Guo Anting, Huang Wenjiang, Ye Huichun, et al. Remote Sensing, 2020, 12(9): 1419.
[15] YUAN Xiao-kang, YANG Zai-qiang, QIU Yi-xuan, et al(袁小康，杨再强，邱译萱，等). Chinese Journal of Agrometeorology(中国农业气象), 2014, 35(6): 700.
[16] Elvanidi A, Katsoulas N, Ferentinos K P, et al. Biosystems Engineering, 2018, 165: 25.
