Research on Lettuce Leaves’ Moisture Prediction Based on Hyperspectral Images
SUN Jun1,2, WU Xiao-hong2, ZHANG Xiao-dong1, GAO Hong-yan1
1. Jiangsu Provincial Key Laboratory of Modern Agricultural Equipment and Technology, Jiangsu University, Zhenjiang 212013，China 2. School of Electrical and Information Engineering of Jiangsu University, Zhenjiang 212013, China
Abstract：In order to conduct rational management of watering lettuce, the model of detecting lettuce leaves’ moisture was built. First of all, the hyperspectral images of lettuce leaves were acquired and simultaneously the moisture proportions of leaves were measured. Meanwhile, hyperspectral images were analyzed and the characteristic bands of lettuce leaves’ moisture were found. Then the images in characteristic bands were processed and the image features of lettuce leaves’ moisture were computed. The image features highly relevant to moisture were obtained through correlation analysis. Furthermore, due to the possible correlation among image features, the principal components of the images were extracted by principal components analysis and were used as BP neural network’s inputs to establish PCA-ANN model. At the same time, other models were constructed by using BP neural network and traditional MLR (multiple liner regression) method respectively. Prediction examinations of the three models were made based on the same sample data. The experimental results show that the average prediction error of PCA-ANN prediction model of tillering stage reaches 9.323% which is improved compared with BP-ANN and MLR prediction models.
[1] Rodriguez D, Fitzgerald G, Christensen L, et al. Remote Sensing of Environment, 2007, 108: 121. [2] MAO Han-ping, ZHANG Xiao-dong, LI Xue, et al(毛罕平, 张晓东, 李 雪, 等). Journal of Jiangsu University·Natural Science Edition(江苏大学学报·自然科学版)，2008, 29(5): 369. [3] HUANG Cai-jin, HAN Lu-jia, LIU Xian, et al(皇才进，韩鲁佳，刘 贤，等). J. Infrared Millim. Waves(红外与毫米波学报)，2009，28：184. [4] CAI Hong-chang, CUI Hai-xin, GAO Li-hong, et al(蔡鸿昌, 崔海信, 高丽红, 等). Chinese Agricultural Science Bulletin(中国农学通报)，2006, 22(8): 532. [5] WANG Fang-yong, WANG Ke-ru, WANG Chong-tao(王方永, 王克如, 王崇桃). Journal of Shihezi University Natural Science(石河子大学学报)，2007，(4): 404. [6] DAI Zhi-xiang, SHAO Lu-shou, DING Ke-jian(戴之祥, 邵陆寿, 丁克坚). Transactions of The Chinese Society of Agricultural Machinery(农业机械学报)，2007，38: 200. [7] CAI Jian-rong, WANG Jian-hei, CHEN Quan-sheng, et al(蔡健荣, 王建黑, 陈全胜, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2009, 25: 127. [8] HONG Tian-sheng, QIAO Jun, NING Wang, et al(洪添胜, 乔 军, NING Wang, 等). Transactions of The Chinese Society of Agricultural Engineering(农业工程学报)，2007，23: 151. [9] LI Jiang-bo, SU Yi-nan, RAO Xiu-qin(李江波, 苏忆楠, 饶秀勤). Packaging and Food Machinery(包装与食品机械)，2010，28: 1. [10] ZHANG Xin-ming, ZHANG Ai-li, ZHANG Yan-bin, et al(张新明, 张爱丽, 郑延斌, 等). Computer Science(计算机科学)，2011，38: 278. [11] LI Lin(李 林). Journal of Tarim University(塔里木大学学报)，2007，19: 40. [12] CHEN Bo, OUYANG Zhu(陈 博, 欧阳竹). Transactions of The Chinese Society of Agricultural Engineering(农业工程学报)，2010，24: 81. [13] MA Sha, XIAO Ming, HUANG Zhi-quan(马 莎, 肖 明, 黄志全). Engineering Journal of Wuhan University(武汉大学学报)，2008，54: 43.
