江苏大学学报（自然科学版）2016，Vol.37Issue(2)：174-182,9.DOI:10.3969/j.issn.1671-7775.2016.02.009
基于PCA－BP多特征融合的油菜水分胁迫无损检测
Nondestructive testing method for rape water stress with multiple features information fusion based on PCA-BP method
摘要
Abstract
The canopy spectral reflectance,the multi-spectral image and the canopy temperature were fused to quantitatively analyze the rape moisture content based on nondestructive testing of rape water stress.Stepwise regression method was used to extract the features of moisture content from different sensors.The water stress index (CWSI)was obtained by detecting canopy-air temperature difference and environment temperature and humidity to compensate light influence.The results show that the spectral features at wavelength of 960,1 450,1 650 nm,the features of image mean value at 560,960,81 0 nm and the image ratios at 960 nm to 81 0 nm are highly correlated with the rape moisture content during the whole growth period of rope.The principal component analysis (PCA)was applied to transform and reduce dimensions for feature space,and the prediction model of moisture content of rape was built by BP neural network.The results show that more information can be integrated to achieve the quantitative analysis of water stress of rape.The proposed model precision is obviously higher than that of single detection method.关键词
油菜/含水率/多光谱图像/水分胁迫指数/信息融合Key words
rape/moisture content/multi-spectral image/water stress index/information fusion分类
化学化工引用本文复制引用
张晓东,李立,毛罕平,高洪燕,苏辰..基于PCA－BP多特征融合的油菜水分胁迫无损检测[J].江苏大学学报（自然科学版）,2016,37(2):174-182,9.基金项目
国家自然科学基金重点资助项目（61233006）；国家“十二五”科技支撑计划项目（2014BAD08B03）；中国博士后科学基金资助项目（20100481097）；江苏高校优势学科建设工程项目（苏政办发［2011］6号）；江苏省农业装备与智能化高技术研究重点实验室项目（BM2009703）；江苏大学高级专业人才基金资助项目 （）
