首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于高光谱图像技术的稻田苗期杂草稻识别
引用本文:陈树人,邹华东,吴瑞梅,闫润,毛罕平.基于高光谱图像技术的稻田苗期杂草稻识别[J].农业机械学报,2013,44(5):253-257,163.
作者姓名:陈树人  邹华东  吴瑞梅  闫润  毛罕平
作者单位:1. 江苏大学现代农业装备与技术教育部重点实验室,镇江,212013
2. 江西农业大学工学院,南昌,330045
3. 江苏大学现代农业装备与技术教育部重点实验室,镇江212013;江苏农林职业技术学院机电工程系,句容212400
基金项目:国家高技术研究发展计划(863计划)资助项目(2008AA10Z204);江苏高校优势学科建设工程项目资助项目(苏财教(2011)8号)
摘    要:以生长期为10 d的杂草稻和水稻为研究对象,采集其高光谱图像信息,对其进行滤波预处理后,利用主成分分析方法优选出1448.89 nm和1469.89 nm波长下的特征图像.对每个特征图像,分别提取其形状特征、纹理特征和颜色特征,共18个特征变量.基于这些特征变量,利用神经网络方法建立杂草稻和水稻的判别模型,模型训练时杂草稻和水稻的回判率都为100%;预测时,杂草稻的回判率为92.86%,水稻的回判率为96.88%.研究表明,利用高光谱图像技术快速鉴别稻田苗期杂草稻是可行的.

关 键 词:杂草稻  水稻  高光谱图像  神经网络

Identification for Weedy Rice at Seeding Stage Based on Hyper-spectral Imaging Technique
Chen Shuren,Zou Huadong,Wu Ruimei,Yan Run and Mao Hanping.Identification for Weedy Rice at Seeding Stage Based on Hyper-spectral Imaging Technique[J].Transactions of the Chinese Society of Agricultural Machinery,2013,44(5):253-257,163.
Authors:Chen Shuren  Zou Huadong  Wu Ruimei  Yan Run and Mao Hanping
Institution:Jiangsu University;Jiangsu University;Jiangxi Agricultural University;Jiangsu University;Jiangsu Polytechnic College of Agriculture and Forestry;Jiangsu University
Abstract:The weedy rice and rice in growth period of 10d were investigated. The hyper spectral image data were captured from weedy rice and rice leaves. After image data were filtered, the feature images at wavelength of 1448.89nm and 1469.89nm were optimized by principal component analysis method. For each feature image, shape feature, texture feature and color feature were extracted, and 18 feature variables in all were attained. Neural network method was used to build the discriminate model. The discriminating rates for weedy rice and rice were both 100% in training set. The discriminating rate for weedy rice was 92.86% and the discriminating rate for rice was 96.88% in prediction set. Experimental results showed that the hyper-spectral imaging technology could be used to identify weedy rice and rice at seeding stage.
Keywords:Weedy rice  Rice  Hyper-spectral image  Neural network
本文献已被 万方数据 等数据库收录!
点击此处可从《农业机械学报》浏览原始摘要信息
点击此处可从《农业机械学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号