| 基于SVM和D-S证据理论的多特征融合杂草识别方法 |
| |
| 引用本文： | 李先锋,朱伟兴,孔令东,花小朋.基于SVM和D-S证据理论的多特征融合杂草识别方法[J].农业机械学报,2011,42(11):164-168,163. |
| |
| 作者姓名： | 李先锋 朱伟兴 孔令东 花小朋 |
| |
| 作者单位： | 1. 盐城工学院信息工程学院,盐城,224051
2. 江苏大学电气信息工程学院,镇江,212013 |
| |
| 基金项目： | 盐城工学院重点建设学科开放基金资助项目(XKY2010021);江苏大学现代农业装备与技术省部共建教育部重点实验室开放基金资助项目(NZ200709) |
| |
| 摘 要： | 针对单一特征识别杂草的低准确率和低稳定性,提出一种支持向量机( SVM)和D-S证据理论相结合的多特征融合杂草识别方法.在对田间植物图像处理的基础上,提取植物叶片的颜色、形状和纹理等3类视觉特征,分别以3类单特征的SVM分类结果作为独立证据构造基本概率指派(BPA),运用D-S证据组合规则进行决策级融合,根据分类判决门...
|
| 关 键 词： | 杂草识别 特征提取 支持向量机 D-S证据理论 决策级融合 |
Method of Multi-feature Fusion Based on SVM and D-S Evidence Theory in Weed Recognition |
| |
| Li Xianfeng,Zhu Weixing,Kong Lingdong and Hua Xiaopeng.Method of Multi-feature Fusion Based on SVM and D-S Evidence Theory in Weed Recognition[J].Transactions of the Chinese Society of Agricultural Machinery,2011,42(11):164-168,163. |
| |
| Authors: | Li Xianfeng Zhu Weixing Kong Lingdong and Hua Xiaopeng |
| |
| Institution: | Yancheng Institute of Technology;Jiangsu University;Yancheng Institute of Technology;Yancheng Institute of Technology |
| |
| Abstract: | According to the low accuracy and low stability of the single feature-based method for weed recognition,a multi-feature fusion method based on SVM and D-S evidence theory was proposed.Firstly,three types of visual features such as color,shape and texture were extracted from the plant leaves after a series of image processing.Then,the plants were classified according to each type of features utilizing SVM and the results were used as evidences to construct the basic probability assignment(BPA).Finally,using ... |
| |
| Keywords: | Weed recognition Feature extraction Support vector machine D-S evidence theory Decision fusion |
| 本文献已被 CNKI 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 |
