基于监督局部线性嵌入算法的玉米田间杂草识别
杂草精准识别是实现农药定向定量喷洒的基础,是精准农业重要的研究课题之一,对环境保护和生产成本控制都有着重要的现实意义。该文以玉米田间常见杂草为研究对象,首先通过超绿特征去除田间复杂背景的影响,然后采用形态学方法自动分割图像中绿色植物区域作为待判别为杂草或作物的识别对象,之后采用基于Fisher投影的监督LLE（locally linear embedding）方法对样本的高维灰度特征进行降维,在低维空间结合支持向量机实现了杂草的快速识别。试验结果表明,该识别方法能更好地发现杂草与玉米的低维特征,对杂草和玉米植株的平均识别率分别达到97.2%和77.8%。该研究结果可为精准喷洒除草剂的自动化实现...
Saved in:
| Published in | 农业工程学报 Vol. 29; no. 14; pp. 171 - 177 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese |
| Published |
安徽大学计算智能与信号处理教育部重点实验室，合肥 230601
2013
国家农业信息化工程技术研究中心，北京 100097 安徽大学电气工程与自动化学院，合肥 230601%安徽大学计算智能与信号处理教育部重点实验室,合肥,230601%安徽大学计算智能与信号处理教育部重点实验室，合肥 230601 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1002-6819 |
| DOI | 10.3969/j.issn.1002-6819.2013.14.022 |
Cover
| Summary: | 杂草精准识别是实现农药定向定量喷洒的基础,是精准农业重要的研究课题之一,对环境保护和生产成本控制都有着重要的现实意义。该文以玉米田间常见杂草为研究对象,首先通过超绿特征去除田间复杂背景的影响,然后采用形态学方法自动分割图像中绿色植物区域作为待判别为杂草或作物的识别对象,之后采用基于Fisher投影的监督LLE（locally linear embedding）方法对样本的高维灰度特征进行降维,在低维空间结合支持向量机实现了杂草的快速识别。试验结果表明,该识别方法能更好地发现杂草与玉米的低维特征,对杂草和玉米植株的平均识别率分别达到97.2%和77.8%。该研究结果可为精准喷洒除草剂的自动化实现提供参考。 |
|---|---|
| Bibliography: | 11-2047/S image processing, identification, algorithms, supervised LLE, support vector machine Yan Qing, Liang Dong, Zhang Dongyan （1. Key Lab of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei 230601, China; 2. National Engineering Research Center for Information Technology in Agriculture, Beijing 100097, China, 3. School of Electronical Engineering and Automation, Anhui University, Hefei 230601, China） Large-scale pesticide spraying will raise costs in agriculture and will cause environmental pollution. In order to realize quantitative and directional spraying, weed identification using image-processing technology is one of the focus problems in the precision-agriculture field. The foundation of automated identification is feature extraction. Because the dimensions of the feature are usually very high, before identification the dimensions must be reduced. The performance of any dimension-reduction method will directly affect the recognition results. The traditional |
| ISSN: | 1002-6819 |
| DOI: | 10.3969/j.issn.1002-6819.2013.14.022 |