| 皮棉中地膜的高光谱图像分割方法 |
| |
| 引用本文： | 张航,乔曦,李振波,李道亮.皮棉中地膜的高光谱图像分割方法[J].农业工程学报,2016,32(13):161-167. |
| |
| 作者姓名： | 张航 乔曦 李振波 李道亮 |
| |
| 作者单位： | 1. 中国农业大学信息与电气工程学院,北京100083;天津农学院计算机与信息工程学院,天津300384;北京市农业物联网工程技术研究中心,北京100083;2. 中国农业大学信息与电气工程学院,北京100083;北京市农业物联网工程技术研究中心,北京100083;农业部农业信息获取技术重点实验室,北京100083 |
| |
| 基金项目： | 国家自然科学基金资助项目(31228016) |
| |
| 摘 要： | 混入棉花中的地膜大部分是透明的或者颜色与棉花相近,使用传统的视觉检测方法很难对其进行检测。针对此问题,采集了地膜的高光谱图像,结合光谱分析与图像处理技术,提出一种地膜的高光谱图像分割方法。首先提取地膜的平均光谱数据,经过去除噪声波段、多项式卷积平滑(Savitzky-Golay,SG)、标准正态变量(standard normal variate,SNV)变换等操作后,使用偏最小二乘回归(partial least squares regression,PLSR)分析方法优选出4个最优波段,分别为560.3、673.9、716.9和798.8 nm;然后提取出4个波段对应的图像,分别进行两次图像融合,并对融合后的图像进行阈值分割、中值滤波操作;最后对处理后的图像再次进行图像融合,并移除小目标得到最终结果。为验证该方法,采用面积交迭度(area overlap measure,AOM)、误分率(misclassified error,ME)和识别率(recognition accuracy)对分割结果进行客观评价分析,结果表明该方法能较好地完成对地膜图像的分割,可为后续的地膜特征提取和自动识别打下良好的基础。
|
| 关 键 词： | 地膜 光谱分析 高光谱图像 算法 图像分割 图像融合 偏最小二乘回归 |
| 收稿时间： | 2016/1/20 0:00:00 |
| 修稿时间： | 2016/3/21 0:00:00 |
Hyperspectral image segmentation method for plastic films in ginned cotton |
| |
| Zhang Hang,Qiao Xi,Li Zhenbo and Li Daoliang.Hyperspectral image segmentation method for plastic films in ginned cotton[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(13):161-167. |
| |
| Authors: | Zhang Hang Qiao Xi Li Zhenbo and Li Daoliang |
| |
| Institution: | College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China;College of Computer and Information Engineering, Tianjin Agricultural University, Tianjin 300384, China;Beijing Engineering and Technology Research Center for Internet of Things in Agriculture, Beijing 100083, China,College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China;Beijing Engineering and Technology Research Center for Internet of Things in Agriculture, Beijing 100083, China;Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture, Beijing 100083, China,College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China;Beijing Engineering and Technology Research Center for Internet of Things in Agriculture, Beijing 100083, China;Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture, Beijing 100083, China and College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China;Beijing Engineering and Technology Research Center for Internet of Things in Agriculture, Beijing 100083, China;Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture, Beijing 100083, China |
| |
| Abstract: | |
| |
| Keywords: | plastic films spectrum analysis hyperspectral image algorithms image segmentation image fusion partial least squares regression |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《农业工程学报》浏览原始摘要信息 |
| 点击此处可从《农业工程学报》下载免费的PDF全文 |
|
