基于计算机视觉的农田残膜定位研究  被引量:2

Research on location of residual plastic film based on computer vision

在线阅读下载全文

作  者:江水泉 张海东[2] 华英杰[2] 

机构地区:[1]江苏楷益智能科技有限公司,江苏无锡214174 [2]云南农业大学机电工程学院,昆明市650201

出  处:《中国农机化学报》2016年第11期150-154,共5页Journal of Chinese Agricultural Mechanization

摘  要:介绍利用计算机单目视觉技术对农田残膜进行定位的方法。通过图像处理对残膜目标区域进行识别;利用最小外接矩形法确定残膜目标区域的形心,并基于形心点特征将识别后的残膜图像与原图像形心坐标进行匹配;最后对这两种坐标进行最小二乘拟合,获取匹配函数。结果表明,该方法所确定的残膜形心位置的偏差被控制在1.2cm以内,说明单目视觉技术可以较准确地定位农田中残膜的位置。A location method using monocular vision technology for residual plastic film on farm field was introduced.The target area of residual plastic film on raw images was segmented first by image processing methods.Then the method of minimum enclosing rectangle(MER)was used to determine the centroid of target area,and matching location based on point future was conducted to get the centroids of raw images.Based above results,the matching function of centroid location were solved out by least square method that was conducted between cetroid coordinates of raw images and segmented images.Result shows that the deviation of centroid coordinates of residual plastic films on farm field was controlled below 1.2cm.It also told that monocular vision technology is a comparatively accurate method for locating residual plastic films on farm field.

关 键 词:单目视觉 农田残膜 形心 图像匹配 

分 类 号:TP242.6[自动化与计算机技术—检测技术与自动化装置] S126[自动化与计算机技术—控制科学与工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象