Research of weed feature extraction method based on image processing technology

TAN Rong-rong; ZHU Wei-xing

doi:10.13873/j.1000-97872009.02.019

Chinese

您当前的位置：

首页 >

文章列表页 >

Research of weed feature extraction method based on image processing technology

更新时间：2025-09-11

- Research of weed feature extraction method based on image processing technology
- Vol. 28, Issue 2, Pages: 56-59+65(2009)
- 作者机构：
  
  江苏大学电气信息工程学院
- 作者简介：
- 基金信息：
- DOI：10.13873/j.1000-97872009.02.019
  CLC： TP391.41
- Published：2009
- 稿件说明：
移动端阅览
[1]谈蓉蓉,朱伟兴.基于图像处理技术的杂草特征提取方法研究[J].传感器与微系统,2009,28(02):56-59+65.

TAN Rong-rong, ZHU Wei-xing. Research of weed feature extraction method based on image processing technology[J]. 2009, 28(2): 56-59+65.
[1]谈蓉蓉,朱伟兴.基于图像处理技术的杂草特征提取方法研究[J].传感器与微系统,2009,28(02):56-59+65. DOI： 10.13873/j.1000-97872009.02.019.

TAN Rong-rong, ZHU Wei-xing. Research of weed feature extraction method based on image processing technology[J]. 2009, 28(2): 56-59+65. DOI： 10.13873/j.1000-97872009.02.019.

摘要

利用计算机视觉技术将杂草从背景中识别出来进行定位喷洒农药已成为精细农业研究的热点。选取颜色空间OHTA中I2′分量作为特征量;利用基于遗传算法的自动阈值选取方法对特征分量I2′进行阈值分割初步分离杂草与小麦;通过颜色聚类和形态滤波获得准确的杂草区域。实验结果表明:直接在彩色空间进行分割

可提高彩色图像的分割效果

利用该方法获得的杂草平均正确识别率达到90.47%。

Abstract

Computer vision technology used to weed identification from background which to spray herbicide in a precise position has become a hot research of precision agriculture.A weed identification method that takes OHTA as color space and I2′as characteristic variant is presented

automatic threshold selection method on the basis of genetic algorithms for the feature component I2′is used to separate weed and wheat preliminarily

and then color clustering and morphological filtering is used to achieve the accurate weed regions.The experiment results show that separating directly in the color space would improve the segmentation effect of color images

and the average correct identification rate reaches 90.47 % using the method proposed before.

关键词

Keywords

references

基于颜色分量运算与色域压缩的杂草实时检测方法 [J]. 周平,汪亚明,赵匀. 农业机械学报 . 2007(01)

在遗传算法基础上的自动阈值选取方法 [J]. 李辉,吕英华. 东北师大学报(自然科学版) . 2006(02)

基于OHTA颜色空间的瓜果轮廓提取方法 [J]. 郭峰,曹其新,谢国俊,周金良. 农业机械学报 . 2005(11)

基于机器视觉的苗期杂草实时分割算法 [J]. 毛文华,王一鸣,张小超. 农业机械学报 . 2005(01)

基于视觉颜色聚类的彩色图像分割 [J]. 王圆圆,丁志杰,万华林. 北京理工大学学报 . 2003(06)

利用色度法识别杂草和土壤背景物 [J]. 相阿荣,王一鸣. 中国农业大学学报 . 2000(04)

图像处理与模式识别[M]. 科学出版社 , 范立南, 2007

Segmentation of row crop plants from weeds using colour and morphology [J] . Christine M. Onyango,J.A. Marchant. Computers and Electronics in Agriculture . 2003 (3)

Weed and crop discrimination using image analysis and artificial intelligence methods [J] . M.J. Aitkenhead,I.A. Dalgetty,C.E. Mullins,A.J.S. McDonald,N.J.C. Strachan. Computers and Electronics in Agriculture . 2003 (3)

A fast scheme for optimal thresholding using genetic algorithms [J] . Peng-Yeng Yin. Signal Processing . 1999 (2)

Views

336

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Networking study on mobile nodes of WSNs in coal mine

Cylinder pressure signal processing in engine based on morphological filter

Related Author

WANG Jian-ping

WU Zheng-feng

LI Bing-lin

WEI Min-xiang

Related Institution

School of Electric Engineering and Automation,Hefei University of Technology

College of Energy and Power Engineering,Nanjing University of Aeronautics andAstronautics

⁰