湖北农业科学 ›› 2021, Vol. 60 ›› Issue (5): 125-130.doi: 10.14088/j.cnki.issn0439-8114.2021.05.025

• 信息工程 • 上一篇    下一篇

基于H分量K-Means多种环境条件下谷子冠层图像提取

郑小南, 张吴平, 韩冀皖, 杨凡, 刘宇平, 梁靓, 李富忠   

  1. 山西农业大学软件学院,山西 太谷 030801
  • 收稿日期:2020-09-29 出版日期:2021-03-10 发布日期:2021-03-22
  • 通讯作者: 李富忠(1969-),男,教授,(电子信箱)sxaulfz@126.com。
  • 作者简介:郑小南(1996-),女,山西洪洞人,在读硕士研究生,研究方向为计算机视觉,(电话)17835424470(电子信箱)995567507@qq.com;
  • 基金资助:
    山西省重点研发计划重点项目(201703D211002-2); 农业大数据创新平台项目(K481811076); 中小企业大数据平台开发项目(K4810902)

Under various environmental conditions millet canopy image extraction based on H-component K-means

ZHENG Xiao-nan, ZHANG Wu-ping, HAN Ji-wan, YANG Fan, LIU Yu-ping, LIANG Liang, LI Fu-zhong   

  1. College of Software, Shanxi Agricultural University, Taigu 030801,Shanxi,China
  • Received:2020-09-29 Online:2021-03-10 Published:2021-03-22

摘要: 以谷子为研究对象,采集谷子阴天、背景复杂有阴影、光照不均、露水雨水反光4类环境条件下的冠层图像,分别采用超绿分割、Lab空间K均值聚类分割和基于H分量的K均值聚类分割3种算法进行冠层提取,探究不同条件下谷子冠层提取的最优方法。对于阴天和背景复杂有阴影的谷子冠层图像,3种算法均可以较完整地提取,分割准确率均达到93%以上;对于光照不均的图像,超绿分割效果最差,基于Lab空间和基于H分量下的K均值聚类分割效果相对优异,分割准确率分别为93%和96%;对于露水雨水反光的图像,基于H分量的K均值聚类分割准确率最高,达到97%。基于H分量的K均值聚类算法对4种不同环境条件下获取的谷子冠层图像分割效果均较理想,为后续谷子生长自动监测提供了一定的参考价值。

关键词: K均值聚类, 谷子冠层分割, H分量

Abstract: This research takes millet as the research object, collects four types of canopy images of millet, cloudy sky, complex background with shadows, uneven illumination, and dew and rain reflection. The extra-green segmentation, K-means clustering segmentation in Lab space and H-component of K-means clustering segmentation are used for canopy extraction, and the optimal method for millet canopy extraction under different conditions is explored. For millet canopy images with cloudy and complex backgrounds and shadows, the three algorithms can extract relatively completely, and the segmentation accuracy was above 93%; for images with uneven lighting, the ultra-green segmentation effect is the worst, based on the Lab space and the K-means clustering segmentation effect of the H-component is relatively excellent, respectively, 93% and 96%; for the image of dew and rain reflection, the K-means clustering segmentation accuracy based on the H component is the highest, reaching 97%. The results show that the K-means clustering algorithm based on H component is ideal for segmentation of millet canopy images obtained under four different environmental conditions, which provides a certain reference value for subsequent automatic monitoring of millet growth.

Key words: K-means, millet canopy segmentation, H-component

中图分类号: