上海交通大学学报(自然版) ›› 2018, Vol. 52 ›› Issue (8): 961-968.doi: 10.16183/j.cnki.jsjtu.2018.08.012

• 学报(中文) • 上一篇    下一篇

基于自定义聚类的水稻剑叶夹角测量

汪韬,贡亮,张经纬,吴林立梓,马志宏,杨刚,毛雨晗,洪骏,刘成良   

  1. 上海交通大学 机械与动力工程学院, 上海 200240
  • 收稿日期:2017-04-17
  • 通讯作者: 贡亮,男,副教授,博士生导师,电话(Tel.):021-34206071;E-mail:gongliang_mi@sjtu.edu.cn.
  • 作者简介:汪韬(1994-),男,浙江省杭州市人,硕士生,主要研究方向为农业机器人视觉伺服控制.
  • 基金资助:
    上海市农业委员会项目(2015-2018),上海科技兴农项目(沪农种字(2015)第20号)

Measurement of Rice Flag Leaf Angle Based on Redefined Clustering Method

WANG Tao,GONG Liang,ZHANG Jingwei,WU Linlizi,MA Zhihong,YANG Gang,MAO Yuhan,HONG Jun,LIU Chengliang   

  1. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
  • Received:2017-04-17

摘要: 针对水稻样本图像中主茎被遮挡,现有算法难以识别剑叶节点、散岔稻穗主轴问题,提出了基于机器视觉的剑叶节点搜索算法,通过自定义聚类生成稻穗与剑叶类中心,识别判定散岔稻穗轴线,最终得到穗叶夹角.其中,提出的剑叶节点搜索算法对剑叶节点的模糊定位进行量化,经过实验验证,具有较好的鲁棒性和准确性;自定义的K-means方法基于样本统计信息,解决了散岔穗叶夹角测量问题.实验表明,该算法误差为1.89%,与现有算法相比,局限性低,鲁棒性强,更准确高效.

关键词: 机器视觉, 剑叶夹角, 在体测量, 聚类, 节点搜索

Abstract: The flag leaf angle is one of key parameters for determining the rice yield, achieving accurate, efficient and in vivo measurement of flag leaf angle is significant to rice breeding, plant type research and production instruction. However, the stems in sample images are usually obscured, moreover, current algorithms cannot recognize flag leaf nodes and axes of diverging, bifurcate rice ears. Hence, a flag leaf node searching algorithm is presented, then the cluster center of rice ear and leaf is generated by a redefined clustering method in order to recognize the angles between rice ear and flag leaf. The leaf node searching algorithm quantifies the fuzzy localization of leaf node, and it is proved to be robust and accurate by experiment. The redefined K-means method is based on the statistical information of samples, it can solve the problem that current algorithms cannot measure angles between diverging, bifurcate rice ear and flag leaf. Furthermore, it is practical in measuring the intersection angles in various plants’ bifurcate form. Hence, the paper proposes a new thought of clustering in multi-axial data set. Experimental results show that, the algorithm had an error of 1.89% with low limitation, stronger robustness and higher degree of accuracy.

Key words: machine vision, flag leaf angle, in vivo measurement, clustering, node searching

中图分类号: