大豆植株分杈数自动提取算法研究  

Study on Automatic Extraction Algorithm for Soybean Plant Tiller Number

作　　者：姚远[1] 孟金慧 李向阳 YAO Yuan;MENG Jin-hui;LI Xiang-yang(College of Physical Science and Technology,Central China Normal University,Wuhan Hubei 430079)

机构地区：[1]华中师范大学物理科学与技术学院

出　　处：《现代农业科技》2019年第11期6-8,共3页Modern Agricultural Science and Technology

基　　金：中央高校基本科研资助项目(CCNU18CG007,CCNU18TS030)

摘　　要：根据大豆植株分杈个数可以预估大豆的产量。为了满足现代农业预测农产品产量的需要,本文提出一种大豆植株分杈数自动提取算法,即首先将采集到的大豆植株图片进行灰度变换、滤波、阈值分割得到二值图像,再进行形态学中的闭运算操作得到大豆植株的轮廓,然后基于Zhang并行快速细化算法提取骨架,最后借助改进的角点检测算法对大豆植株的所有分杈点进行标记并自动统计分杈数,仿真结果与大豆植株实际分杈点一致。The number of soybean plants can predict the yield of soybean. In order to meet the needs of prediction for the agricultural production in modern agriculture,this paper proposed an automatic extraction algorithm for soybean plant tiller number.Firstly,the collected soybean plants were subjected to gradation transformation,filtering and threshold segmentation to obtain a binary image;secondly,the closed operation in morphology was performed to obtain the outline of the soybean plant,and the skeleton was extracted based on the Zhang parallel rapid refinement algorithm;thirdly,all the tillers of soybean plants were marked and the number of branches automatically counted by using the improved corner detection algorithm.The simulation results are consistent with the actual tillering points of soybean plants.

关 键 词：大豆植株 分杈数提取 角点检测 快速细化 

分 类 号：S565.1[农业科学—作物学]