基于计算机视觉的原木材积检测方法研究  

Research of log volume measuring method based on computer vision technology

作　　者：华蓓[1] 曹圃 黄汝维[1] HUA Bei;CAO Pu;HUANG Ruwei(School of Computer,Electronics and Information,GuangXi University,Nanning 530004,China)

机构地区：[1]广西大学计算机与电子信息学院,广西南宁530004

出　　处：《河南科技学院学报（自然科学版）》2022年第2期64-69,共6页Journal of Henan Institute of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金项目(62062009);广西科技重大专项(AA17204058-17);广西科技重大专项(桂科AA18118047-7)。

摘　　要：针对原木材积检测中存在的效率低下和人工成本高等问题,提出了基于计算机视觉技术的原木堆自动化检尺方案.方案首先采集原木堆两侧端面图像,进行包括灰度变换、二值化、孔洞填充以及边缘检测在内的一系列图像处理操作;然后对获得的处理结果,利用霍夫变换圆检测进行原木端面类圆形检测;最后,将检测得到原木两端检尺径数据排序整理,运用国家标准规定的原木材积检测公式计算得到原木材积.实验证明,算法的原木材积检测准确率可达到97%.Aiming at the problems of low efficiency and high labor cost in log volume measurement,an automatic measuring scheme of log piles based on computer vision technology is proposed.Firstly,the image of the end faces on both sides of the log pile is collected,and a series of image processing operations including gray-scale transformation,binarization,hole filling and edge detection are carried out.Then,based on the processing results,the Hough transform circle detection is used to measure the quasi circle of log end face.Finally,the measured log diameter data is sorted and the log volume is calculated by using the log volume measuring formula specified in the national standard.Experiments show that the log volume detection accuracy of the algorithm can reach 97%.

关 键 词：原木材积检测 计算机视觉 图像处理 霍夫变换 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]