基于双目立体视觉的纱线运动参数识别  

Motion parameter identification of yarn based on binocular stereo vision

作　　者：赵鹏翔 冯培[1,2] 欧建鑫 李姝佳[1,2] 王永兴 ZHAO Pengxiang;FENG Pei;OU Jianxin;LI Shujia;WANG Yongxing(College of Mechanical Engineering,Donghua University,Shanghai 201620,China;Engineering Research Center of Advanced Textile Machin-ery of Ministry of Education,Donghua University,Shanghai 201620,China)

机构地区：[1]东华大学机械工程学院,上海201620 [2]东华大学纺织装备教育部工程研究中心,上海201620

出　　处：《河南理工大学学报（自然科学版）》2023年第3期103-110,共8页Journal of Henan Polytechnic University（Natural Science）

基　　金：国家重点研发计划项目(2017YFB1304000)。

摘　　要：针对目前运用传统接触方法难以准确、无干扰测量纱线运动参数的问题,提出基于双目立体视觉的纱线运动参数识别方法。采用双目高速相机采集运动纱线图像,开发双目高速同步抓帧存图程序;利用高精度标定板进行双目标定;经滑动窗口和线面交点方法定位纱线测试点;对极线校正后严格行对准的像对使用块匹配、原始和改进半全局块匹配等立体匹配算法计算深度图,并采用视差原理求得纱线测试点空间位置坐标;结合存图时刻求得纱线运动参数。实验表明,本文方法得到的纱线运动参数中位移误差均值为0.132 mm,与实际情况吻合良好。Aiming at the problems of low accuracy and no interference of measuring yarn motion parameters for traditional contact method,a binocular stereo vision method was proposed:Images were collected by bin-ocular high-speed camera,stored by the developed software of binocular high-speed synchronous frame cap-ture;The binocular camera was calibrated by high precision calibration board;The yarn test point was de-tected by sliding window and intersection;After polar correction,the depth map was calculated by stereo matching algorithms of Block Matching,Semi-Global Block Matching and improved SGBM algorithm.The spatial location information of yarn test point was obtained by parallax principle.The yarn motion parameters were obtained with the three-dimensional coordinate and image storage time,the average error of displace-ment was 0.132 mm.The experimental results showed that the yarn motion parameters were in good agree-ment with the actual situation.

关 键 词：双目立体视觉 纱线运动参数 非接触测定 双目标定 极线校正 改进SGBM算法 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置] TS141.8[自动化与计算机技术—控制科学与工程]