基于视觉的结构变形测量系统的实现  

Implementation of structure deformation measurement system based on vision

作　　者：林砺宗[1] 倪小鹏[1] 周罗善[1] 张东方[1] 曹成兵[1] 

机构地区：[1]华东理工大学机械及动力工程学院,上海200237

出　　处：《计算机工程与设计》2012年第5期1904-1907,共4页Computer Engineering and Design

摘　　要：为了测量自行车把动态加载变形量,辅助车把疲劳试验,提出了基于机器视觉的车把图像测量系统设计方法。考虑到零件表面不确定性,采用黏贴圆形标志于表面进行变形量测量,对采集的实时图像进行线性滤波等预处理,连续轮廓搜索函数搜寻待测目标,进行基于随机Hough变换的圆形标志检测,接着利用图像特征参数计算实时变形量。根据误差理论对测量结果进行数据处理与分析。实验结果表明该测量方法效果明显,测量精度可以达到0.03mm,高于常规测试方法的测试精度,能够达到车把加载变形高精度测量的要求。To measure dynamic loading deformation of a bicycle handle-bar and assist handlebar fatigue test,a design method of image measurement system of a bicycle handle-bar based on machine vision is presented.Firstly,considering the reflection on the uncertainty surfaces of parts,the study uses circular mark to locate the object profile for deformation measurements.Through the linear filtering preprocessing and other image preprocessing for real-time image on collection,continuous contour search function for searching test target and circular detection based on random hough transform（RHT）,the real-time deformation is measured through characteristics of images in any time.Then,the results of the measurement need to be data processing and analysis according to error theory.The test results prove that the method of digital image measurement is very effective,and the accuracy of the measurement is 0.03mm.It can ensure the accuracy is more than the accuracy of regular test method.At the same time,the high precision measurement require of loading deformation measurement of a bicycle handle-bar is met.

关 键 词：图像测量 自行车把 动态变形量 机器视觉 测量精度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]