基于改进梯度法的数字图像相关亚像素位移求解算法  

Digital image correlation sub-pixel displacement solving algorithm based on improved gradient method

作　　者：董一 王桂荣 洪亮[2] DONG Yi;WANG Guirong;HONG Liang(College of Mechanical and Electrical Engineering,China Jiliang University,Hangzhou 310018,China;College of Electronics and Information,Communication University of Zhejiang,Hangzhou 310018,China)

机构地区：[1]中国计量大学机电工程学院,浙江杭洲310018 [2]浙江传媒学院电子信息学院,浙江杭州310018

出　　处：《现代电子技术》2022年第17期29-34,共6页Modern Electronics Technique

基　　金：国家自然科学基金项目(61671404)。

摘　　要：在数字散斑相关法中,传统梯度法搜索的亚像素测量精度已无法满足实际工程中的要求。针对此问题,提出了一种基于插值和梯度的亚像素位移测量混合算法。该算法在已知整像素配准点的基础上,先利用双三次插值法粗匹配出精度为0.2 pixel的亚像素配准点,再通过梯度法匹配得到更高精度的亚像素配准点,避免了梯度法在一阶泰勒公式展开时的舍弃量过大问题,在不提升摄像机分辨率的情况下,有效地提高了测量精度及计算效率。通过仿真实验测试了该算法的性能,并与曲面拟合法、插值法及梯度法进行对比,显示该算法的精度可达0.01 pixel,高于另外三种算法的精度。此外通过刚体平移实验检验该算法在实际应用中的效果,实验结果显示,所提算法的位移精度可达0.001 mm,误差在0~3%之间,计算时间为0.027 s。综上所述,所提出的亚像素位移测量混合算法的精度较高,计算效率也满足工程应用的要求。In the digital speckle correlation method,the sub-pixel measurement accuracy searched by the traditional gradient method can no longer meet the requirements of actual engineering,so a sub-pixel displacement measurement hybrid algorithm based on interpolation and gradient is proposed.On the basis of the known integer pixel registration points,the bicubic interpolation method is used to roughly match the sub-pixel registration points with an accuracy of 0.2 pixel,and then by the gradient matching,the sub-pixel registration points with higher accuracy are obtained,which avoids excessive discarding of the gradient method when the first-order Taylor formula is expanded,and effectively improves the measurement accuracy and calculation efficiency without improving the resolution of camera.The performance of this algorithm was tested in simulation experiments.The proposed algorithm is contrasted with surface fitting method,interpolation method and gradient method.The results show that the accuracy of this algorithm can reach 0.01 pixel,which is higher than that of the other three algorithms.In addition,the effect of the algorithm in practical applications has been verified by rigid body translation experiments.The experimental results show that the displacement accuracy of this algorithm can reach 0.001 mm,its error is within 0~3% and its calculation duration is 0.027 s.In summary,the sub-pixel displacement measurement hybrid algorithm proposed has high accuracy,and its calculation efficiency can meet the requirements of engineering applications.

关 键 词：亚像素位移 数字图像 改进梯度法 数字散斑相关法 像素配准点 双三次插值法 粗匹配 曲面拟合法 

分 类 号：TN911.73-34[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]