粒子图像测速互相关中亚像素位移定位的改进方法  

Error Compensation for Sub-Pixel Displacement Estimation in Cross-Correlation Particle Image Velocimetry(PIV)

作　　者：陈波[1] 李万平[1] 

机构地区：[1]华中科技大学土木工程与力学学院,武汉430074

出　　处：《计算机辅助设计与图形学学报》2011年第11期1896-1901,共6页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(10372033)

摘　　要：通过分析粒子图像测速技术中互相关算法位移偏小的原因和误差变化规律,提出一种误差补偿修正的方法.首先计算出2个分别大于和小于真实亚像素位移的相关值平面,再对这2个相关值平面进行加权平均,通过分析误差变化规律得到加权系数;再由三点高斯插值计算加权平均后的相关值平面,得到较为精确的亚像素位移.在模拟均匀流场、Oseen涡流场以及标准射流场下进行实验的结果表明,该方法不但能提高均匀流场的计算精度,也能提高具有较大速度梯度流场的精度,具有较好的适用性.Analyzing the cause and the relationship between displacement and bias error in the evaluation of PIV recordings with the correlation-based interrogation algorithm, an error compensation method is presented in this paper. In our proposed algorithm, two correlation planes are obtain first, one with values higher and the another with values smaller than the true sub-pixel displacement. The two correlation planes are then averaged with weights, which is obtained through analyzing the error distribution. Finally, three-point Gaussian interpolation in the new correlation plane provides more accurate sub-pixel displacement. The assessment of synthetic image.s in the uniform flow, Oseen vortex flow and standard target flow shows that the proposed method can achieve higher evaluation accuracy not only for uniform flows, but also for flows with large velocity magnitude and gradients.

关 键 词：粒子图像测速 互相关 修正算法 偏移误差 

分 类 号：O351.3[理学—流体力学] TH73[理学—力学]