采用整体最小二乘法的条纹图配准方法  

Inference fringe image registration using total least square method

作　　者：穆治亚[1] 艾华[1] 樊孝贺 何昕[1] 何丁龙 韩冬松[2] 于国栋[3] 

机构地区：[1]中国科学院长春光学精密机械与物理研究所,吉林长春130033 [2]中国人民解放军防化研究院,北京102205 [3]白城兵器试验中心,吉林白城137001

出　　处：《中国光学》2016年第6期625-632,共8页Chinese Optics

基　　金：吉林省自然科学基金资助项目(No.201115124)~~

摘　　要：针对共光路菲索型动态干涉仪采集到的4幅条纹图的空间一致性问题,本文提出一种新的条纹图配准思路,将条纹图与图像配准在关联度上人为分开,搭建了专用的图像配准装置,避免将条纹与十字丝标志点混在一幅图像内而影响干涉仪的测量精度。首先通过本文搭建的条纹图配准装置对4台CMOS相机进行物理配准,然后利用整体最小二乘法对采集到的同一十字丝刻划板图像进行十字丝提取、交点计算以及旋转量计算,实现共光路菲索型动态干涉仪条纹图像的点点对应。最后通过试验对比验证,证明了本文算法的配准精度优于模板重心法的配准结果,互相关度达到96%以上。To solve the space coherence of four inference fringe images by dynamic interferometer with common light paths,we propose a new notion of inference fringe image registration. We detach the conjunction between the inference fringe image and the image registration,and erect the equipment for inference fringe image registration,avoiding the confusion between the inference fringe and the cross wire which can influence the measure precision of dynamic interferometer. First,we realize the physical registration of four CMOS cameras using the equipment for inference fringe image registration. Then,we go along the image registration for the four cross wire images of the depict board by cross wire extraction,intersection point caculation and rotution amount caculation using total least square method,and realize the parallelism between the pix and pix of the dynamic interferometer with common light paths. Last,experimental results show that the proposed registration algorithm can improve the accuracy of registration,which is superior to that of the method of bary center. Themethod proposed in this paper can achieve the cross-correlation value of over 96%.

关 键 词：共光路动态干涉仪 条纹图配准 整体最小二乘法 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]