基于模型选择的模式波前重构算法研究  

Zernike modal wavefront reconstruction algorithm based on model selection

作　　者：谢文科[1] 高穹[1] 马浩统[1] 魏文俭[1] 江文杰[1] 

机构地区：[1]国防科学技术大学光电科学与工程学院,长沙410073

出　　处：《物理学报》2015年第14期145-150,共6页Acta Physica Sinica

基　　金：中国科学院光束控制重点实验室基金(批准号:2014LBC004);国家自然科学基金(批准号:61008037;11404398;61205144);国防科学技术大学科研计划项目(批准号:JC 13-07-01)资助的课题~~

摘　　要：基于Zernike模式的波前重构算法通常忽略实际波前像差构成的差异,而用一定数量的低阶Zernike模式进行波前重构,导致模式混淆或耦合等问题,进而影响波前重构的精度.根据信息论中的最小描述长度准则对重构模型的阶数进行了选择,在此基础上应用非线性优化算法计算重构系数,并最终实现波前重构;对不同信噪比条件下振幅均匀分布入射光束的波前进行了重构.结果表明:该算法不但能够实现相对于现有算法相对较高的波前重构精度,并且具有优良的噪声适应性,体现了模型选择在模式法波前重构算法中的意义.In Zernike modal wavefront reconstruction algorithm, because of a certain number of the low Zernike modes is selected subjective for making up the reconstruction model, the modes confusion and modes coupling will produced, the accuracy reduction of wavefront reconstruction is deduced. According to the minimal description length principal, a principle can balance the model error against model size so as to prevent the model from overfitting. The reconstruction model is selected by top-down method, and Levenberg-Marquardt nonlinear optimization algorithm is applied to the solution of reconstruction coefficients, then the wavefronts reconstruction is realized. Under different noise conditions, the reconstruction algorithm is validated with the numerical simulation of the wavefront reconstruction of uniform amplitude incidence beam, the results indicate： Zernike modal wavefront reconstruction algorithm based on the model selection can improve the wavefront reconstruction accuracy, and algorithm possesses the property of resistance to noise.

关 键 词：波前重构 模型选择 最小描述长度 非线性优化 

分 类 号：O437[机械工程—光学工程]