基于动态区域提取的模式复原算法  

Modal Reconstruction Algorithm Based on Dynamic Region Extraction

作　　者：文良华 杨平[1,2] 王帅[1,2] 陈善球[1,2] 刘文劲[1,2] 许冰[1,2] 

机构地区：[1]中国科学院自适应光学重点实验室,四川成都610209 [2]中国科学院光电技术研究所,四川成都610209 [3]中国科学院大学,北京100049 [4]宜宾学院物理与电子工程学院,四川宜宾644007

出　　处：《激光与光电子学进展》2017年第11期35-42,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(60978049);中国科学院创新基金(CXJJ-16M208);中国科学院青年创新促进会项目(2012280);中国科学院卓越青年科学家项目

摘　　要：追踪了由远场光电探测器采样宽度限制引入的量化噪声在算法实现过程中的传递,分析了其对算法在波前像差校正中的效果和收敛速度产生影响的原因。根据斯特列尔比值(SR)的变化,提出了一种基于动态区域提取的模式复原算法,并利用18阶和33阶Zernike多项式模拟得到的符合Kolmogrove大气湍流功率谱的波前对该算法进行数值计算。计算结果表明:采用动态区域提取的复原算法校正波前像差,在12位相机采样宽度和33阶初始像差情况下,算法经31次迭代后收敛,波前复原残差均方根为0.058λ(λ为波长),SR达0.9以上。该算法减小了量化噪声的影响,无波前传感自适应光学系统的收敛速度和校正效果得到显著提高。Transferring of quantization noise in algorithm implementation is tracked, which is caused by the finite sampling width of far field photodetector. The effect of quantization noise on wavefront aberration correction effect and convergence speed is analyzed. According to the changing of Strehl ratio （SR）, a modal reconstruction algorithm based on dynamic region extraction is presented. Numerical calculations are carried out with the wavefront which fits the Kolmogrove atmospheric turbulence power spectrum and is obtained by the simulation of 18- and 33- order Zernike terms. The results show that, under the condition of the camera sampling width of 12 bits and 33- order initial aberration, the SR is larger than 0.9, the root-mean-square value of wavefront recuperative residual is 0.058~ （）, is wavelength）, and the algorithm is converged after iteration for 31 times. The proposed algorithm greatly improves the correction performance and convergence speed of the wavefront sensorless adaptive optics system and reduces the effect of the quantization noise.

关 键 词：大气光学 自适应光学 量化噪声 动态区域提取 模式复原 

分 类 号：TP273.2[自动化与计算机技术—检测技术与自动化装置]