摘要
为了实现对飞秒光丝内部空间结构特征的精细化描述,通过对光丝诱导形成超声信号的正向传播过程进行精细化模拟,然后采用通用反投影算法(UBP)、延迟叠加算法(DAS)和超优光声非负重构算法(SPANNER)等多种光声层析图像重建算法进行反向重建,理论验证了利用多元线性阵列探测的方式重建飞秒单丝和多丝轴向r-z截面图像的可行性。结果表明,当探测距离为3 mm时,单丝和多丝诱导形成的超声信号最大频率约为5 MHz;光声层析法能够较为准确地实现对单丝位置、r-z截面轮廓等信息的反演,但是不同图像重建算法重建效果差异较大。UBP重建算法对单丝的重建存在较为明显的伪影现象;DAS重建算法由于受到“有限孔径效应”的影响,高估了光丝的直径;SPANNER重建算法由于使用最优理论来改进非线性共轭梯度算子,实现了非负性和各向异性总变分正则化,可有效避免噪声干扰,因而对多丝图像的重建效果最好。该研究结果对于揭示光丝结构特征和促进基于光丝的大气应用研究具有一定的参考价值。
To finely describe the internal spatial structure characteristics of femtosecond laser filaments,the forward propagation process of ultrasound induced by optical filaments is first simulated in fine detail,and then different photoacoustic tomography image reconstruction algorithms,such as the universal back projection algorithm(UBP),delay and sum(DAS)and superiorized photo-acoustic nonnegative reconstruction algorithm(SPANNER),are used to perform reverse reconstruction image of filaments.The results theoretically verify the feasibility of using a multiple linear array detection to reconstruct the axial r-z section of a single filament and multiple filaments.The results show that the maximum frequency of the ultrasonic signal induced by a single filament and multiple filaments at a detection distance of 3 mm is approximately 5 MHz.Photoacoustic tomography can accurately retrieve the single filament position and r-z section profile,but the reconstruction effects of different image reconstruction algorithms are quite different.The UBP algorithm has obvious artifacts in the reconstruction of filaments;the DAS algorithm overestimates the diameter of light filaments due to the"finite aperture effect";the SPANNER has the best effect on multiwire image reconstruction because it uses optimal theory to improve the nonlinear conjugate gradient operator and realize nonnegative and anisotropic total variational regularization,which can effectively avoid noise interference.The results of this study have certain reference value for revealing the structural characteristics of laser filaments and promoting the laser filamentation based atmospheric application research.
作者
曾庆伟
刘磊
胡帅
李书磊
陈鸣
Zeng Qingwei;Liu Lei;Hu Shuai;Li Shulei;Chen Ming(College of Meteorology and Oceanography,National University of Defense Technology,Changsha 410073,China;31110 Troops of PLA,Nanjing 211101,China)
出处
《红外与激光工程》
EI
CSCD
北大核心
2022年第8期178-186,共9页
Infrared and Laser Engineering
基金
国家自然科学基金(42105176)
湖南省自然科学基金(2020JJ4662,2021JJ40664,2021 JJ10047)。
关键词
飞秒激光成丝
光声层析
线性阵列探测
图像重建算法
femtosecond laser filamentation
photoacoustic tomography
linear array detection
image reconstruction algorithm
