基于高斯过程回归的距离选通成像系统工作参数的在线优化
|
摘要
通过调整模块的工作参数,提出了一种对距离选通成像系统性能进行在线优化的方法。将眼图参数视为一个随系统可调参数变化的随机变量,采用高斯过程回归方法拟合此变化关系,并在学习过程中引入参数优化步骤,从而在更快速地从高维参数空间中学习到随机过程变化特征的同时优化系统参数。实验结果表明:所提方法可在线优化系统参数配置,提高距离分辨能力,揭示模块参数配置对距离分辨能力的影响,可为成像系统的设计提供一定依据。
An online optimization method for improving the performance of a range-gated imaging system is introduced by means of adaptively adjusting the operation parameters of modules. The eye pattern parameter is treated as a random variable varying with the tunable parameters of the system, and the Gaussian process regression method is applied for fitting this variation relationship. In addition, the parameter optimization procedure is also involved in the learning process. Thus the variable characteristic of a random process in the high dimensional parameter space is learnt rapidly, and simultaneously the system parameters are optimized. The experimental results show that the proposed method can be used to optimize the system parameter configuration online and improve the range resolution. The dependence of the range resolution on the configuration parameters of modules is illustrated, which provides a basis for the design of an imaging system.
An online optimization method for improving the performance of a range-gated imaging system is introduced by means of adaptively adjusting the operation parameters of modules. The eye pattern parameter is treated as a random variable varying with the tunable parameters of the system, and the Gaussian process regression method is applied for fitting this variation relationship. In addition, the parameter optimization procedure is also involved in the learning process. Thus the variable characteristic of a random process in the high dimensional parameter space is learnt rapidly, and simultaneously the system parameters are optimized. The experimental results show that the proposed method can be used to optimize the system parameter configuration online and improve the range resolution. The dependence of the range resolution on the configuration parameters of modules is illustrated, which provides a basis for the design of an imaging system.
引文
[1] Steinvall O,Andersson P,Elmqvist M,et al.Overview of range gated imaging at FOI[J].Proceedings of SPIE,2007,6542:654216.
[2] Tan C S,Sluzek A,Seet G,et al.Three-dimensional machine vision using gated imaging system:a numerical analysis[C].IEEE Conference on Robotics,Automation and Mechatronics,2006:1-6.
[3] Busck J,Heiselberg H.Gated viewing and high-accuracy three-dimensional laser radar[J].Applied Optics,2004,43(24):4705-4710.
[4] Huang Y W,Wang X,Jin W Q,et al.Temporal model of underwater laser range-gated imaging and pulse stretching[J].Acta Optica Sinica,2010,30(11):3177-3183.黄有为,王霞,金伟其,等.水下激光距离选通成像与脉冲展宽的时序模型[J].光学学报,2010,30(11):3177-3183.
[5] Chua S Y,Wang X,Guo N Q,et al.Range compensation for accurate 3D imaging system[J].Applied Optics,2016,55(1):153-158.
[6] Sun J,Zhang X H,Ge W L,et al.Relation between imaging quality and gate-control signal of underwater range-gated imaging system[J].Acta Optica Sinica,2009,29(8):2185-2190.孙健,张晓晖,葛卫龙,等.距离选通激光水下成像系统的门控信号对图像质量的影响[J].光学学报,2009,29(8):2185-2190.
[7] Li X L,Chen Y H,Yu F,et al.Comparison and analysis of inversion models for water optical property parameters by ocean lidar[J].Acta Optica Sinica,2017,37(10):1001005.李晓龙,陈永华,于非,等.海洋激光雷达水体光学特性参数反演模型对比及分析[J].光学学报,2017,37(10):1001005.
[8] Yan Z,Anjum M R,Wang X W.Influence factor analysis for 3D imaging laser radar range profile[J].Middle-East Journal of Scientific Research,2013,17(2):142-147.
[9] Kajava T T,Gaeta A L.Q switching of a diode-pumped Nd\:YAG laser with GaAs[J].Optics Letters,1996,21(16):1244-1247.
[10] Pan J S.Microchannel plates and its main characteristics[J].Journal of Applied Optics,2004,25(5):25-29.潘京生.微通道板及其主要特征性能[J].应用光学,2004,25(5):25-29.
[11] Laurenzis M.Evaluation metrics for range-gated active imaging systems using a Lissajous-type eye pattern[J].Applied Optics,2010,49(12):2271-2276.
[12] Laurenzis M,Christnacher F,Monnin,et al.3D range-gated imaging in scattering environments[J].Proceedings of SPIE,2010,7684:768406.
[13] Laurenzis M,Christnacher F,Bacher E,et al.New approaches of three-dimensional range-gated imaging in scattering environments[J].Proceedings of SPIE,2010,8186:818603.
[14] Rasmussen C E,Williams C K I.Gaussian processes for machine learning[M].Massachusetts:MIT Press,2006:105-112.
[15] MacCarone A,McCarthy A,Ren X M,et al.Underwater depth imaging using time-correlated single-photon counting[J].Optics Express,2015,23(26):33911-33926.
[16] Wigley P B,Everitt P J,van den Hengel A,et al.Fast machine-learning online optimization of ultra-cold-atom experiments[J].Scientific Reports,2016,6:25890.
[2] Tan C S,Sluzek A,Seet G,et al.Three-dimensional machine vision using gated imaging system:a numerical analysis[C].IEEE Conference on Robotics,Automation and Mechatronics,2006:1-6.
[3] Busck J,Heiselberg H.Gated viewing and high-accuracy three-dimensional laser radar[J].Applied Optics,2004,43(24):4705-4710.
[4] Huang Y W,Wang X,Jin W Q,et al.Temporal model of underwater laser range-gated imaging and pulse stretching[J].Acta Optica Sinica,2010,30(11):3177-3183.黄有为,王霞,金伟其,等.水下激光距离选通成像与脉冲展宽的时序模型[J].光学学报,2010,30(11):3177-3183.
[5] Chua S Y,Wang X,Guo N Q,et al.Range compensation for accurate 3D imaging system[J].Applied Optics,2016,55(1):153-158.
[6] Sun J,Zhang X H,Ge W L,et al.Relation between imaging quality and gate-control signal of underwater range-gated imaging system[J].Acta Optica Sinica,2009,29(8):2185-2190.孙健,张晓晖,葛卫龙,等.距离选通激光水下成像系统的门控信号对图像质量的影响[J].光学学报,2009,29(8):2185-2190.
[7] Li X L,Chen Y H,Yu F,et al.Comparison and analysis of inversion models for water optical property parameters by ocean lidar[J].Acta Optica Sinica,2017,37(10):1001005.李晓龙,陈永华,于非,等.海洋激光雷达水体光学特性参数反演模型对比及分析[J].光学学报,2017,37(10):1001005.
[8] Yan Z,Anjum M R,Wang X W.Influence factor analysis for 3D imaging laser radar range profile[J].Middle-East Journal of Scientific Research,2013,17(2):142-147.
[9] Kajava T T,Gaeta A L.Q switching of a diode-pumped Nd\:YAG laser with GaAs[J].Optics Letters,1996,21(16):1244-1247.
[10] Pan J S.Microchannel plates and its main characteristics[J].Journal of Applied Optics,2004,25(5):25-29.潘京生.微通道板及其主要特征性能[J].应用光学,2004,25(5):25-29.
[11] Laurenzis M.Evaluation metrics for range-gated active imaging systems using a Lissajous-type eye pattern[J].Applied Optics,2010,49(12):2271-2276.
[12] Laurenzis M,Christnacher F,Monnin,et al.3D range-gated imaging in scattering environments[J].Proceedings of SPIE,2010,7684:768406.
[13] Laurenzis M,Christnacher F,Bacher E,et al.New approaches of three-dimensional range-gated imaging in scattering environments[J].Proceedings of SPIE,2010,8186:818603.
[14] Rasmussen C E,Williams C K I.Gaussian processes for machine learning[M].Massachusetts:MIT Press,2006:105-112.
[15] MacCarone A,McCarthy A,Ren X M,et al.Underwater depth imaging using time-correlated single-photon counting[J].Optics Express,2015,23(26):33911-33926.
[16] Wigley P B,Everitt P J,van den Hengel A,et al.Fast machine-learning online optimization of ultra-cold-atom experiments[J].Scientific Reports,2016,6:25890.