激光与光电子学进展, 2016, 53 (10): 102801, 网络出版: 2016-10-12   

人工神经网络计算大气点扩展函数

Computing the Atmospheric Point Spread Function by Artificial Neural Networks
作者单位
1 中国科学院国家空间科学中心复杂航天系统电子信息技术重点实验室, 北京 100190
2 中国科学院大学, 北京 100049
摘要
大气点扩展函数(PSF)是开展光学遥感邻近效应研究和校正的有效方法。基于蒙特卡罗模拟获得的大气PSF,设计足够多带有Sigmoid函数的隐藏神经元和线性输出神经元的两层前馈神经网络,采用Levenberg-Marquardt反向传播算法,获得了大气、光谱和观测几何等输入参数与大气PSF之间的关系。模拟结果证明该方法能够在相对较短的时间内,以95%的计算精度产生预期的大气PSF的近似值。
Abstract
Atmospheric point spread function (PSF) is an effective research and correction method for the adjacency effect of the optical remote sensing. Based on the atmospheric PSF acquired by Monte Carlo simulation, a two-layer feed-forward neural network which has enough hidden neurons with Sigmoid function and linear output neurons is designed and implemented. By means of Levenberg-Marquardt back-propagation algorithm, the relationship between the atmospheric PSF and its influence factors, such as atmosphere condition, spectral range and observation geometry is obtained. The results obtained show that our neural network can estimate the atmosphere PSF with 95% accuracy within relatively short time.
参考文献

[1] 李海巍, 张浩, 陈正超, 等. 去除大气邻近效应影响的遥感图像MTF计算方法[J]. 光学学报, 2015, 35(3): 0328002.

    Li Haiwei, Zhang Hao, Chen Zhengchao, et al. MTF computing method of remote sensing image after removing the effects of atmospheric adjacency effect[J]. Acta Optica Sinica, 2015, 35(3): 0328002.

[2] 王倩, 陈雪, 马建文, 等. 基于SHDOM经验方程和基于同步实测光谱数据的遥感影像邻近效应校正算法对比研究[J]. 光学学报, 2010, 30(11): 3342-3348.

    Wang Qian, Chen Xue, Ma Jianwen, et al. A comparative study of two remote sensing image adjacency effect correction algorithms base on SHDOM empirical equation and synchronized measured spectral data[J]. Acta Optica Sinica, 2010, 30(11): 3342-3348.

[3] Richter R, Bachmann M, Dorigo W, et al. Influence of the adjacency effect on ground reflectance measurements[J]. IEEE Geoscience & Remote Sensing Letters, 2006, 3(4): 565-569.

[4] Lyapustin A I, Kaufman Y J. Role of adjacency effect in the remote sensing of aerosol[J]. Journal of Geophysical Research Atmospheres, 2001, 106(D11): 11909-11916.

[5] Reinersman P N, Carder K L. Monte Carlo simulation of the atmospheric point-spread function with an application to correction for the adjacency effect[J]. Applied Optics, 1995, 34(21): 4453-4471.

[6] Jia G R, Zhao H J, Li N. Simulation of hyperspectral scene with full adjacency effect[C]. IEEE International Geoscience and Remote Sensing Symposium, 2008(3): III724-III727.

[7] 杨贵军, 柳钦火, 刘强, 等. 高分辨率中红外遥感(3~5 μm)成像模拟中邻近效应分析[J]. 红外与毫米波学报, 2008, 27(3): 233-240.

    Yang Guijun, Liu Qinhuo, Liu Qiang, et al. Adjacency effect analysis in imaging simulation of high-resolution mid-infrared (3~5 μm) remote sensing[J]. Journal of Infrared and Millimeter Waves, 2008, 27(3): 233-240.

[8] 刘成玉, 陈春, 张树清, 等. ETM图像大气邻近效应校正[J]. 光谱学与光谱分析, 2010, 30(9): 2529-2532.

    Liu Chengyu, Chen Chun, Zhang Shuqing, et al. Atmospheric adjacency effect correction of ETM images[J]. Spectroscopy & Spectral Analysis, 2010, 30(9): 2529-2532.

[9] 李宏顺, 刘伟. 用逆向蒙特卡罗法分析卫星遥感中的邻近效应[J]. 华中科技大学学报(自然科学版), 2004, 32(11): 1-3.

    Li Hongshun, Liu Wei. Analysis of the adjacency effect in satellite remote sensing by using backward Monte Carlo method[J]. Journal of Huazhong University of Science & Technology (Nature Science Edition), 2004, 32(11): 1-3.

[10] 马晓珊, 郭晓勇, 孟新, 等. 光学遥感对地成像过程中的邻近效应模拟分析[J]. 红外与毫米波学报, 2015, 34(2): 250-256.

    Ma Xiaoshan, Guo Xiaoyong, Meng Xin, et al. Simulation and analysis of the adjacency effect in earth-imaging process of the optical remote sensing[J]. Journal of Infrared and Millimeter Waves, 2015, 34(2): 250-256.

[11] Modest M F. Backward Monte Carlo simulations in radiative heat transfer[J]. Journal of Heat Transfer, 2001, 125(1): 57-62.

[12] 徐希孺, 王平荣. 用蒙特-卡罗方法计算大气点扩散函数[J]. 遥感学报, 1999, 3(4): 268-278.

    Xu Xiru, Wang Pingrong. Computing atmospheric point spread function by Monte-Carlo method[J]. Journal of Remote Sensing, 1999, 3(4): 268-278.

[13] Cong B. Encoding neural networks to compute the atmospheric point spread function[C]. The International Conference on Information Technology: Coding and Computing, 2000: 344-349.

[14] 黄丽. BP神经网络算法改进及应用研究[D]. 重庆: 重庆师范大学, 2008.

    Huang Li. BP neural algorithm improvement and application research[D]. Chongqing: Chong Qing Normal University, 2008.

[15] Hagan M T, Menhaj M B. Training feed forward networks with the Marquardt algorithm[J]. IEEE Transactions on Neural Networks, 1994, 5(6): 989-993.

王海东, 马晓珊, 杨震, 李立钢. 人工神经网络计算大气点扩展函数[J]. 激光与光电子学进展, 2016, 53(10): 102801. Wang Haidong, Ma Xiaoshan, Yang Zhen, Li Ligang. Computing the Atmospheric Point Spread Function by Artificial Neural Networks[J]. Laser & Optoelectronics Progress, 2016, 53(10): 102801.

本文已被 2 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!