基于深度学习的机载遥感通信系统自适应光学波前校正技术
Adaptive optics wavefront correction technology for airborne remote sensing communication system based on deep learning
仲崇丽 1路龙宾 2刘华2
作者信息
- 1. 西安明德理工学院信息工程学院,西安 710100
- 2. 西安邮电大学,西安 710100
- 折叠
摘要
自适应光学波前校正过程易受复杂背景、光照强度、噪声信号等问题的干扰,导致校正的效果降低.为了解决上述问题,提出基于深度学习的机载遥感通信系统自适应光学波前校正技术.通过相位差法实现自适应光学波前的探测,采用小波变换算法剔除其中的噪声,避免噪声对校正过程产生干扰.根据深度神经网络的预测与自学习能力构建动力学模型网络、策略网络与决策单元,通过与校正阈值的对比,完成机载遥感通信系统自适应光学波前的校正.实验结果表明,所提方法的斯特列尔比接近1,且校正时间短、校正效果好.
Abstract
The wavefront correction of adaptive optics is vulnerable to the interference of complex background,light intensity,noise signal and other problems,resulting in reduced correction effect.In order to solve these prob-lems,a adaptive optics wavefront correction technique based on deep learning for airborne remote sensing communica-tion system is proposed.The adaptive optics wavefront is detected by the phase difference method,and the noise is e-liminated by the wavelet transform algorithm to avoid the interference of noise in the correction process.According to the prediction and self-learning ability of the deep neural network,a dynamic model network,a strategy network and a decision unit are constructed.By comparing with the correction threshold,the adaptive optics wavefront of the air-borne remote sensing communication system is corrected.The experimental results show that the proposed method has a Stellerian ratio close to 1,and has a short correction time and good correction effect.
关键词
波前畸变函数/离散小波变换/深度神经网络/最佳校正策略/校正阈值Key words
wavefront distortion function/discrete wavelet transform/deep neural network/best calibration strat-egy/correction threshold引用本文复制引用
基金项目
陕西省科技厅科技成果转移与推广计划(2020CGXNG-027)
出版年
2024
NETL
NSTL
万方数据