基于神经网络的全天时天文导航图像去噪方法  

Neural Network-Based Noise Suppression Algorithm for Star Images Captured During Daylight Hours

作　　者：刘宇宸 赵春晖[1] 徐卿[1] Liu Yuchen;Zhao Chunhui;Xu Qing(Beijing Institute of Control Engineering,China Academy of Space Technology,Beijing 100190,China)

机构地区：[1]中国空间技术研究院北京控制工程研究所

出　　处：《光学学报》2019年第6期103-110,共8页Acta Optica Sinica

基　　金：国家重大仪器设备开发专项(2013YQ310799)

摘　　要：全天时天文导航图像是在大气层内白天的条件下拍摄,因此图像具有强背景,低信噪比等特点,传统星点提取算法对图像星点的提取效果较差。为提高星点识别率,提出一种较准确的全天时天文导航图像模拟方法,并基于模拟星图训练了一种可加入图像降采样结构的卷积神经网络,有效抑制了星图噪声,并提高了星点信噪比。实验结果表明:本文方法得到的峰值信噪比平均提高了11.28 dB;在效果相同的条件下,本文方法的平均处理时间仅为0.2 s,远少于传统神经网络方法的处理时间。利用真实星图对网络进行测试,发现本文方法对星点信噪比的提升效果较常用算法提升了88.9倍。Typically, star images captured in the atmosphere during daylight hours have a strong background and low signal-to-noise ratio(SNR), which makes it difficult for traditional algorithms to extract the star from the images. To improve the recognition rate, we propose an accurate method for simulating star images and train a deep convolutional neural network with a downsampling layer using the simulated images. The trained network can denoise and enhance the star images. Experimental results demonstrate that the proposed method improves the peak SNR by 11.28 dB within an average runtime of 0.2 s, which is significantly less than that of a traditional neural network. In addition, we test the proposed method on the trained network using real star images and find that the improved SNR is 88.9 times greater than that of the existing methods.

关 键 词：图像处理 卷积神经网络 全天时星敏感器 残差网络 降采样层 星图模拟 噪声抑制 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TN215[自动化与计算机技术—控制科学与工程]