基于卷积神经网络的辐射计阵列近海亮温误差校正方法  

A convolutional neural network based method for repairing offshore bright temperature error of radiometer array

作　　者：梁爽[1] 靳榕[1] 李一楠[2] 窦昊锋 LIANG Shuang;JIN Rong;LI Yinan;DOU Haofeng(Research Center of 6G Mobile Communications,School of Cyber Science and Engineering,Huazhong University of Science and Technology,Wuhan 430074,China;China Academy of Space Technology(Xi’an),Xi’an 710000,China)

机构地区：[1]华中科技大学网络空间安全学院第六代移动通信研究中心,武汉430074 [2]中国空间技术研究院西安分院,西安710000

出　　处：《空间电子技术》2024年第6期39-49,共11页Space Electronic Technology

基　　金：民用航天预先研究项目(编号:D040202)。

摘　　要：对于星载综合孔径微波阵列辐射计而言,由于天线数量的限制,反演亮温图像时常常会出现吉布斯震荡现象,导致图像中的海陆边界变得模糊,难以与真实边界完全吻合。近年来,卷积神经网络在遥感图像处理领域取得了广泛的应用,为解决这一问题提供了新思路。然而,传统卷积神经网络的训练数据集大多基于光学图像生成,与星载综合孔径微波辐射计实际观测得到的海陆亮温图像存在较大差异,这不可避免地影响了模型的训练效果。针对上述问题,文章提出了一种通过正向模型仿真亮温观测图像生成的方法。该方法基于真实海陆信息,能够获取大量具有高度真实性的模拟综合孔径微波辐射计观测亮温图像。同时,文章还对卷积神经网络模型的结构进行了优化改进,有效防止了过拟合现象的发生。与传统的加窗法相比,文章所提出的基于卷积神经网络模型的近海亮温误差校正方法在保证图像分辨率、降低吉布斯震荡效果方面相较于传统方法在图像观感上提升明显。For spaceborne synthetic aperture microwave array radiometers,the limitation in the number of antennas often results in Gibbs oscillations when retrieving brightness temperature images.This causes the sea-land boundaries in the images to become blurred,making it difficult to fully align with the real boundaries.In recent years,convolutional neural networks(CNN)have been widely applied in the field of remote sensing image processing,providing new ideas for solving this problem.However,the training datasets for traditional CNN are mostly generated based on optical images,which differ significantly from the sea-land brightness temperature images obtained by spaceborne synthetic aperture microwave radiometers.This inevitably affects the training effectiveness of the models.To address the aforementioned issues,this paper first proposes a method for generating simulated brightness temperature observation images through a forward model.This method,based on real sea-land information,can obtain a large number of highly realistic simulated brightness temperature images observed by synthetic aperture microwave radiometers.Additionally,the paper optimizes and improves the structure of the CNN model to effectively prevent overfitting.Compared to traditional windowing methods,the proposed nearshore brightness temperature error correction method based on the CNN model significantly improves image resolution and reduces Gibbs oscillation effects,resulting in a noticeable enhancement in image quality.

关 键 词：吉布斯震荡 综合孔径亮温图像反演 亮温图像数据集 卷积神经网络 

分 类 号：V443[航空宇航科学与技术—飞行器设计] TP722[自动化与计算机技术—检测技术与自动化装置] TP183[自动化与计算机技术—控制科学与工程]