电子学报 ›› 2020, Vol. 48 ›› Issue (11): 2208-2214.DOI: 10.3969/j.issn.0372-2112.2020.11.016

所属专题: 压缩感知

• 学术论文 • 上一篇    下一篇

对比源框架下的多任务贝叶斯压缩感知微波成像方法

张清河, 于士奇, 时李萍, 张士惠   

  1. 三峡大学计算机与信息学院, 湖北宜昌 443002
  • 收稿日期:2019-10-08 修回日期:2020-05-05 出版日期:2020-11-25 发布日期:2020-11-25
  • 通讯作者: 张清河
  • 作者简介:于士奇 男,1993年生于河南濮阳,三峡大学计算机与信息学院硕士研究生.研究方向为电磁散射与逆散射、微波成像等.E-mail:549749310@qq.com;时李萍 女,1994年生,三峡大学计算机与信息学院硕士研究生.研究方向为机器学习方法、天线设计与综合等;张士惠 女,1994年生,三峡大学计算机与信息学院硕士研究生.研究方向为阵列信号处理.
  • 基金资助:
    国家自然科学基金(No.61771008)

Microwave Imaging by Multitask Bayesian Compressed Sensing Within Contrast Source Framework

ZHANG Qing-he, YU Shi-qi, SHI Li-ping, ZHANG Shi-hui   

  1. School of Computer and Information, China Three Gorges University, Yichang, Hubei 443002, China
  • Received:2019-10-08 Revised:2020-05-05 Online:2020-11-25 Published:2020-11-25

摘要: 针对强散射体微波成像困难问题,本文提出了一种对比源框架下的基于拉普拉斯先验的多任务贝叶斯压缩感知方法,实现了稀疏强散射体的微波成像.在对比源框架下,基于"数据"积分方程并对成像区域网格离散建立稀疏感知模型,前向问题采用矩量法数值模拟;构造基于拉普拉斯先验的贝叶斯压缩感知分层模型;在多入射波情况下,利用多任务贝叶斯压缩感知方法对对比源进行优化求解;最后利用"状态方程"实现了目标函数的重构.本文在考虑噪声情况下,通过对多像素单目标、不均匀目标、多目标的微波成像数值模拟,并与共轭梯度方法、一阶Born近似框架下的多任务贝叶斯压缩感知方法的重构结果比较,验证了本文方法的有效性和鲁棒性.

关键词: 微波成像, 对比源, 共轭梯度, 一阶Born近似, 拉普拉斯先验, 多任务贝叶斯压缩感知

Abstract: Aiming at the difficulty of microwave imaging of strong scatterers,a multi-task Bayesian compressed sensing method based on Laplacian priori is proposed,which realizes microwave imaging of sparse strong scatterers.In the framework of contrast sources,sparse sensing model is established based on the "data" integral equation and the mesh discretization in the imaging region.The forward problem is simulated by the moment method; a Bayesian compressed sensing hierarchical model based on Laplacian priori is constructed; and in the case of multi-incident waves,multi-task Bayesian compressed sensing method is used to optimize the contrast source.Finally,the objective function is reconstructed by using the "state equation".Considering the influence of noise,Through the numerical simulation of multi-pixel single target,non-uniform single target and multi-target microwave imaging,and compared with the reconstructed results of conjugate gradient method and multi-task Bayesian compressed sensing method in the first-order Born approximation framework,which verifies the effectiveness and robustness of the proposed algorithm.

Key words: microwave imaging, contrast source, conjugate gradient, first order Born approximation, Laplacian priori, multi-task Bayesian compressed sensing

中图分类号: