正交匹配追踪算法的迭代残差重建方法
PDF下载 (4737)付 敏,王金平.正交匹配追踪算法的迭代残差重建方法[J].宁波大学学报(理工版),2021,34(1):50-54.DOI:
FU Min,WANG Jinping.An iterative residual reconstruction method of the orthogonal matching pursuit algorithm[J].Journal of Ningbo University(Natural Science & Engineering Edition),2021,34(1):50-54.DOI:
| Title: | An iterative residual reconstruction method of the orthogonal matching pursuit algorithm |
| 作者: | 付 敏, 王金平 |
| Author(s): | FU Min, WANG Jinping |
| 关键词: | 稀疏重构; OMP算法; 回溯 |
| Keywords: | sparse reconstruction; OMP algorithm; backtracking |
| 分类号: | O177.92 |
| 文献标识码: | A |
| 摘要: | 正交匹配追踪(Orthogonal Matching Pursuit, OMP)算法是一种重要的压缩感知重构算法. OMP算法在每次迭代中选择与当前残差最相关的原子. 针对每次迭代需要重新计算残差的问题, 本文考虑偶数次迭代下残差未知的情况. 首先, 研究了奇数次迭代的残差与下一次迭代的残差之间的关系, 得到了一种偶数次迭代时选择原子的标准. 然后, 引入一种回溯机制来处理前面所得的迭代结果, 这种机制通过剔除其中多余的原子来实现精确重建. 据此, 提出了可减少计算残差的改进型正交匹配追踪算法. |
| Abstract: | Orthogonal Matching Pursuit (OMP) is an important compressed sensing reconstruction algorithm. The OMP algorithm selects the atoms which are most associated to the current residual in each iteration. For the problem of recalculating the residual in each iteration, we consider the case where the residual of even number iterations is unknown. First, we study the relationship between the residuals of odd number iterations and the residuals of the next iteration followed by obtaining a benchmark for selecting atoms in even number iterations. Then we introduce a backtracking mechanism to process the results of previous iterations. The mechanism achieves the precise reconstruction by removing the extra atoms. An improved orthogonal matching pursuit algorithm is thus presented in this study. |
| 参考文献 /References: | [1] Donoho D L. Compressed sensing[J]. IEEE Transactions on Information Theory, 2006, 52(4):1289-1306. [2] Tropp J A, Gilbert A C. Signal recovery from random measurements via orthogonal matching pursuit[J]. IEEE Transactions on Information Theory, 2007, 53(12):4655-4666. [3] Needell D, Vershynin R. Signal recovery from incomplete and inaccurate measurements via regularized orthogonal matching pursuit[J]. IEEE Journal of Selected Topics in Signal Processing, 2010, 4(2):310-316. [4] Needell D, Tropp J A. CoSaMP: Iterative signal recovery from incomplete and inaccurate samples[J]. Applied and Computational Harmonic Analysis, 2009, 26(3):301-321. [5] Dai W, Milenkovic O. Subspace pursuit for compressive sensing signal reconstruction[J]. IEEE Transactions on Information Theory, 2009, 55(5):2230-2249. [6] Donoho D L, Tsaig Y, Drori I, et al. Sparse solution of underdetermined systems of linear equations by stagewise orthogonal matching pursuit[J]. IEEE Transactions on Information Theory, 2012, 58(2):1094-1121. [7] Do T T, Gan L, Nguyen N, et al. Sparsity adaptive matching pursuit algorithm for practical compressed sensing[C]. Asilonar Conference on Signals, Systems, and Computers, 2008:581-587. [8] 刘学文, 肖嵩, 王玲, 等. 迭代预测正交匹配追踪算法[J]. 信号处理, 2017, 33(2):178-184. [9] Baraniuk R G. Compressive sensing[J]. IEEE Signal Processing Magazine, 2007, 24(4):118-121. |
| 备注/Memo: | 收稿日期: 2020－06－01. 宁波大学学报（理工版）网址: http://journallg.nbu.edu.cn/基金项目: 国家自然科学基金（62071262）.第一作者: 付敏（1997－）, 女, 安徽合肥人, 在读硕士研究生, 主要研究方向: 积分变换与图像处理. E-mail: 2818391447@qq.com*通信作者: 王金平（1962－）, 男, 湖北武汉人, 博士/教授, 主要研究方向: 积分变换与图像处理. E-mail: wangjinping@nbu.edu.cn 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
