基于压缩感知的双向阈值匹配追踪算法  

Ovonic Threshold Matching Pursuit for Sparse Signal Reconstruction Based on Compressed Sensing

作　　者：黄宏伟[1] 谢正光[1] 蒋小燕[1] 蔡旭[1] 

机构地区：[1]南通大学电子信息学院,江苏南通226019

出　　处：《电视技术》2015年第10期5-10,共6页Video Engineering

基　　金：国家自然科学基金面上项目(61171077)

摘　　要：最近提出的前向后向算法(Forward-backward Pursuit,FBP)因为重构精度较高受到人们更多关注。但是FBP算法没有考虑到当前迭代残差信号的变化,每次迭代选取的原子和删减原子的数目是固定的。鉴于此,提出了双向阈值匹配追踪算法(Ovonic Threshold Matching Pursuit,OTMP)。OTMP前向原子选择过程通过限制等距性质(RIP)和残差的条件选出部分新增加原子,在回溯过程中通过当前迭代的重构水平剔除可能错误的原子。实验表明,在一定条件下OTMP时间复杂度和正交匹配追踪算法(Orthogonal Matching Pursuit,OMP),子空间追踪算法(Subspace Pursuit,SP)相当,重构精度明显高于SP,FBP算法和其他几种贪婪算法。Due to high accuracy in signal reconstruction, Forward-backward Pursuit algorithm （FBP） has received more attention. However, the change of residual signal is not considered, and the number of atoms selected in each iteration is a constant. As a result, Ovonic Threshold Matching Pursuit （OTMP） is put up. On the one hand, OTMP tries to pick out part new atoms by Restricted Isometry Property and residual eondition in the forward atom selection process. On the other hand, based on reconstruction level of current iteration, some atoms which are probably wrong are deleted. The experimental result shows that under certain condition, time complexity of OTMP is comparable with OMP, SP. Meanwhile, the reconstruction accuracy of OTMP surpasses SP, FBP and other greedy algorithms obviously.

关 键 词：压缩感知 贪婪算法 原子 回溯 子空间追踪算法 前向后向算法 

分 类 号：TN911.73[电子电信—通信与信息系统]