摘要
压缩感知(CS)理论是在已知信号具有稀疏性或可压缩性的条件下,对其进行数据采集、编解码的新理论。而含噪信号的重构是压缩感知理论研究的关键技术,基追踪算法(BP)是比较成熟的信号重构算法。对BP及BPDN算法(基追踪去噪算法)进行了MATLAB仿真分析,并通过对算法的改进,扩展了BP算法的应用范围,使其在脉冲噪声条件下重构信号。然后与经典BP算法进行了仿真对比,验证了在脉冲噪声干扰条件下,改进算法计算速度相对原算法复杂度降低,而且能够比较准确地重构信号。
Compressed sensing（CS）theory is a novel data collection and coding theory under the condition that signal is sparse or compressible.The recovery for sparse signal is the key technique in compressed sensing.Technique which is commonly used in this setting is the basis pursuit（BP）.With the Matlab language,BP and BPDN（Basis Pursuit Denoising）is simulated and calculated.The modified basis pursuit denoising enlarges its application.It can reconstruct a string signal from underdetermined noisy measurements,in which the noise is not an impulse noise.Then we compare the modified basis pursuit denoising with the original and verify that the modified algorithm can reconstruct signal from impulse noise more quickly.
出处
《电子测量技术》
2010年第4期38-41,共4页
Electronic Measurement Technology
关键词
压缩感知
基追踪
信号重构
脉冲噪声
compressed sensing
basis pursuit
reconstruct signal
impulse noise
