压缩感知增强型自适应分段正交匹配追踪算法

信号重建算法是压缩感知技术中的关键问题。大部分贪婪迭代重建算法需要已知信号稀疏度，但实际情况下信号稀疏度很难获得。该文提出了一种增强型自适应分段正交匹配追踪算法。该算法在已有的分段正交匹配追踪算法的基础上，引入回溯思想，在原有的阈值参数的基础上引入一个新的标识参数I，达到有效的二次支撑集筛选，从而在未知信号稀疏度的前提下更好地重建信号。仿真结果表明，与其他相关算法相比，该文提出的算法无论在测量信号无噪还是有噪情况下，均可获得更优的信号重建质量:无噪条件下准确重建概率平均提高30%~40%，有噪条件下重建信号的均方误差（Mean Square Error, MSE）平均改善5~10dB，算法复杂度增加较少。 

Enhanced Adaptive Stagewise Orthogonal Matching Pursuit Algorithm Based on Compressed Sensing

The algorithms of the sparse signals reconstruction is the key issue in the theory of compressed sensing. The majority of greedy iterative-based algorithms only work under the condition of the prior known sparsity, which is hardly to be obtained accurately in real applications. An enhanced adaptive stagewise orthogonal matching pursuit algorithm is proposed in this paper. The proposed algorithm employs the backtracking and introduces an index parameter “I” based on the original threshold of the existing stagewise orthogonal matching pursuit algorithm, which can get the final support set more efficiently, obtaining better signal reconstruction. The simulation results show that, no matter whether the noise exists or not, the proposed algorithm can get better signal reconstruction quality with signal accurate reconstruction probability increased by 30%~40% without noise in measurement signals and MSE improved by 5~10dB averagely with noise in measurement signals, with less increase of computational complexity, as compared with other relevant algorithms.