关键词: 自适应压缩感知, 观测矩阵优化, 观测信噪比, 特征分解, Gram矩阵

Abstract: Abstract: In order to improve the robustness of compressed sensing (CS) recovery algorithm, a kind of adaptive compressed sensing (ACS) algorithm is proposed based on the idea of observation matrix optimization and adaptive observation. The algorithm allocates the energy all in the support position estimated by the traditional CS recovery algorithm, which can effectively improve the observed signal-to-noise ratio (SNR), and then derive the optimal new observation vector from the perspective of observation matrix optimization, that is its nonzero part is designed as the eigenvector of Gram matrix. The simulation results show that the energy growth of the non-diagonal elements of the Gram matrix is slower than that of the traditional CS algorithm with the increase of the number of observations, and the reconstruction errors of the proposed algorithm is respectively lower than the traditional CS recovery algorithm and typical Bayesian adaptive algorithm under the same conditions of the number of observations, sparsity and SNR. The analysis shows that the proposed adaptive observation mechanism can effectively improve the anti-noise performance of the traditional CS recovery algorithm.

Key words: Keywords: adaptive compressed sensing, observation matrix optimization, observed signal-to-noise ratio, feature decomposition, Gram matrix