Compressed Sensing Data Reconstruction Using Adaptive Generalized Orthogonal Matching Pursuit Algorithm

Compressed sensing (CS), which breaks the limitations of the traditional Nyquist sampling theorem, takes full advantage of the sparse signal characteristics to achieve the accurate reconstruction of the compressed signal. An effective algorithm called GOAMP (Generalized Orthogonal Adaptive Matching Pursuit) algorithm was proposed by studying and summarizing the existing Matching Pursuit algorithm. The GOAMP algorithm can reconstruct the compressed signal exactly when the sparsity of the signal is unknown. Compare to the OMP (Orthogonal Matching Pursuit), the number of columns of the measurement matrix selected at each step is decided by the descent speed of the residual. Then like the OMP and the GOMP (Generalized Orthogonal Matching Pursuit), use the columns (atoms) selected before to reconstruct the original signal. The experiments show that the algorithm can choose the near-optimal iteration step quickly, signal reconstruction quality and efficiency of the algorithm are both ideal.