自适应权重的GPSR压缩感知重构算法

Adaptive reweighting via GPSR algorithm for compressed sensing signal reconstruction

在压缩感知信号重构的过程中,为使投影梯度稀疏重构算法(GPSR)在保持低复杂度的同时,能有效提高重构性能,引入了自适应思想,给重构模型添加具有惩罚意义的权重系数,以寻找算法复杂度和精度之间的最佳平衡点;根据解的收敛进程不断调整权重值,以加速收敛.仿真实验表明:在相同条件下,该算法的计算效率优于传统的GPSR算法和典型的OMP算法,能在较短的运行时间内大幅度提高重构精度.

In order to improve the performance of gradient projection for sparse reconstruction(GPSR)algorithm effectively during the process of compressed sensing signal reconstruction,the weight coefficients for penalty is introduced into the reconstruction model.Its advantage is to find the best balance between the complexity and the construction precision.The weights are adaptively adjusted during every iterative step to accelerate the convergence.Simulation experiment results show that the proposed algorithm has a better performance on computational efficiency than that of the traditional GPSR algorithm and the typical OMP algorithm,enabling high precision reconstruction in less time.