Regularised reweighted BPDN for compressed video sensing
In traditional compressed sensing methods, imposing sparsity alone usually does not produce the most visually pleasing reconstructed videos. Thus, by leveraging more prior information extracted from the temporal redundancy, a regularised reweighted basis pursuit denoising method with estimated support and signal value is proposed for a compressively sampled video. Moreover, an effective alternating direction method of multipliers is presented to solve the optimisation problem. Simulation results show that the proposed method compares favourably with conventional algorithms in the recovery performance.
