High noise astronomical image denoising via 2G-bandelet denoising compressed sensing

In deep space exploration, high resolution astronomical image captured is often contaminated by various cosmic noise signals during its shooting and long distance transmission, which has brought inconvenience to astronomical image analysis. The famous compressed sensing (CS) proposed by Candes et al. can successfully solve the problem of high resolution astronomical image compression and low noise reconstruction. In this paper, we further concern how to reconstruct a high quality image from a high resolution and high noise astronomical image. A 2G-bandelet denoising compressed sensing (BDCS) is first proposed based on the advantage of CS in image denoising and the superior ability of 2G-bandelet in sparse representation of astronomical images, then iterative bandelet thresholding (IBT-BTCS) algorithm based on BDCS is proposed for high resolution and high noise astronomical image reconstruction. Firstly, an iterative bandelet thresholding method is designed to obtain optimal approximation of original image; Secondly, to further improve the reconstructed image quality, group sparse total variation with stepsize constraints (GSTV-SC) method is proposed to adjust the reconstructed astronomical image in each iteration. The simulation results show that the proposed algorithm can quickly reconstruct a high quality astronomical image only using a few observations, preserve more astronomical image details and effectively solve high noise astronomical image denoising problem.