Thin cloud removal from optical remote sensing images using the noise-adjusted principal components transform

Abstract

Cloud cover is a common problem in optical remote sensing images due to its contamination of the reflectance from the Earth’s surface. Cloud removal has become a necessary preprocessing step for most applications. In this paper, we develop an effective thin cloud removal method with the help of a noise-adjusted principal components transform model (CR-NAPCT). We discover that cloud-contaminated data has the highest signal-to-noise ratio (S/N) due to its high spatial correlation, and are shown in the first NAPCT component (NAPC1) in the NAPCT data. Image restoration is achieved by performing an inverse NAPCT after removing the cloud component in NAPC1. In the experiments, both simulated and real images from Landsat 8 were used to assess the performance of the proposed method quantitatively and qualitatively. The results show that the CR-NAPCT method is effective in eliminating thin cloud effects and performs better than the existing similar approaches tested.