Cloud and cloud shadow removal of landsat 8 images using Multitemporal Cloud Removal method

Cloud and cloud shadow cover on satellite images limit remote sensing and geo-information systems (GIS) applications in all application areas, especially for change detection and time series analyses. A novel method of cloud and cloud shadow removal called Multitemporal Cloud Removal (MCR) is proposed in this paper. The method has main steps: (1) radiometric correction, (2) cloud and cloud shadow detection, and (3) image reconstruction. Top of Atmosphere (TOA) radiometric correction converts digital number values to TOA reflectance for Landsat 8 OLI was first completed. In the second step, Multi-temporal Cloud Masking (MCM) was used to detect cloud and cloud shadow. This method uses a target image which has cloud and cloud shadow contaminated pixels and a reference image which is clear. The aim is to obtain the difference in reflectance values in visible, near-infrared and short wave infrared bands between target and reference images. These values can be used to detect cloud and cloud shadow in Landsat 8 images. The Landsat 8 cirrus band is used to detect thin cirrus cloud in this method. We use target image and reference image from a sequence acquisition dates of Landsat 8 images to avoid the significant land cover change. In the last step, we use multitemporal images to reconstruct pixels which are contaminated by cloud and cloud shadow. Cloud and cloud shadow contaminated pixels on the target image are replaced by pixels from the reference image. Landsat 8 images which have heterogeneous land cover and variety of cloud types are chosen in the experiments to prove that MCR is robust method for removing cloud and cloud shadow and can be used for image that has heterogeneous land cover and variety of cloud types. We use visual and statistical assessments to evaluate the results. As results show, cloud and cloud shadow can be removed by MCR. In visual evaluation, the corrected images are similar to the reference image. In statistical assessments between corrected and references images, the correlation coefficient for each band is quite high (>0.9) for the thick cloud case and equal to 1 for thin cloud case. Within band tandard deviations in the reference image and the corrected image were higher in the corrected image compared to the the reference image and original image. Although not comprehensive, the visual and statistical assessments, provide some indication that th MCR method was robust method for removing cloud and cloud shadow in Landsat 8 images examined in this work. The advantage of this appoach is that original reflectance values can be retained as long as they are not contaminated by cloud and cloud shadow. In addition, as we use a sequence acquisition date of Landsat 8 images, we can produce free cloud and cloud shadow images.