Automatic cloud detection for high spatial resolution multi-temporal images

Abstract

In this article, we propose an automatic cloud detection process for images with high spatial resolution. First, thick cloud regions are detected by applying a simple threshold method to the target image (an image that includes a cloud-covered region). Next, a reference image (another image that was acquired at a different time and includes the region with relatively little or no cloud-cover) is transformed to the coordinates of the target image by a modified scale-invariant feature transform (SIFT) method. The difference between the target image and transformed reference image is used to extract the peripheral cloud regions. The thick and peripheral cloud regions are then merged based on their relative locations and areas to detect the final cloud regions. Multi-temporal Korea Multi-Purpose Satellite-2 (KOMPSAT-2) images are used to construct study sites to evaluate the proposed method for a range of cloud-cover cases. From the proposed method, a large number of correctly matched points were extracted for this generation of the transformation model, and cloud-covered regions were effectively detected for all sites without manual intervention.