Detecting clouds and cloud shadows in multispectral satellite images for tropical areas

Abstract

A practical approach for detecting clouds and cloud shadows in multispectral satellite images is presented. In tropical regions, where clouds are common throughout the year, cloud detection is useful in improving the accuracy of land cover classification in multispectral images. After detection and removal of clouds we can selectively merge classification results from two temporally separate images of the same area to minimise the cloud effect. We emphasise the ease of implementation of the algorithm so that practitioners can easily adapt the method for their own use.