Systematic study of color spaces and components for the segmentation of sky/cloud images

摘要

Sky/cloud imaging using ground-based Whole Sky Imagers (WSI) is acost-effective means to understanding cloud cover and weather patterns. Theaccurate segmentation of clouds in these images is a challenging task, asclouds do not possess any clear structure. Several algorithms using differentcolor models have been proposed in the literature. This paper presents asystematic approach for the selection of color spaces and components foroptimal segmentation of sky/cloud images. Using mainly principal componentanalysis (PCA) and fuzzy clustering for evaluation, we identify the mostsuitable color components for this task.