Watershed image segmentation and cloud classification from multispectral MSG-SEVIRI imagery |
| |
Authors: | Albano González Juan C PérezJonathan Muñoz Zebensui MéndezMontserrat Armas |
| |
Institution: | Grupo de Observación de la Tierra y la Atmósfera (GOTA), Universidad de La Laguna, 38200 Canary Islands, Spain |
| |
Abstract: | In this work a technique for cloud detection and classification from MSG-SEVIRI (Meteosat Second Generation-Spinning Enhanced Visible and Infra-red Imager) imagery is presented. It is based on the segmentation of the multispectral images using order-invariant watershed algorithms, which are applied to the corresponding gradient images, computed by a multi-dimensional morphological operator. To reduce the over-segmentation produced by the watershed method, a RAG (Region Adjacency Graph) based region merging technique is applied, using region dissimilarity functions. Once the objects present in the image have been segmented, they are classified using a multi-threshold method based on physical considerations that takes into account the statistical parameters inside each region. |
| |
Keywords: | Cloud detection Cloud classification MSG-SEVIRI |
本文献已被 ScienceDirect 等数据库收录! |