Automatic cloud segmentation from INSAT‐3D satellite image via IKM and IFCM clustering. Issue 7 (1st May 2020)

• Record Type: Journal Article
• Authors: A, Pugazhenthi; Kumar, Lakshmi Sutha
• Is Part Of: IET image processing. Volume 14:Issue 7(2020)
• Page Start: 1273
• Page End: 1280
• Publication Date: 2020-05-01
• Subjects: clouds -- image classification -- fuzzy set theory -- geophysical image processing -- image segmentation -- remote sensing -- atmospheric techniques; automatic cloud segmentation -- IFCM clustering -- satellite imagery -- satellite images -- image texture -- FCM clustering algorithms -- unsupervised pixel classification -- low‐level clouds -- middle‐level clouds -- high‐level clouds -- noncloudy region -- visible image -- VIS image -- cloudy -- IKM segmentation algorithm -- IFCM segmentation algorithm -- low‐level cloud region -- middle‐level cloud region -- high‐level cloudregion -- satellite system‐three‐dimensional satellite image -- k‐means clustering algorithms -- fuzzy c‐means clustering algorithms -- TIR image histogram; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.5271
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Cloud extraction and classification from satellite imagery is important for many applications in remote sensing. Satellite images are segmented based on distance, intensity and texture of the images. The popular segmentation algorithms, k ‐means (KM) and fuzzy c ‐means (FCM) clustering algorithms, face some problems such as unknown number of groups, unknown initialization and dead centers. In this paper, an unsupervised pixel classification by the KM and FCM algorithms is improved and the selection of centroids is made automatic. The proposed improved k ‐means (IKM) and improved fuzzy c ‐means (IFCM) clustering algorithms segment the INSAT‐3D satellite's thermal infrared image into low‐level, middle‐level, high‐level clouds and non‐cloudy region. As human beings can easily find the clouds in the satellite images, visible image is used to differentiate the clouds from the background. A threshold is found from the histogram of the visible image to separate the cloudy and non‐cloudy pixels. The other three thresholds to divide the clouds into three types are found from the thermal infrared image's histogram. The segmentation results of IKM and IFCM algorithms are compared with the existing segmentation algorithms. The comparison shows that IFCM algorithm matches well with original image followed by IKM algorithm as compared with existing algorithms.