Abstract
Cloud and cloud shadow detection is an important preprocess before using satellite images for different applications. It can be considered as a classification process, in which the objective pixels are partitioned into cloud/cloud shadow or non-cloud/non-cloud shadow classes. However, some cloud pixels, especially the thin cloud pixels, can be considered as a mixture of reflectances of clouds and land objects. In fuzzy clustering, the data points can belong to two or more clusters; hence, fuzzy clustering may better characterize the status of one given pixel belonging to clouds or non-clouds. The fuzzy c-means method (FCM), one typical fuzzy clustering method, was utilized in this study for cloud and cloud shadow detection. In addition, the “flood-fill” morphological transformation may misclassify some clear-sky areas surrounded by clouds as cloud shadows as a whole, so a modified cloud shadow index calculation was proposed. Moreover, a cloud and cloud shadow spatial matching strategy based on the projection direction and spatial coexistence was used to exclude some pseudo cloud shadows. Fewer predefined parameters and spectral bands are needed is one characteristic of the proposed method. In this study, 41 scenes including 27 Landsat ETM+ images in eight latitude zones and 14 Landsat OLI images comprising seven land cover types, including barren, forest, grass, shrubland, urban, water, and wetlands areas, with percentages of cloud cover from 4.99% to 97.63%, were utilized to confirm the validity of the FCM. The detected results demonstrate that the thick and thin clouds along with their associated cloud shadows can be precisely extracted by using the FCM. Compared with the function of mask (Fmask) method, the FCM has relatively lower producer agreement rates, but it misclassifies as clouds fewer clear-sky pixels; compared with the support vector machine (SVM) method, the FCM can achieve better cloud detection accuracy. The results demonstrate that the FCM can attain a better balance between cloud pixel detection and non-cloud pixel exclusion.
Highlights
T HE spectral bands of optical sensors are commonly influenced by clouds and cloud shadows [1]–[4]
We proposed a cloud and cloud shadow detection method based on the fuzzy c-means algorithm for multi-spectral satellite sensors with visible and NIR bands
Instead of classifying the objective pixels into one specific class, in fuzzy clustering, the data points can belong to more than one cluster, and are each associated with certain membership grades that represent the degree to which they belong to the different clusters
Summary
T HE spectral bands of optical sensors are commonly influenced by clouds and cloud shadows [1]–[4]. In light of Manuscript received December 24, 2019; revised February 18, 2020 and March 20, 2020; accepted April 11, 2020. Date of publication April 22, 2020; date of current version May 5, 2020. The surface of the Earth, when covered by clouds and cloud shadows, cannot be correctly presented in the satellite images; this could, in turn, affect many types of studies, such as those on atmospheric correction, land cover classification and change detection, and feature extraction [2], [6]. Cloud and cloud shadow detection is an essential preprocess before using satellite images for different applications
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
