A Cloud Removal Algorithm to Generate Cloud and Cloud Shadow Free Images Using Information Cloning
- PDF / 4,799,121 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 51 Downloads / 194 Views
RESEARCH ARTICLE
A Cloud Removal Algorithm to Generate Cloud and Cloud Shadow Free Images Using Information Cloning Kaan Kalkan1 • M. Derya Maktav2 Received: 13 February 2017 / Accepted: 22 January 2018 Ó Indian Society of Remote Sensing 2018
Abstract One of the main problems of optical remote sensing is clouds and cloud shadows caused by specific atmospheric conditions during data acquisition. These features limit the usage of acquired images and increase the difficulty in data analysis, such as normalized difference vegetation index values, misclassification, and atmospheric correction. Accurate detection and reliable cloning of cloud and cloud shadow features in satellite images are very useful processes for optical remote sensing applications. In this study, an automated cloud removal algorithm to generate cloud and cloud shadow free images from multitemporal Landsat-8 images is introduced. Cloud and cloud shadow areas are classified by using process-based rule set developed by using spectral and spatial features after applying simple linear iterative clustering superpixel segmentation algorithm to the image to find cloud pixel groups easily and correctly. Segmentation-based cloud detection method gives better results than pixel-based for detection of cloud and cloud shadow patches. After detection of clouds and cloud shadows, cloud-free images are created by cloning cloudless regions from multitemporal dataset. Spectral and structural consistency are preserved by considering spectral features and seasonal effects while cloning process. Statistical similarity tests are applied to find best cloud-free image to use for cloning process. Cloning results are tested with the structural similarity index metric to evaluate the performance of cloning algorithm. Keywords Landsat 8 Cloud Cloud shadow Cloud determination Cloning Information reconstruction Flood Fill
Introduction Remote sensing images are more or less influenced by clouds and cloud shadows during the data acquisition. Therefore detection of clouds and cloud shadows are important for further digital image processing analysis of remote sensing images (Arvidson et al. 2001; Irish 2000). When there is no multitemporal images of the same region available, clouds become a serious problem for image classification and interpretation processes (Zhang et al. & Kaan Kalkan [email protected] M. Derya Maktav [email protected] 1
¨ BI˙TAK Space Technologies Research Institute, ODTU, TU 06800 Ankara, Turkey
2
Geomatics Engineering Department, Istanbul Technical University, 34469 Maslak, Istanbul, Turkey
2010). Elimination of haze effects and missing information reconstruction from multitemporal satellite images are the main methods to produce cloud-free images. Google Earth, Bing, MapQuest and MapBox are using satellite images of the visible spectrum for their web maps of the earth (Gundersen 2013; Hancher 2016). Cloud-free mosaics are needed for showing their interested areas to users cloud-free and updated. Averaging multitemporal satellite i
Data Loading...
