Abstract
An approach to remove clouds in Landsat-8 operational land imager (OLI) data was developed with independent component analysis (ICA). Within cloud-covered areas, histograms were derived to quantify changes of the reflectance values before and after the use of the algorithm. Referred to a cloud-free image, changes of histogram curves validated the algorithm. Scatterplots were generated and linear regression performed for the reflectance values of each band before and after the algorithm, and compared to those of the reference image. Band-by-band, results in cloud removal were acceptable. The algorithm had little effect on pixels in cloud-free areas after the analyses of histograms, scatterplots, and linear regression equations. Finally, the algorithm was applied to various land use and land cover types and cloud conditions, and to a full Landsat-8 scene yielding satisfactory results efficiently.
Highlights
Landsat-8 was launched into space in February of 2013
The physical meaning of each independent component (IC) is usually unclear, the absolute weight value from Band 9 related to each IC is used to delineate cloud component in the ICs
Since the developed algorithm is applied to the entire image, the algorithm is assessed as two parts, the pixels in cloud-covered areas and the pixels in cloud-free areas
Summary
Landsat-8 was launched into space in February of 2013. The success in data collection has operationally ensured the data continuity from Landsats-4, -5 and -7 to current Landsat-8 in acquisition geometry, multispectral characteristics, and ground coverage as well as radiometric and geometric calibration. The removal of cloud effect is necessary Numerous methods such as image filtering, replacement, and transformation have been developed to remove clouds. Coupled with Band 9 and QA band, Shen et al (2015) [3] developed an image replacement approach using one single image to remove clouds for Bands 1–5 of Landsat-8. The HOT approach is based on a defined “clear line” (CL) in a two-dimensional scatterplot between two spectral bands using reflectance values from pixels of cloud-free areas. The cloud component for Landsat-8 data is yet to be developed, the Tasseled Cap transformation using Landsat-8 data has been studied [17,18]. We investigate an image transformation approach using the ICA to remove clouds in visible and infrared bands (Bands 1–7) of Landsat-8 operational land imager (OLI) data. The effectiveness of the ICA method is assessed qualitatively and quantitatively
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
