Cloud Detection for Landsat Images by Fusion of Multi-Temporal Data

Landsat images are the most widely used satellite data; they are susceptible to cloud interference that will affects the subsequent applications. In this paper, an effective cloud detection algorithm is proposed for Landsat images by fusing multi-temporal Landsat data. The algorithm includes two parts: thick clouds detection based on the reflection characteristics of thick clouds in the blue band; and thin clouds detection by Fast Independent Component Analysis (FastICA). Experimental results indicate that the algorithm proposed has good accuracy and effectiveness both for thick and thin cloud detection in large area scene.

[1]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[2]  C. Woodcock,et al.  Monitoring land-use change in the Pearl River Delta using Landsat TM , 2002 .

[3]  Martha C. Anderson,et al.  Landsat-8: Science and Product Vision for Terrestrial Global Change Research , 2014 .

[4]  Zhe Zhu,et al.  Object-based cloud and cloud shadow detection in Landsat imagery , 2012 .

[5]  Aapo Hyvärinen,et al.  The Fixed-Point Algorithm and Maximum Likelihood Estimation for Independent Component Analysis , 1999, Neural Processing Letters.

[6]  Bo Yi Lin,et al.  Radiometric normalization and cloud detection of optical satellite images using invariant pixels , 2015 .

[7]  C. Woodcock,et al.  The factor of scale in remote sensing , 1987 .

[8]  James C. Storey,et al.  Four years of Landsat-7 on-orbit geometric calibration and performance , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Daoliang Li,et al.  Image segmentation incorporating double-mask via graph cuts , 2016, Comput. Electr. Eng..

[10]  S. Goward,et al.  Characterization of the Landsat-7 ETM Automated Cloud-Cover Assessment (ACCA) Algorithm , 2006 .

[11]  Zhe Zhu,et al.  Improving Fmask cloud and cloud shadow detection in mountainous area for Landsats 4–8 images , 2017 .

[12]  Y. Kaufman,et al.  Corection of thin cirrus path radiances in the 0.4–1.0 μm spectral region using the sensitive 1.375 μm cirrus detecting channel , 1998 .