干旱区生态环境知识资源中心(Arid): Cloud detection algorithm using SVM with SWIR2 and tasseled cap applied to Landsat 8

Arid

DOI	10.1016/j.jag.2019.101898
	Cloud detection algorithm using SVM with SWIR2 and tasseled cap applied to Landsat 8
	Joshi, Pratik P.1; Wynne, Randolph H.2; Thomas, Valerie A.2
通讯作者	Joshi, Pratik P.
来源期刊	INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
ISSN	1569-8432
EISSN	1872-826X
出版年	2019
卷号	82
英文摘要	Landsat satellite images are subject to cloud cover effects resulting in erroneous analysis and observations of ground features. In this work, we present a novel algorithm (STmask) combining tasseled cap band 4 (TC4) with short wave infrared spectral band 2, SWIR2 (2.107-2.294 mu m) for generating cloud, water, shadow, snow and vegetation masks. A support vector machine (SVM) with a non-linear kernel is trained on a feature space of TC4 versus SWIR2 for generating feature masks. To develop a generic and unbiased algorithm, the SVM is trained using reference data comprised of 12891 pixels from Landsat 8 scenes from ten spatially and temporally diverse biomes including deciduous forest, rainforest, great plain, savanna, desert, ocean, freshwater, taiga, tundra, and icesheet. 960000 text pixels spanning 96 scenes across 8 biomes from the USGS Landsat cloud cover assessment data set are used for accuracy assessment of STmask as well as to compare its performance with the operational Landsat algorithm, C function of mask (CFmask). Using McNemar's statistic, STmask is shown to maximize both the precision and sensitivity of the classification of all features compared to CFmask. It addresses the challenges of CFmask through statistically significant improvement in the precision of cloud detection over snow/ice, barren, water, urban, and shrubland biomes. Aggregated over all biomes, the average improvement in cloud detection over CFmask is observed to be similar to 3.8% using the F-measure. The classification of non-cloud features exhibits promising improvements and mostly comparable performance to CFmask. Overall classification performance is promising, and thus STmask is a novel, biome-independent, parsimonious, and computationally efficient alternative (and/or a cloud screening addition) to the operational CFmask algorithm. The work is timely and is targeted as an innovative processing solution for the land surface remote sensing research community.
英文关键词	Cloud detection SWIR Tasseled cap SVM Landsat 8 Feature mask
类型	Article
语种	英语
国家	USA
收录类别	SCI-E
WOS记录号	WOS:000484871800028
WOS关键词	HAZE REMOVAL ; AUTOMATED CLOUD ; SNOW DETECTION ; SATELLITE DATA ; CLASSIFICATION ; TRANSFORMATION ; SHADOW ; ACCURACY
WOS类目	Remote Sensing
WOS研究方向	Remote Sensing
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/216347
作者单位	1.Univ Illinois, Dept Elect & Comp Engn, Urbana, IL 61801 USA; 2.Virginia Tech, Dept Forest Resources & Environm Conservat, Blacksburg, VA 24060 USA
推荐引用方式 GB/T 7714	Joshi, Pratik P.,Wynne, Randolph H.,Thomas, Valerie A.. Cloud detection algorithm using SVM with SWIR2 and tasseled cap applied to Landsat 8[J],2019,82.
APA	Joshi, Pratik P.,Wynne, Randolph H.,&Thomas, Valerie A..(2019).Cloud detection algorithm using SVM with SWIR2 and tasseled cap applied to Landsat 8.INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION,82.
MLA	Joshi, Pratik P.,et al."Cloud detection algorithm using SVM with SWIR2 and tasseled cap applied to Landsat 8".INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION 82(2019).