Cloud Detection Method for High Resolution Satellite Image Based on Multi-Dimensional Features

Journal of Atmospheric and Environmental Optics ›› 2017, Vol. 12 ›› Issue (6): 465-.

Cloud Detection Method for High Resolution Satellite Image Based on Multi-Dimensional Features

XIA Yu1,2, CUI Shengcheng1, YANG Shizhi1*

(1 Key Laboratory of Atmospheric Composition and Optical Radiation, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China;
2 University of Chinese Academy of Sciences, Beijing 100049, China )

Received:2016-04-25 Revised:2016-07-07 Online:2017-11-28 Published:2017-11-13
Supported by:
Supported by National Natural Science Foundation of China(国家自然科学基金, 41305019）

Abstract

Abstract:

Cloud is a large obstacle to remote sensing image processing and analysis. In order to solve this problem, an optimizational cloud detection algorithm is proposed for GF-1 satellite image based on the spectral and textural information. In the cloud-like areas detected by spectral analysis, a new sub-image segment method and dynamic threshold is used to improve the accuracy of texture detection. The Otsu algorithm is used to restore the thick cloud boundary information, since neither the fixed spectral threshold setting nor textural detection can get the boundaries of cloud in a complex environment. The results show that this method can effectively detect the cloud cover in the remote sensing image, optimally extract thick cloud boundary information, and effectively separate thin cloud and thick cloud.

Key words: multi-spectrum, texture features, cloud detection

CLC Number:

TP346
TP347

XIA Yu, CUI Sheng-Cheng, YANG Shi-Zhi. Cloud Detection Method for High Resolution Satellite Image Based on Multi-Dimensional Features[J]. Journal of Atmospheric and Environmental Optics, 2017, 12(6): 465-.

References

[1] Girolamo L D, Davies R. The image navigation cloud mask for the multiangle imaging spectroradiometer (MISR) [J]. J. Atmos. Ocean. Tech., 1995, 12(6): 1215-1228.
[2] Marais I V Z, Preez J A D, Steyn W H. An optimal image transform for threshold-based cloud detection using heteroscedastic discriminant analysis [J]. Int. J. Remote Sens., 2011, 32(6): 1713-1729.
[3] Shan Na, Zheng Tianyao, Wang Zhensong. High-speed and high-accuracy algorithm for cloud detection and its application [J]. Journal of Remote Sensing, 2009, 13(6): 1138-1155(in Chinese).
单娜, 郑天垚, 王贞松. 快速高准确度云检测算法及其应用 [J]. 遥感学报, 2009, 13(6): 1138-1155.
[4] Tao Shuping, Jin Guang, Zhang Guixiang, et al. A wavelet SCM algorithm used to detect cloud in remote sensing cameras [J]. Acta Geodaetica et Cartographica Sinica, 2011, 40(5): 598-603(in Chinese).
陶淑苹, 金光, 张贵祥, 等. 实现遥感相机自主辨云的小波SCM算法 [J]. 测绘学报, 2011, 40(5): 598-603.
[5] Chen Zhenwei, Zhang Guo, Ning Jinsheng, et al. An automatic cloud detection method for ZY-3 satellite [J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(3): 292-300(in Chinese).
陈振炜, 张过, 宁津生, 等. 资源三号测绘卫星自动云检测 [J]. 测绘学报, 2015, 44(3): 292-300.
[6] Zhang Y, Guindon B, Cihlar J. An image transform to characterize and compensate for spatial variations in thin cloud contamination of Landsat images [J]. Remote Sens. Environ., 2002, 82(2): 173-187.
[7] Chen P Y, Srinivasan R, Fedosejevs G, et al. An automated cloud detection method for daily NOAA14 AVHRR data for Texas, USA [J]. Int. J. Remote Sens., 2002, 23(23): 2939-2950.
[8] Li Wei, Fang Shenghui, Dian Yuanyong, et al. Cloud Detection in MODIS data based on spectrum analysis [J]. Editorial Board of Geomatics & Information Science of Wuhan University, 2005, 30(5): 435-438(in Chinese).
李微, 方圣辉, 佃袁勇, 等. 基于光谱分析的MODIS云检测算法研究 [J]. 武汉大学学报: 信息科学版, 2005, 30(5): 435-438.
[9] Zhu Z, Woodcock C E. Object-based cloud and cloud shadow detection in landsat imagery [J]. Remote Sens. Environ., 2012, 118(6): 83-94.
[10] Ding Haiyan, Ma Lingling, Li Ziyang, et al. Automatic identification of cloud and snow based on fractal dimension [J]. Remote Sensing Technology & Application, 2013, 28(1): 52-57(in Chinese).
丁海燕, 马灵玲, 李子扬, 等. 基于分形维数的全色影像云雪自动识别方法 [J]. 遥感技术与应用, 2013, 28(1): 52-57.
[11]Ohtsu N. A Threshold selection method from gray-level histograms [J]. IEEE T. Syst. Man Cy., 1979, 9(1): 62-66.