Fuzzy AutoEncode Based Cloud Detection for Remote Sensing Imagery

被引:50
作者
Shao, Zhenfeng [1 ,2 ]
Deng, Juan [1 ,2 ]
Wang, Lei [1 ,2 ]
Fan, Yewen [1 ,2 ]
Sumari, Neema S. [3 ]
Cheng, Qimin [4 ]
机构
[1] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan 430079, Peoples R China
[2] Collaborat Innovat Ctr Geospatial Technol, 129 Luoyu Rd, Wuhan 430079, Peoples R China
[3] SUA, Fuculty Sci, Dept Informat, POB 3038, Morogoro, Tanzania
[4] Huazhong Univ Sci & Technol, Sch Elect Informat & Commun, 1037 Luoyu Rd, Wuhan 430074, Peoples R China
关键词
remote sensing imagery; fuzzy autoencode mode; cloud detection; SHADOW DETECTION; AUTOMATED CLOUD; LANDSAT IMAGERY; SNOW DETECTION; ALGORITHM; EXTRACTION;
D O I
10.3390/rs9040311
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Cloud detection of remote sensing imagery is quite challenging due to the influence of complicated underlying surfaces and the variety of cloud types. Currently, most of the methods mainly rely on prior knowledge to extract features artificially for cloud detection. However, these features may not be able to accurately represent the cloud characteristics under complex environment. In this paper, we adopt an innovative model named Fuzzy Autoencode Model (FAEM) to integrate the feature learning ability of stacked autoencode networks and the detection ability of fuzzy function for highly accurate cloud detection on remote sensing imagery. Our proposed method begins by selecting and fusing spectral, texture, and structure information. Thereafter, the proposed technique established a FAEM to learn the deep discriminative features from a great deal of selected information. Finally, the learned features are mapped to the corresponding cloud density map with a fuzzy function. To demonstrate the effectiveness of the proposed method, 172 Landsat ETM+ images and 25 GF-1 images with different spatial resolutions are used in this paper. For the convenience of accuracy assessment, ground truth data are manually outlined. Results show that the average RER (ratio of right rate and error rate) on Landsat images is greater than 29, while the average RER of Support Vector Machine (SVM) is 21.8 and Random Forest (RF) is 23. The results on GF-1 images exhibit similar performance as Landsat images with the average RER of 25.9, which is much higher than the results of SVM and RF. Compared to traditional methods, our technique has attained higher average cloud detection accuracy for either different spatial resolutions or various land surfaces.
引用
收藏
页数:19
相关论文
共 44 条
[1]   Scene Learning for Cloud Detection on Remote-Sensing Images [J].
An, Zhenyu ;
Shi, Zhenwei .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2015, 8 (08) :4206-4222
[2]  
[Anonymous], SPIE ASIA PAC REMOTE
[3]   Structure-texture image decomposition - Modeling, algorithms, and parameter selection [J].
Aujol, JF ;
Gilboa, G ;
Chan, T ;
Osher, S .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2006, 67 (01) :111-136
[4]   Cloud Detection for High-Resolution Satellite Imagery Using Machine Learning and Multi-Feature Fusion [J].
Bai, Ting ;
Li, Deren ;
Sun, Kaimin ;
Chen, Yepei ;
Li, Wenzhuo .
REMOTE SENSING, 2016, 8 (09)
[5]   Object Classification via Feature Fusion Based Marginalized Kernels [J].
Bai, Xiao ;
Liu, Chuntian ;
Ren, Peng ;
Zhou, Jun ;
Zhao, Huijie ;
Su, Yun .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2015, 12 (01) :8-12
[6]   A threshold-based cloud mask for the high-resolution visible channel of Meteosat Second Generation SEVIRI [J].
Bley, S. ;
Deneke, H. .
ATMOSPHERIC MEASUREMENT TECHNIQUES, 2013, 6 (10) :2713-2723
[7]   Cloud Detection based on HSI Color Space and SWT from High Resolution Color Remote Sensing Imagery [J].
Chen, Zhong ;
Deng, Tao ;
Zhou, Heng ;
Luo, Song .
MIPPR 2013: PATTERN RECOGNITION AND COMPUTER VISION, 2013, 8919
[8]   Cloud detection in Landsat imagery of ice sheets using shadow matching technique and automatic normalized difference snow index threshold value decision [J].
Choi, H ;
Bindschadler, R .
REMOTE SENSING OF ENVIRONMENT, 2004, 91 (02) :237-242
[9]   Cloud and Cloud-Shadow Detection in SPOT5 HRG Imagery with Automated Morphological Feature Extraction [J].
Fisher, Adrian .
REMOTE SENSING, 2014, 6 (01) :776-800
[10]   Cloud and cloud shadow screening across Queensland, Australia: An automated method for Landsat TM/ETM plus time series [J].
Goodwin, Nicholas R. ;
Collett, Lisa J. ;
Denham, Robert J. ;
Flood, Neil ;
Tindall, Daniel .
REMOTE SENSING OF ENVIRONMENT, 2013, 134 :50-65