A post-classification change detection method based on iterative slow feature analysis and Bayesian soft fusion

被引:224
作者
Wu, Chen [1 ,4 ]
Du, Bo [2 ]
Cui, Xiaohui [1 ]
Zhang, Liangpei [3 ]
机构
[1] Wuhan Univ, Int Sch Software, Wuhan, Hubei, Peoples R China
[2] Wuhan Univ, Sch Comp, Wuhan, Hubei, Peoples R China
[3] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Hubei, Peoples R China
[4] Wuhan Univ, Int Sch Software, Res Ctr Spatial Informat & Digital Engn, Wuhan, Hubei, Peoples R China
基金
中国博士后科学基金; 中国国家自然科学基金;
关键词
Change detection; Post-classification; Iterative slow feature analysis; Bayesian soft fusion; Land-use/land-cover; Multi-temporal; Landsat; LAND-USE CHANGE; AUTOMATIC RADIOMETRIC NORMALIZATION; COVER CHANGE DETECTION; IMAGERY; DYNAMICS; CITIES; CHINA;
D O I
10.1016/j.rse.2017.07.009
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Post-classification with multi-temporal remote sensing images is one of the most popular change detection methods, providing the detailed "from-to" change information in real applications. However, due to the fact that it neglects the temporal correlation between corresponding pixels in multi-temporal images, the post-classification approach usually suffers from an accumulation of misclassification errors. In order to solve this problem, previous studies have separated the change and non-change candidates with change vector analysis, and they have only updated the classes of the changed pixels with the post-classification; however, this approach with thresholding loses the continuous change intensity information, where larger values indicate higher probability to be changed. Therefore, in this paper, a new post-classification method with iterative slow feature analysis (ISFA) and Bayesian soft fusion is proposed to obtain reliable and accurate change detection maps. The proposed method consists of three main steps: 1) independent classification is implemented to obtain the class probability for each image; 2) the ISFA algorithm is used to obtain the continuous change probability map of multi-temporal images, where the value of each pixel indicates the probability to be changed; and 3) based on Bayesian theory, the a posteriori probabilities for the class combinations of coupled pixels are calmlated to integrate the class probability with the change probability, which is named as Bayesian soft fusion. The class combination with the maximum a posteriori probability is then determined as the change detection result. In addition, a class probability filter is proposed to avoid the false alarms caused by the spectral variation within the same class. Two experiments with multi-temporal Landsat Thematic Mapper (TM) images indicated that the proposed method achieves a clearly higher change detection accuracy than the current state-of-the-art methods. The proposed method based on Bayesian theory and ISFA was also verified to have the ability to improve the change detection rate and reduce the false alarms at the same time. Given its effectiveness and flexibility, the proposed method could be widely applied in land-use/land-cover change detection and monitoring at a large scale. (C) 2017 Elsevier Inc. All rights reserved.
引用
收藏
页码:241 / 255
页数:15
相关论文
共 51 条
[1]   Extending post-classification change detection using semantic similarity metrics to overcome class heterogeneity: A study of 1992 and 2001 US National Land Cover Database changes [J].
Ahlqvist, OlA .
REMOTE SENSING OF ENVIRONMENT, 2008, 112 (03) :1226-1241
[2]   Slow feature analysis yields a rich repertoire of complex cell properties [J].
Berkes, P ;
Wiskott, L .
JOURNAL OF VISION, 2005, 5 (06) :579-602
[3]  
Berkes P., 2005, COGN SCI EPRINT ARCH, pv4104
[4]   Ice sheet change detection by satellite image differencing [J].
Bindschadler, Robert A. ;
Scambos, Ted A. ;
Choi, Hyeungu ;
Haran, Terry M. .
REMOTE SENSING OF ENVIRONMENT, 2010, 114 (07) :1353-1362
[5]   A theoretical framework for unsupervised change detection based on change vector analysis in the polar domain [J].
Bovolo, Francesca ;
Bruzzone, Lorenzo .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2007, 45 (01) :218-236
[6]   An iterative technique for the detection of land-cover transitions in multitemporal remote-sensing images [J].
Bruzzone, L ;
Serpico, SB .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1997, 35 (04) :858-867
[7]   Automatic radiometric normalization of multitemporal satellite imagery with the iteratively re-weighted MAD transformation [J].
Canty, Morton J. ;
Nielsen, Allan A. .
REMOTE SENSING OF ENVIRONMENT, 2008, 112 (03) :1025-1036
[8]   Bayesian updating of land-cover estimates in a data-rich environment [J].
Cardille, Jeffrey A. ;
Fortin, Julie A. .
REMOTE SENSING OF ENVIRONMENT, 2016, 186 :234-249
[9]   Unsupervised Change Detection in Satellite Images Using Principal Component Analysis and k-Means Clustering [J].
Celik, Turgay .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2009, 6 (04) :772-776
[10]   LIBSVM: A Library for Support Vector Machines [J].
Chang, Chih-Chung ;
Lin, Chih-Jen .
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)