Change detection of remote sensing images through DT-CWT and MRF

Kuikui FAN; Zhongyuan WANG; Sida OUYANG; Huibing WANG; Shaoyu SHI

doi:10.11834/jrs.20176251

Views : 0 下载量: 318 CSCD: 2 更多指标

PDF
Export
Share
Collection
Album

Change detection of remote sensing images through DT-CWT and MRF
Vol. 21, Issue 3, Pages: 375-385(2017)
Published： 2017-5 ，

Accepted： 1 December 2016
DOI： 10.11834/jrs.20176251

扫描看全文

Kuikui FAN, Zhongyuan WANG, Sida OUYANG, et al. Change detection of remote sensing images through DT-CWT and MRF. [J]. Journal of Remote Sensing 21(3):375-385(2017)
DOI：

Kuikui FAN, Zhongyuan WANG, Sida OUYANG, et al. Change detection of remote sensing images through DT-CWT and MRF. [J]. Journal of Remote Sensing 21(3):375-385(2017) DOI： 10.11834/jrs.20176251.

摘要

为了解决多尺度遥感图像变化检测在降噪时丢失大量高频信息及单一像素孤立性的问题，提出了一种双树复小波变换DT-CWT(Dual-tree Complex Wavelet Transform)和马尔可夫随机场MRF(Markov Random Field)相结合的非监督遥感图像变化检测算法，首先采用DT-CWT对差异图像进行多尺度分解，并根据MRF模型分割算法提取高频区域的变化特征，然后进行相应层的高、低频重构，再对重构后的各层建立MRF模型并根据贝叶斯最大后验概率准则MAP(Maximum A Posterior)进行最终分割，最后对各层分割结果进行求交融合，得到最终的变化检测结果掩膜图。对比实验结果表明，该方法在去除杂点和噪声的同时能够较好地保留高频信息，并且边缘检测更加平滑，具有较高的变化检测精度和很好的鲁棒性。

Abstract

Image change detection uses an algorithm that is based on multiscale analysis and Markov Random Field (MRF) model. The algorithm is widely used owing to time–frequency wavelet characteristics and the good expression to spatial correlation of the MRF model. To address the significant loss of high-frequency information during noise reduction and pixel independence in change detection of multiscale remote sensing images

this paper proposes an unsupervised change detection algorithm based on the combined dual-tree complex wavelet transform (DT-CWT) and MRF. The algorithm can be divided into the following steps. First

to enhance detail expression and objective image edges

the difference image is decomposed on a multiscale by DT-CWT. Second

the change characteristics in high-frequency regions are extracted by setting the high-frequency components of the first layer to zero and performing MRF segmentation to the other levels. Third

the high- and low-frequency sub-bands of each layer are reconstructed

and the maximum a posteriori probability is estimated by the Iterative Condition Model (ICM) based on the K-means segmentation algorithm

which fully obtains the correlation between pixels. Finally

the segmentation results of each layer are fused to obtain the mask of the final change detection result. To verify the effectiveness and stability of the proposed algorithm

the DT-CWT–Bayes

MRF–Bayes

DWT-MRF–Bayes methods

and the proposed algorithm are comparatively tested and analyzed. The contrast experiment proves that compared with the other methods

the proposed method produces change detection results for edges that subjectively look smoother and more delicate with less noise. In addition

as shown in the table of evaluation indices of the four change detection methods

the proposed method has the least total number of errors and the highest accuracy rate. Thus

the proposed method balances the reduction of tiny spots and noise and the retention of high frequency information. Moreover

the proposed method has high precision for change detection and predominant robust properties. The proposed algorithm fully uses the multidirectional expression

anisotropy

and multiscale properties of DT-CWT

which helps the expression and analysis of image information. In addition

the extraction of the change characteristics in high-frequency regions based on the segmentation algorithm of ICM better balances between noise reduction and retention of high frequency information. Finally

the final iteration and segmentation based on the MRF segmentation algorithm determines the correlation between pixels with considerably reduced false alarm rates while avoiding the influence of registration error. However

the proposed algorithm takes more time due to the existence of some iterative processes.

关键词

变化检测双树复小波变换DT-CWTMRF模型多尺度分解

Keywords

change detectionDT-CWTMRFmulti-scale decomposition

references

Bruzzone L and Prieto D F. 2000.Automatic analysis of the difference image for unsupervised change detection.IEEE Transactions on Geoscience and Remote Sensing, 38(3): 1171–1182

Celik T and Ma KK. 2010. Unsupervised change detection for satellite images using dual-tree complex wavelet transform. IEEE Transactions on Geoscience and Remote Sensing, 48(3): 1199–1210

陈忠辉, 王卫星, 于天超, 林丽群. 2011. 基于多尺度马尔科夫随机场融合的遥感图像变化检测. 四川大学学报(工程科学版), 43(3): 104–108

Chen Z H, Wang W X, Yu T C and Lin L Q.2011.Remote sensing image variation detection on multi-scale MRF fusion.Journal of Sichuan University(Engineering Science Edition), 43(3): 104–108

佃袁勇, 方圣辉, 姚崇怀. 2014. 一种面向地理对象的遥感影像变化检测方法. 武汉大学学报(信息科学版), 39(8): 906–912

Dian Y Y, Fang S H and Yao C H. 2014.The geographic object-based method for change detection with remote sensing imagery.Geomatics and Information Science of Wuhan University, 39(8): 906–912

佃袁勇, 方圣辉, 姚崇怀. 2016. 多尺度分割的高分辨率遥感影像变化检测. 遥感学报, 20(1): 129–137

Dian Y Y, Fang S H and Yao C H. 2016.Change detection for high-resolution images using multilevel segment method. Journal of Remote Sensing, 20(1): 129–137

Geman S and Geman D. 1984.Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images.IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-6(6): 721–741

Kasetkasem T and Varshney P K. 2002. An image change detection algorithm based on Markov random field models. IEEE Transactions on Geoscience and Remote Sensing, 48(8): 1815–1823

Kingsbury N. 1998. The dual-tree complex wavelet transform: a new efficient tool for image restoration and enhancement//Proceedings of the9th European Signal Processing Conference. Rhodes: IEEE, 319–322.

Kingsbury N. 2001. Complex wavelets for shift invariant analysis and filtering of signals.Applied and Computational Harmonic Analysis, 10(3): 234–253

李长春, 齐修东, 张光胜. 2013. 基于MRF模型的SAR图像变化检测研究. 现代雷达, 35(7): 31–35

Li C C, Qi X D and Zhang G S. 2013.A study on SAR image change detection based on Markov Random Field models. Modern Radar,35(7): 31–35

李长春, 张光胜, 李昊东, 李东东. 2014. 基于改进MRF模型SAR图像变化检测研究. 现代雷达, 36(9): 36–39

Li C C, Zhang G S, Li H D and Li D D. 2014.A study on SAR image change detection based on improved Markov random field models. Modern Radar, 36(9): 36–39

Marchesi S and Bruzzone L. 2009. ICA and kernel ICA for change detection in multispectral remote sensing images//Proceedings of 2009 IEEE International Geoscience and Remote Sensing Symposium. Cape Town: IEEE, 2: II-980-II-983 [DOI: 10.1109/IGARSS.2009.5418265]

孙晓霞, 张继贤, 燕琴, 高井祥. 2011. 遥感影像变化检测方法综述及展望. 遥感信息, (1): 119–123

Sun X X, Zhang J X, Yan Q and Gao J X.2011. A summary on current techniques and prospects of remote sensing change detection. Remote Sensing Information, (1): 119–123

魏小莉, 沈未名. 2010. 一种基于马尔科夫随机场模型的彩色纹理图像分割. 武汉大学学报(信息科学版), 35(8): 955–958

Wei X L and Shen W M. 2010.Gabor-MRF model based on color texture image segmentation. Geomatics and Information Science of Wuhan University,35(8): 955–958

Wu C, Du B and Zhang L P. 2013. Slow feature analysis for change detection in multispectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 52(5): 2858–2874

吴一全, 曹照清, 陶飞翔. 2015. 结合多尺度几何分析和KICA的遥感图像变化检测. 遥感学报, 19(1): 126–133

Wu Y Q, Cao Z Q and Tao F X. 2015.Change detection of remote sensing images by multi-scale geometric analysis and KICA. Journal of Remote Sensing, 19(1): 126–133

辛芳芳, 焦李成, 王桂婷, 万红林. 2012. 利用小波域HMC模型进行遥感图像变化检测. 西安电子科技大学学报(自然科学版), 39(3): 43–49

Xin F F, Jiao L C, Wang G T and Wan H L. 2012.Change detection in multi-temporal remote sensing images based on the wavelet-domain hidden Markov chain model. Journal of Xidian University(Natural Science), 39(3): 43–49

张斌. 2013. 基于MRF的SAR图像分类与变化检测应用研究. 武汉: 武汉大学

Zhang B. 2013. Research on the Sar Image Classification and Change Detection Based on the Markov Random Field. Wuhan: Wuhan University

张晗, 倪维平, 严卫东, 边辉, 吴俊政, 李莎, 金骁. 2016. 利用分形和多尺度分析的中低分辨率SAR图像变化检测. 武汉大学学报(信息科学版), 41(5): 642–648

Zhang H, Ni W P, Yan W D, Bian H, Wu J Z, Li S and Jin X. 2016. Mid and low resolution SAR image change detection based on fractal and multi-scale analysis. Geomatics and Information Science of Wuhan University, 41(5): 642–648

Alert me when the article has been cited

提交

MtSCCD： Land-use scene classification and change-detection dataset for deep learning

Optical-signal token guided change detection network for heterogeneous remote sensing image

Spectral-frequency domain attribute pattern fusion for hyperspectral image change detection

A siamese Nested-UNet for change detection in posterior probability space （SNU-PS）

Review of remote sensing change detection in deep learning： Bibliometric and analysis