[1]雷涛,王洁,薛丁华,等.差异特征融合的无监督SAR图像变化检测[J].智能系统学报,2021,16(3):595-604.[doi:10.11992/tis.202103011]
 LEI Tao,WANG Jie,XUE Dinghua,et al.Unsupervised SAR image change detection based on difference feature fusion[J].CAAI Transactions on Intelligent Systems,2021,16(3):595-604.[doi:10.11992/tis.202103011]
点击复制

差异特征融合的无监督SAR图像变化检测(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第16卷
期数:
2021年3期
页码:
595-604
栏目:
人工智能院长论坛
出版日期:
2021-05-05

文章信息/Info

Title:
Unsupervised SAR image change detection based on difference feature fusion
作者:
雷涛12 王洁3 薛丁华3 王兴武2 杜晓刚2
1. 陕西科技大学 电子信息与人工智能学院,陕西 西安 710021;
2. 陕西科技大学 陕西省人工智能联合实验室,陕西 西安 710021;
3. 陕西科技大学 电气与控制工程学院,陕西 西安 710021
Author(s):
LEI Tao12 WANG Jie3 XUE Dinghua3 WANG Xingwu2 DU Xiaogang2
1. School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an 710021, China;
2. Shaanxi Joint Laboratory of Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an 710021, China;
3. School of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xi’an 710021, China
关键词:
SAR遥感影像变化检测无监督学习卷积神经网络特征融合差异图像模糊聚类孪生网络
Keywords:
SAR remote sensing imagechange detectionunsupervised learningconvolution neural networkfeature fusiondifference imagefuzzy c-meansSiamese network
分类号:
TP18
DOI:
10.11992/tis.202103011
摘要:
针对Siamese网络忽略不同层级差异特征之间的关联导致检测精度有限的问题,提出了基于差异特征融合的无监督SAR(synthetic aperture radar)图像变化检测算法。首先,利用对数比值算子和均值比值算子构建两幅信息互补的差异图,通过引入能量矩阵对差异图进行像素级融合以提高其信噪比;其次,设计了一种基于差异特征融合的Siamese网络(difference feature fusion for Siamese,DFF-Siamese),该网络能够通过差异特征提取模块在决策层综合衡量不同层级特征之间的差异程度,从而有效增强网络的特征表达能力;最后,利用模糊聚类算法对融合结果进行分类构建“伪标签”,用于训练DFF-Siamese网络以实现高精度SAR图像变化检测。在3组真实遥感数据集上的实验结果表明,本文提出的算法与其他对比算法相比具有更高的检测精度和更低的错误率。
Abstract:
The Siamese network ignores the correlation between different levels of different features, leading to limited detection accuracy. To overcome this limitation, an unsupervised synthetic aperture radar (SAR) image change detection algorithm based on the fusion of different features is proposed. The method uses log-ratio and mean-ratio operators to construct two complementary difference images and introduces an energy matrix to perform pixel-level fusion on these difference maps to improve its signal-noise ratio. Next, a Siamese network based on different feature fusion (DFF-Siamese) is designed. By introducing a difference feature extraction module, the DFF-Siamese comprehensively measure the differences and similarities between the multitemporal images using high-level semantic features, effectively improving the feature representation capability of the network. Finally, a fuzzy clustering algorithm is used to classify the fusion images to construct fake labels used to train the developed DFF-Siamese network, achieving accurate change detection for the SAR images. Experimental results from three real remote sensing datasets showed that the proposed method exhibits higher change detection accuracy with lower error rates compared with other popular algorithms.

参考文献/References:

[1] LI Lu, WANG Chao, ZHANG Hong, et al. Urban building change detection in SAR images using combined differential image and residual U-Net network[J]. Remote sensing, 2019, 11(9):1091.
[2] KURUOGLU E E, ZERUBIA J. Modeling SAR images with a generalization of the Rayleigh distribution[J]. IEEE transactions on image processing, 2004, 13(4):527-533.
[3] WANG Rongfang, ZHANG Jie, CHEN Jiawei, et al. Imbalanced learning-based automatic SAR images change detection by morphologically supervised PCA-Net[J]. IEEE geoscience and remote sensing letters, 2019, 16(4):554-558.
[4] CHEN Hongruixuan, WU Chen, DU Bo, et al. Change detection in multisource VHR images via deep Siamese convolutional multiple-layers recurrent neural network[J]. IEEE transactions on geoscience and remote sensing, 2020, 58(4):2848-2864.
[5] PIRRONE D, BOVOLO F, BRUZZONE L. A novel framework based on polarimetric change vectors for unsupervised multiclass change detection in dual-pol intensity SAR images[J]. IEEE transactions on geoscience and remote sensing, 2020, 58(7):4780-4795.
[6] XUE Dinghua, LEI Tao, JIA Xiaohong, et al. Unsupervised change detection using multiscale and multiresolution Gaussian-mixture-model guided by saliency enhancement[J]. IEEE journal of selected topics in applied earth observations and remote sensing, 2020, 14:1796-1809.
[7] GONG Maoguo, ZHOU Zhiqiang, MA Jingjing. Change detection in synthetic aperture radar images based on image fusion and fuzzy clustering[J]. IEEE transactions on image processing, 2012, 21(4):2141-2151.
[8] JIA Lu, LI Ming, ZHANG Peng, et al. Remote-sensing image change detection with fusion of multiple wavelet kernels[J]. IEEE journal of selected topics in applied earth observations and remote sensing, 2016, 9(8):3405-3418.
[9] ZHENG Yaoguo, ZHANG Xiangrong, HOU Biao, et al. Using combined difference image and k-means clustering for SAR image change detection[J]. IEEE geoscience and remote sensing letters, 2014, 11(3):691-695.
[10] 邵攀,任东,董婷.顾及冲突分析的模糊积分非监督变化检测[EB/OL].(2019?07?02)[2021?03?05] https://doi.org/10.16383/j.aas.c190047.
SHAO Pan, REN Dong, DONG Ting. Unsupervised change detection based on fuzzy integral considering conflict analysis[EB/OL]. (2019?07?02)[2021?03?05] https://doi.org/10.16383/j.aas.c190047.
[11] GONG Maoguo, SU Linzhi, JIA Meng, et al. Fuzzy clustering with a modified MRF energy function for change detection in synthetic aperture radar images[J]. IEEE transactions on fuzzy systems, 2014, 22(1):98-109.
[12] LEI Tao, XUE Dinghua, LYU Zhiyong, et al. Unsupervised change detection using fast fuzzy clustering for landslide mapping from very high-resolution images[J]. Remote sensing, 2018, 10(9):1381.
[13] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab:semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE transactions on pattern analysis and machine intelligence, 2018, 40(4):834-848.
[14] LEI Tao, ZHANG Yuxiao, LYU Zhiyong, et al. Landslide inventory mapping from bitemporal images using deep convolutional neural networks[J]. IEEE geoscience and remote sensing letters, 2019, 16(6):982-986.
[15] LIU Jia, GONG Maoguo, QIN Kai, et al. A deep convolutional coupling network for change detection based on heterogeneous optical and radar images[J]. IEEE transactions on neural networks and learning systems, 2018, 29(3):545-559.
[16] ZHAO Wei, WANG Zhirui, GONG Maoguo, et al. Discriminative feature learning for unsupervised change detection in heterogeneous images based on a coupled neural network[J]. IEEE transactions on geoscience and remote sensing, 2017, 55(12):7066-7080.
[17] GONG Maoguo, ZHAO Jiaojiao, LIU Jia, et al. Change detection in synthetic aperture radar images based on deep neural networks[J]. IEEE transactions on neural networks and learning systems, 2016, 27(1):125-138.
[18] GAO Feng, DONG Junyu, LI Bo, et al. Automatic change detection in synthetic aperture radar images based on PCANet[J]. IEEE geoscience and remote sensing letters, 2016, 13(12):1792-1796.
[19] DONG Huihui, MA Wenping, WU Yue, et al. Local descriptor learning for change detection in synthetic aperture radar images via convolutional neural networks[J]. IEEE access, 2018, 7:15389-15403.
[20] 王昶, 张永生, 韩世静, 等. 基于频域显著性方法和ELM的遥感影像变化检测[J]. 华中科技大学学报(自然科学版), 2020, 48(5):19-24
WANG Chang, ZHANG Yongsheng, HAN Shijing, et al. Remote sensing image change detection based on frequency domain significance method and ELM[J]. Journal of Huazhong University of Science and Technology (natural science edition), 2020, 48(5):19-24
[21] MA Jiayi, MA Yong, LI Chang. Infrared and visible image fusion methods and applications:a survey[J]. Information fusion, 2019, 45:153-178.
[22] ZHANG Z, VOSSELMAN G, GERKE M, et al. Change detection between multimodal remote sensing data using Siamese CNN[EB/OL]. (2018?07?25)[2021?02?11]https://arxiv.org/pdf/1807.09562.
[23] ZAGORUYKO S, KOMODAKIS N. Learning to compare image patches via convolutional neural networks[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA, 2015:4353-4361.
[24] KRINIDIS S, CHATZIS V. A robust fuzzy local information C-means clustering algorithm[J]. IEEE transactions on image processing, 2010, 19(5):1328-1337.
[25] LEI Tao, JIA Xiaohong, ZHANG Yanning, et al. Significantly fast and robust fuzzy C-means clustering algorithm based on morphological reconstruction and membership filtering[J]. IEEE transactions on fuzzy systems, 2018, 26(5):3027-3041.
[26] 雷涛, 张肖, 加小红, 等. 基于模糊聚类的图像分割研究进展[J]. 电子学报, 2019, 47(8):1776-1791
LEI Tao, ZHANG Xiao, JIA Xiaohong, et al. Research progress on image segmentation based on fuzzy clustering[J]. Acta electronica sinica, 2019, 47(8):1776-1791

备注/Memo

备注/Memo:
收稿日期:2021-03-08。
基金项目:国家自然科学基金项目(61871259,61861024);陕西省杰出青年科学基金项目(2021JC-47);陕西省重点研发计划项目(2021ZDLGY08-07)
作者简介:雷涛,教授,博士生导师,陕西科技大学电子信息与人工智能学院副院长,IEEE高级会员,主要研究方向为计算机视觉、机器学习。发表学术论文90余篇;王洁,硕士研究生,主要研究方向为遥感影像分析、深度学习;薛丁华,博士研究生,主要研究方向为遥感影像分析、深度学习
通讯作者:雷涛.E-mail:leitaoly@163.com
更新日期/Last Update: 2021-06-25