多尺度融合卷积神经网络支持下的SAR影像变化检测

doi:10.13474/j.cnki.11-2246.2023.0355

测绘通报 ›› 2023, Vol. 0 ›› Issue (12): 31-37.doi: 10.13474/j.cnki.11-2246.2023.0355

• 学术研究 • 上一篇

多尺度融合卷积神经网络支持下的SAR影像变化检测

段玉^1,2, 刘善伟^1,2, 万剑华^1,2, MUHAMMAD Yasir^1,2, 郑爽³

1. 中国石油大学(华东)海洋与空间信息学院, 山东青岛 266580;
2. 自然资源部海上丝绸之路海洋资源与环境网络观测技术创新中心, 山东青岛 266580;
3. 山东财经大学公共外语教学部, 山东济南 250014

收稿日期:2023-03-21 发布日期:2024-01-08
作者简介:段玉(1997-),女,硕士生,主要研究方向为SAR变化检测。E-mail:S20160046@upc.edu.cn
基金资助:
国家自然科学基金(41776182)

SAR image change detection based on multi-scale fusion convolutional neural network

DUAN Yu^1,2, LIU Shanwei^1,2, WAN Jianhua^1,2, MUHAMMAD Yasir^1,2, ZHENG Shuang³

1. College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, China;
2. Technology Innovation Center for Maritime Silk Road Marine Resources and Environment Networked Observation, Ministry of Natural Resources, Qingdao 266580, China;
3. School of Foreign Language Education, Shandong University of Finance and Economic, Jinan 250014, China

Received:2023-03-21 Published:2024-01-08

摘要/Abstract

摘要： 相干斑噪声的存在影响着合成孔径雷达(SAR)影像识别变化信息的能力。为了提高变化检测的准确性,必须充分考虑相干斑噪声的影响。本文提出了一种新的变化检测方法,利用联系上下文显著性提取方法,从差异图中提取潜在变化区域和背景信息,在保留图像主要纹理细节的同时去除背景噪声。针对当前变化检测方法特征表达不足的问题,设计了一种多尺度通道注意力模块squeeze,expand and excitation(SEE),在获取多感受野信息的同时强调重要信息,不至于产生信息冗余。在此基础上,提出了一种多尺度融合卷积神经网络——SEENet。SEENet将3个SEE模块残差连接,以实现信息的多级利用。通过在4个SAR真实数据集上的试验,验证了该方法的有效性。

关键词: 多尺度, SAR影像, 变化检测, SEENet

Abstract: The presence of speckle noise significantly affects the capability of synthetic aperture radar (SAR) image to recognize changing information. In order to enhance the accuracy of change detection, the influence of speckle noise must be adequately addressed. This study introduces a novel approach for change detection. Firstly, a context-aware saliency extraction method is employed to extract potential change regions and background information from the difference image. This process retains the main textural details of the image while removing background noise. A multi-scale channel attention module, the squeeze, expand, and excitation (SEE) module, is designed to address the issue of inadequate feature representation in current change detection methods. This module captures multi-scale information while emphasizing crucial details without introducing information redundancy.Building upon this foundation, a multi-scale fusion convolutional neural network called the squeeze, expand, and excitation network (SEENet) is proposed. SEENet connects three SEE modules through residual connections to achieve multi-level information utilization. Through experimentation on four real SAR datasets, the effectiveness of this method is validated.

Key words: multi-scale, SAR image, change detection, SEENet

中图分类号:

P237

段玉, 刘善伟, 万剑华, MUHAMMAD Yasir, 郑爽. 多尺度融合卷积神经网络支持下的SAR影像变化检测[J]. 测绘通报, 2023, 0(12): 31-37.

DUAN Yu, LIU Shanwei, WAN Jianhua, MUHAMMAD Yasir, ZHENG Shuang. SAR image change detection based on multi-scale fusion convolutional neural network[J]. Bulletin of Surveying and Mapping, 2023, 0(12): 31-37.

参考文献

[1] ZHAO Jixiang,LIU Shanwei,WAN Jianhua,et al. Change detection method of high resolution remote sensing image based on D-S evidence theory feature fusion [J]. IEEE Access,2021,9: 4673-4687.
[2] GENG J,MA X,ZHOU X,et al. Saliency-guided deep neural networks for SAR image change detection [J]. IEEE Transactions on Geoscience and Remote Sensing,2019,57(10): 7365-7377.
[3] LIU R,WANG R,HUANG J,et al. Change detection in SAR images using multiobjective optimization and ensemble strategy [J]. IEEE Geoscience and Remote Sensing Letters,2021,18: 1585-1589.
[4] 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.
[5] LEE J S. Digital image enhancement and noise filtering by use of local statistics[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1980,2(2): 165-168.
[6] KUAN D T,SAWCHUK A A,STRAND T C,et al. Adaptive noise smoothing filter for images with signal-dependent noise[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1985,7(2): 165-177.
[7] LIU Luyang,JIA Zhenhong,YANG Jie,et al. SAR image change detection based on mathematical morphology and the k-means clustering algorithm [J]. IEEE Access,2019,7: 43970-43978.
[8] BOVOLO F,BRUZZONE L. A detail-preserving scale-driven approach to change detection in multitemporal SAR images [J]. IEEE Transactions on Geoscience and Remote Sensing,2005,43(12): 2963-2972.
[9] INGLADA J,MERCIER G. A new statistical similarity measure for change detection in multitemporal SAR images and its extension to multiscale change analysis[J]. IEEE Transactions on Geoscience and Remote Sensing,2007,45(5): 1432-1445.
[10] LI H,GONG M,WANG Q,et al. A multiobjective fuzzy clustering method for change detection in SAR images [J]. Applied Soft Computing,2016,46: 767-777.
[11] LI Yangyang,PENG Cheng,CHEN Yanqiao,et al. A deep learning method for change detection in synthetic aperture radar images [J]. IEEE Transactions on Geoscience and Remote Sensing,2019,57(8): 5751-5763.
[12] ZHAN Yang,FU Kun,YAN Menglong,et al. Change detection based on deep siamese convolutional network for optical aerial images[J]. IEEE Geoscience and Remote Sensing Letters,2017,14(10): 1845-1849.
[13] GAO Feng,WANG Xiao,GAO Yunhao,et al. Sea ice change detection in SAR images based on convolutional-wavelet neural networks [J]. IEEE Geoscience and Remote Sensing Letters,2019,16(8): 1240-1244.
[14] LIU Tao,LI Ying,CAO Ying,et al. Change detection in multitemporal synthetic aperture radar images using dual-channel convolutional neural network [J]. Journal of Applied Remote Sensing,2017,11(4):1.
[15] HU J,SHEN L,ALBANIE S,et al. Squeeze-and-excitation networks[J]. IEEE Trans Pattern Anal Mach Intell,2020,42(8): 2011-2023.
[16] IANDOLA F N,HAN Song,MOSKEWICZ M W,et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size[EB/OL]. [2023-02-20]. https://arxiv.org/abs/1602.07360.
[17] GOFERMAN S,ZELNIK-MANOR L,TAL A. Context-aware saliency detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,34(10):1915-1926.
[18] LIU Fang,JIAO Licheng,TANG Xu,et al. Local restricted convolutional neural network for change detection in polarimetric SAR images[J]. IEEE Transactions on Neural Networks and Learning Systems,2019,30(3): 818-833.
[19] OTSU N. A threshold selection method from gray level histograms [J]. IEEE Transactions on Systems,Man,and Cybernetics,1979,9(1): 62-66.
[20] 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.
[21] HARALICK R M,SHANMUGAM K S,DINSTEIN I H. Textural features for image classification [J]. IEEE Transactions on Systems,Man and Cybernetics,1973,3(6): 610-621.
[22] MOSER G,SERPICO S B. Generalized minimum-error thresholding for unsupervised change detection from SAR amplitude imagery [C]//Proceedings of 2005 IEEE International Geoscience and Remote Sensing Symposium. Korea:IEEE,2005.
[23] GAO Feng,DONG Junyu,LI Bo,et al. Change detection from synthetic aperture radar images based on neighborhood-based ratio and extreme learning machine [J]. Journal of Applied Remote Sensing,2016,10(4):046019.
[24] 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.
[25] QU Xiaofan,GAO Feng,DONG Junyu,et al. Change detection in synthetic aperture radar images using a dual-domain network[J]. IEEE Geoscience and Remote Sensing Letters,2021,19:4012405.
[26] GAO Yunhao,GAO Feng,DONG Junyu,et al. SAR image change detection based on multiscale capsule network[J].IEEE Geoscience and Remote Sensing Letters,2020,18(3):484-488.

多尺度融合卷积神经网络支持下的SAR影像变化检测

SAR image change detection based on multi-scale fusion convolutional neural network

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张宝安, 高小龙, 金仔燕, 马兰花. 甘肃省地表要素遥感解译样本库建设与应用[J]. 测绘通报, 2023, 0(9): 144-149.
[2]	陈婕, 刘纪平, 徐胜华. 增强边缘信息的全卷积神经网络遥感影像建筑物变化检测[J]. 测绘通报, 2023, 0(6): 61-67.
[3]	沈鑫甦, 嵇灵. 面向遥感地类变化检测的U型深度学习神经网络改进方法[J]. 测绘通报, 2023, 0(6): 93-97,103.
[4]	王丽梅, 王延正. 基于高分辨率遥感影像的建筑物提取[J]. 测绘通报, 2023, 0(6): 180-183.
[5]	黄桦, 葛为燎, 刘微微, 钱荣荣, 李杰. 利用倾斜影像重建点云的建筑物变化检测[J]. 测绘通报, 2023, 0(5): 125-129.
[6]	齐建伟, 王伟峰, 张乐, 王光彦. 基于改进DeepLabV3+算法的遥感影像建筑物变化检测[J]. 测绘通报, 2023, 0(4): 145-149.
[7]	王本礼, 王也, 唐先龙, 董胜光. 遥感影像变化图斑智能化提取平台研发与应用[J]. 测绘通报, 2023, 0(2): 150-154.
[8]	付乐宜, 赵小阳, 吴凯华, 孙颖. 科学绿化地理场景的动态符号设计与多尺度表达[J]. 测绘通报, 2023, 0(11): 88-94.
[9]	王松伦, 马晓楠, 潘子轩. 基于遥感影像的生产建设项目扰动图斑人机协同智能提取方法[J]. 测绘通报, 2023, 0(11): 132-138.
[10]	李睿, 周晓光, 侯东阳. 基于正态分布的三维建筑物变化检测高度差阈值确定方法[J]. 测绘通报, 2022, 0(9): 98-104.
[11]	冯炜明, 张新长, 孙颖, 姜明, 甘巧, 侯幸幸. 融合Transformer结构的高分辨率遥感影像变化检测网络[J]. 测绘通报, 2022, 0(8): 36-40,92.
[12]	黄宇鸿, 周维勋. 高分辨率遥感影像场景变化检测的相似度方法[J]. 测绘通报, 2022, 0(8): 48-53.
[13]	柳林, 孙毅, 李万武. 基于CNN海上钻井平台检测模型的构建及训练算法分析[J]. 测绘通报, 2022, 0(7): 26-32,99.
[14]	李慧敏, 罗大伟, 窦世卿. 利用腾讯位置大数据进行多尺度人口空间化估算[J]. 测绘通报, 2022, 0(6): 93-97.
[15]	阮明浩, 卢永华, 刘玉贤, 汤圣君, 王伟玺, 张宇琦, 李游. 激光与倾斜点云精确配准与无缝融合[J]. 测绘通报, 2022, 0(4): 6-10.