用于高分辨率遥感影像度量变化检测的多路径非对称融合网络

闫利; 李希

doi:10.12263/DZXB.20221071

您当前的位置：

首页 >

文章列表页 >

用于高分辨率遥感影像度量变化检测的多路径非对称融合网络

学术论文 | 更新时间：2025-12-08

- 用于高分辨率遥感影像度量变化检测的多路径非对称融合网络
- MAFNet: A Multi-Path Asymmetric Fusion Network for Metric-Based Change Detection in High-Resolution Remote Sensing Images
- 电子学报 2023年51卷第7期页码：1781-1790
- 作者机构：
  
  武汉大学测绘学院，湖北武汉 430079
- 作者简介：
  
  [ "闫利男，1966年8月出生，山西山阴人. 现为武汉大学测绘学院教授、博士生导师. 主要研究方向是摄影测量与遥感、图像理解与分析、精密图像测量.E-mail: lyan@sgg.whu.edu.cn" ]
  [ "李希（通讯作者）女，1994年1月出生，山东菏泽人. 现为武汉大学测绘学院博士研究生. 主要研究方向是遥感影像变化检测、多时相SAR干涉测量与形变监测.E-mail: lixi2019@whu.edu.cn" ]
- 基金信息：
  
  国家重点研发计划(2020YFD1100203);湖北省科技重大专项(2021AAA010)
- DOI：10.12263/DZXB.20221071
  中图分类号： P237
- 收稿：2022-09-20，
  
  修回：2023-05-21，
  
  纸质出版：2023-07-25
- 稿件说明：
移动端阅览
闫利,李希.用于高分辨率遥感影像度量变化检测的多路径非对称融合网络[J].电子学报,2023,51(07):1781-1790.

YAN Li,LI Xi.MAFNet: A Multi-Path Asymmetric Fusion Network for Metric-Based Change Detection in High-Resolution Remote Sensing Images[J].ACTA ELECTRONICA SINICA,2023,51(07):1781-1790.
闫利,李希.用于高分辨率遥感影像度量变化检测的多路径非对称融合网络[J].电子学报,2023,51(07):1781-1790. DOI： 10.12263/DZXB.20221071.

YAN Li,LI Xi.MAFNet: A Multi-Path Asymmetric Fusion Network for Metric-Based Change Detection in High-Resolution Remote Sensing Images[J].ACTA ELECTRONICA SINICA,2023,51(07):1781-1790. DOI： 10.12263/DZXB.20221071.

摘要

现有的基于深度学习的度量变化检测方法侧重于高级变化语义特征的提取，难以捕获细粒度地物的变化，检测的变化边界模糊.一些方法引入了包含高分辨率和细节特征的低级视觉特征，但这些特征更容易受到内部细节等伪变化的干扰，缺少可靠的远程依赖关系.针对上述问题，提出了一种基于深度学习的端到端的度量变化检测网络，称为用于高分辨率遥感影像度量变化检测的多路径非对称融合网络（Multi-path Asymmetric Fusion network，MAFNet），可以检测到更清晰的边界和更完整的细粒度地物.MAFNet提出了一种多路径非对称融合网络用于捕获长短路径依赖关系，用细粒度的低级视觉特征细化粗略的高级语义特征.MAFNet提出了一种基于深度监督的度量模块，获取更具判别力的特征，端对端的测量变化.实验表明，与其他6种基准方法相比，MAFNet网络在SYSU数据集和CDD数据集上都实现了最高的精度，F1分别为80.56%，95.02%.

Abstract

Existing deep learning-based metric change detection methods focus on the extraction of high-level change semantic features

which is difficult to capture changes in fine-grained targets

and the detected change boundaries are blurred. Some methods introduce low-level visual features containing high-resolution and detailed features

but these features are more susceptible to interference from pseudo-change such as internal details and lack reliable long-range dependencies. In response to the above problems

an end-to-end metric-based change detection network based on deep learning is proposed

named multi-path asymmetric fusion network (MAFNet) for metric-based change detection in high resolution remote sensing images

which can detect sharper boundaries and more complete fine-grained targets. MAFNet proposes a multi-path asymmetric fusion network to capture long and short range dependencies

and refine coarse high-level semantic features with fine-grained low-level visual features. MAFNet proposes a metric module based on deep supervision to obtain more discriminative features and end-to-end measure changes. Experiments show that compared with other six benchmark methods

MAFNet achieves the highest accuracy on both the SYSU dataset and the CDD dataset

with F1 scores at 80.56% and 95.02%

respectively.

关键词

Keywords

references

SINGH A . Review article digital change detection techniques using remotely-sensed data [J]. International Journal of Remote Sensing , 1989 , 10 ( 6 ): 989 - 1003 .

PEDUZZI P . The disaster risk, global change, and sustainability nexus [J]. Sustainability , 2019 , 11 ( 4 ): 957 .

张良培 , 武辰 . 多时相遥感影像变化检测的现状与展望 [J]. 测绘学报 , 2017 , 46 ( 10 ): 1447 - 1459 .

ZHANG L P , WU C . Advance and future development of change detection for multi-temporal remote sensing imagery [J]. Acta Geodaetica et Cartographica Sinica , 2017 , 46 ( 10 ): 1447 - 1459 . (in Chinese)

眭海刚 , 冯文卿 , 李文卓 , 等 . 多时相遥感影像变化检测方法综述 [J]. 武汉大学学报(信息科学版) , 2018 , 43 ( 12 ): 1885 - 1898 .

SUI H G , FENG W Q , LI W Z , et al . Review of change detection methods for multi-temporal remote sensing imagery [J]. Geomatics and Information Science of Wuhan University , 2018 , 43 ( 12 ): 1885 - 1898 . (in Chinese)

BRUNNER D , LEMOINE G , BRUZZONE L . Earthquake damage assessment of buildings using VHR optical and SAR imagery [J]. IEEE Transactions on Geoscience and Remote Sensing , 2010 , 48 ( 5 ): 2403 - 2420 .

HUSSAIN M , CHEN D , CHENG A , et al . Change detection from remotely sensed images: From pixel-based to object-based approaches [J]. ISPRS Journal of Photogrammetry and Remote Sensing , 2013 , 80 : 91 - 106 .

DEMIR B , BOVOLO F , BRUZZONE L . Updating land-cover maps by classification of image time series: A novel change-detection-driven transfer learning approach [J]. IEEE Transactions on Geoscience and Remote Sensing , 2013 , 51 ( 1 ): 300 - 312 .

WANG D C , CHEN X N , JIANG M Y , et al . ADS-Net: An attention-based deeply supervised network for remote sensing image change detection [J]. International Journal of Applied Earth Observation and Geoinformation , 2021 , 101 : 102348 .

肖进胜 , 张舒豪 , 陈云华 , 等 . 双向特征融合与特征选择的遥感影像目标检测 [J]. 电子学报 , 2022 , 50 ( 2 ): 267 - 272 .

XIAO J S , ZHANG S H , CHEN Y H , et al . Remote sensing image object detection based on bidirectional feature fusion and feature selection [J]. Acta Electronica Sinica , 2022 , 50 ( 2 ): 267 - 272 . (in Chinese)

刘国强 , 房胜 , 李哲 . 用于遥感图像变化检测的全尺度特征聚合网络 [J]. 北京航空航天大学学报 , 2022 , 48 ( 8 ): 1464 - 1470 .

LIU G Q , FANG S , LI Z . A full-scale feature aggregation network for remote sensing image change detection [J]. Journal of Beijing University of Aeronautics and Astronautics , 2022 , 48 ( 8 ): 1464 - 1470 . (in Chinese)

王鑫 , 张香梁 , 吕国芳 . 基于融合边缘变化信息全卷积神经网络的遥感图像变化检测 [J]. 电子与信息学报 , 2022 , 44 ( 5 ): 1694 - 1703 .

WANG X , ZHANG X L , LÜ G F . Remote sensing image change detection based on fully convolutional neural networks with edge change information [J]. Journal of Electronics & Information Technology , 2022 , 44 ( 5 ): 1694 - 1703 . (in Chinese)

PENG D F , ZHANG Y J , GUAN H Y . End-to-end change detection for high resolution satellite images using improved UNet++ [J]. Remote Sensing , 2019 , 11 ( 11 ): 1382 .

ZHAN Y , FU K , YAN M L , 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 .

HEDJAM R , ABDESSELAM A , MELGANI F . Change detection in unlabeled optical remote sensing data using Siamese CNN [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2020 , 13 : 4178 - 4187 .

LONG J , SHELHAMER E , DARRELL T . Fully convolutional networks for semantic segmentation [C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2015 : 3431 - 3440 .

ZHENG Z , WAN Y , ZHANG Y J , et al . CLNet: Cross-layer convolutional neural network for change detection in optical remote sensing imagery [J]. ISPRS Journal of Photogrammetry and Remote Sensing , 2021 , 175 : 247 - 267 .

ZHANG M Y , XU G L , CHEN K M , et al . Triplet-based semantic relation learning for aerial remote sensing image change detection [J]. IEEE Geoscience and Remote Sensing Letters , 2019 , 16 ( 2 ): 266 - 270 .

CHEN J , YUAN Z Y , PENG J , et al . DASNet: Dual attentive fully convolutional Siamese networks for change detection in high-resolution satellite images [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2020 , 14 : 1194 - 1206 .

CHEN H , SHI Z W . A spatial-temporal attention-based method and a new dataset for remote sensing image change detection [J]. Remote Sensing , 2020 , 12 ( 10 ): 1662 .

SHI Q , LIU M X , LI S C , et al . A deeply supervised attention metric-based network and an open aerial image dataset for remote sensing change detection [J]. IEEE Transactions on Geoscience and Remote Sensing , 2021 , 60 : 1 - 16 .

LEE H , LEE K , KIM J H , et al . Local similarity Siamese network for urban land change detection on remote sensing images [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2021 , 14 : 4139 - 4149 .

GUO E Q , FU X S , ZHU J W , et al . Learning to measure change: Fully convolutional siamese metric networks for scene change detection [EB/OL]. ( 2018 )[2022]. https://doi.org/10.48550/arXiv.1810.09111 https://doi.org/10.48550/arXiv.1810.09111 .

LEBEDEV M A , VIZILTER Y V , VYGOLOV O V , et al . Change detection in remote sensing images using conditional adversarial networks [J]. International Archives of the Photogrammetry , Remote Sensing & Spatial Information Sciences, 2018 , 42 ( 2 ): 565 - 571 .

HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Seattle : IEEE , 2016 : 770 - 778 .

CHEN L C , PAPANDREOU G , SCHROFF F , et al . Rethinking atrous convolution for semantic image segmentation [EB/OL]. ( 2017 )[2022]. https://doi.org/10.48550/arXiv.1706.05587 https://doi.org/10.48550/arXiv.1706.05587 .

ZHU Z , XU M D , BAI S , et al . Asymmetric non-local neural networks for semantic segmentation [C]// Proceedings of the IEEE/CVF International Conference on Computer Vision . Seoul : IEEE , 2019 : 593 - 602 .

NEKRASOV V , SHEN C H , REID I . Light-weight refinenet for real-time semantic segmentation [EB/OL]. ( 2018 )[2022]. https://doi.org/10.48550/arXiv.1810.03272 https://doi.org/10.48550/arXiv.1810.03272 .

LIN G S , MILAN A , SHEN C H , et al . RefineNet: Multi-path refinement networks for high-resolution semantic segmentation [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 5168 - 5177 .

ZHANG C X , YUE P , TAPETE D , et al . A deeply supervised image fusion network for change detection in high resolution bi-temporal remote sensing images [J]. ISPRS Journal of Photogrammetry and Remote Sensing , 2020 , 166 : 183 - 200 .

DING Q , SHAO Z F , HUANG X , et al . DSA-Net: A novel deeply supervised attention-guided network for building change detection in high-resolution remote sensing images [J]. International Journal of Applied Earth Observation and Geoinformation , 2021 , 105 : 102591 .

CAYE DAUDT R , LE SAUX B , BOULCH A . Fully convolutional Siamese networks for change detection [C]// 2018 25th IEEE International Conference on Image Processing (ICIP) . Piscataway : IEEE , 2018 : 4063 - 4067 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向时序异常检测的可变视距多向扫描方法

基于稀疏平滑自蒸馏的差分隐私深度学习方法

基于非一般类算子融合方法及硬件架构设计

基于注意力融合多尺度特征的解压缩点云质量增强方法

基于深度压缩感知的联合信源信道编码方法研究