高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

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

王鑫 张香梁 吕国芳

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. doi: 10.11999/JEIT210389
引用本文: 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. doi: 10.11999/JEIT210389
WANG Xin, ZHANG Xiangliang, LÜ Guofang. 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. doi: 10.11999/JEIT210389
Citation: WANG Xin, ZHANG Xiangliang, LÜ Guofang. 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. doi: 10.11999/JEIT210389

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

doi: 10.11999/JEIT210389
基金项目: 国家自然科学基金(51979085),江苏省 “六大人才高峰”高层次人才项目(XYDXX-007),江苏政府留学奖学金项目
详细信息
    作者简介:

    王鑫:女,1981年生,副教授,主要研究方向为图像处理、模式识别、计算机视觉、机器学习

    张香梁:女,1997年生,硕士生,研究方向为深度学习理论

    吕国芳:男,1962年生,副教授,主要研究方向为遥感图像处理和分析

    通讯作者:

    王鑫 wang_xin@hhu.edu.cn

  • 中图分类号: TN911.73; TP394.1

Remote Sensing Image Change Detection Based on Fully Convolutional Neural Networks with Edge Change Information

Funds: The National Natural Science Foundation of China (51979085), The Six Talents Peak Project of Jiangsu Province (XYDXX-007), Jiangsu Province Government Scholarship for Studying Abroad
  • 摘要: 高分辨率遥感图像变化检测是了解地表变化的关键,是遥感图像处理领域的一个重要分支。现有很多基于深度学习的变化检测方法,取得了良好的效果,但是不易获得高分辨率遥感图像中的结构细节且检测精度有待提高。因此,该文提出融合了边缘变化信息和通道注意力模块的网络框架(EANet),分为边缘结构变化信息检测、深度特征提取和变化区域判别3个模块。首先,为了得到双时相图像的边缘变化信息,对其进行边缘检测得到边缘图,并将边缘图相减得到边缘差异图;其次,考虑到高分辨率遥感图像精细的图像细节和复杂的纹理特征,为了充分提取单个图像的深度特征,构建基于VGG-16网络的3支路模型,分别提取双时相图像和边缘差异图的深度特征;最后,为了提高检测精度,提出将通道注意力机制嵌入到模型中,以关注信息量大的通道特征来更好地进行变化区域的判别。实验结果表明,无论从视觉解释或精度衡量上看,提出算法与目前已有的一些方法相比,具有一定的优越性。
  • 图  1  本文所提方法的总体框架

    图  2  SE模块结构示意图

    图  3  不同网络架构的变化检测定性结果对比

    图  4  不同的网络架构在训练集和测试集上Loss曲线与F1曲线对比

    图  5  不同算法的变化检测定性结果对比

    图  6  不同算法在训练集和测试集上Loss曲线与F1曲线对比

    表  1  不同网络架构的变化检测定量结果对比(%)

    架构AccRecallPrecisionF1
    BASIC99.6390.7795.1592.91
    BSE99.6691.5095.6793.54
    本文EANet99.6792.3595.3893.85
    下载: 导出CSV

    表  2  不同算法的变化检测定量结果对比(%)

    算法 AccRecallPrecisionF1
    PCA-Kmeans90.5710.9510.0910.50
    Unet++98.4192.3763.9875.60
    DSIFN99.6491.7894.5493.14
    本文99.6792.3595.3893.85
    下载: 导出CSV

    表  3  不同算法的计算效率结果对比

    算法 FLOPs(G)Params(M)训练时间(ms)
    Unet++38.119.2095.86
    DSIFN63.0050.44115.35
    本文86.2070.85129.23
    下载: 导出CSV
  • [1] 徐从安, 吕亚飞, 张筱晗, 等. 基于双重注意力机制的遥感图像场景分类特征表示方法[J]. 电子与信息学报, 2021, 43(3): 683–691. doi: 10.11999/JEIT200568

    XU Congan, LÜ Yafei, ZHANG Xiaohan, et al. A discriminative feature representation method based on dual attention mechanism for remote sensing image scene classification[J]. Journal of Electronics &Information Technology, 2021, 43(3): 683–691. doi: 10.11999/JEIT200568
    [2] LYU H, LU Hui, MOU Lichao, et al. Long-term annual mapping of four cities on different continents by applying a deep information learning method to Landsat data[J]. Remote Sensing, 2018, 10(3): 471. doi: 10.3390/rs10030471
    [3] 冀广宇, 梁兴东, 董勇伟, 等. 基于体散射约束的极化SAR相干变化检测方法[J]. 电子与信息学报, 2018, 40(10): 2461–2469. doi: 10.11999/JEIT180035

    JI Guangyu, LIANG Xingdong, DONG Yongwei, et al. Polarimetric SAR coherent change detection method based on volume scattering constraint[J]. Journal of Electronics &Information Technology, 2018, 40(10): 2461–2469. doi: 10.11999/JEIT180035
    [4] HUANG Fenghua, YU Ying, and FENG Tinghao. Automatic building change image quality assessment in high resolution remote sensing based on deep learning[J]. Journal of Visual Communication and Image Representation, 2019, 63: 102585. doi: 10.1016/j.jvcir.2019.102585
    [5] CHEN Jin, CHEN Xuehong, CUI Xihong, et al. Change vector analysis in posterior probability space: A new method for land cover change detection[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(2): 317–321. doi: 10.1109/LGRS.2010.2068537
    [6] LV Zhiyong, LIU Tongfei, SHI Cheng, et al. Novel land cover change detection method based on k-Means clustering and adaptive majority voting using bitemporal remote sensing images[J]. IEEE Access, 2019, 7: 34425–34437. doi: 10.1109/ACCESS.2019.2892648
    [7] MALPICA J A, ALONSO M C, PAPÍ F, et al. Change detection of buildings from satellite imagery and lidar data[J]. International Journal of Remote Sensing, 2013, 34(5): 1652–1675. doi: 10.1080/01431161.2012.725483
    [8] QIN Rongjun, HUANG Xin, GRUEN A, et al. Object-based 3-D building change detection on multitemporal stereo images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015, 8(5): 2125–2137. doi: 10.1109/JSTARS.2015.2424275
    [9] SAHA S, BOVOLO F, and BRUZZONE L. Unsupervised deep change vector analysis for multiple-change detection in VHR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(6): 3677–3693. doi: 10.1109/TGRS.2018.2886643
    [10] CHEN Hongruixuan, WU Chen, DU Bo, et al. Deep siamese multi-scale convolutional network for change detection in multi-temporal VHR images[C]. The 2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images, Shanghai, China, 2019: 1–4.
    [11] LONG J, SHELHAMER E, and DARRELL T. Fully convolutional networks for semantic segmentation[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 3431–3440.
    [12] LAN Lingxiang, WU Dong, and CHI Mingmin. Multi-temporal change detection based on deep semantic segmentation networks[C]. The 2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images, Shanghai, China, 2019: 1–4.
    [13] PENG Daifeng, ZHANG Yongjun, and GUAN Haiyan. End-to-end change detection for high resolution satellite images using improved UNet++[J]. Remote Sensing, 2019, 11(11): 1382. doi: 10.3390/rs11111382
    [14] HOU Bin, WANG Yunhong, and LIU Qingjie. Change detection based on deep features and low rank[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(12): 2418–2422. doi: 10.1109/LGRS.2017.2766840
    [15] DAUDT R C, LE SAUX B, and BOULCH A. Fully convolutional siamese networks for change detection[C]. The 2018 25th IEEE International Conference on Image Processing, Athens, Greece, 2018: 4063–4067.
    [16] ZHANG Chenxiao, YUE Peng, 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. doi: 10.1016/j.isprsjprs.2020.06.003
    [17] JIANG Huiwei, HU Xiangyun, LI Kun, et al. PGA-SiamNet: Pyramid feature-based attention-guided Siamese network for remote sensing orthoimagery building change detection[J]. Remote Sensing, 2020, 12(3): 484. doi: 10.3390/rs12030484
    [18] RONNEBERGER O, FISCHER P, and BROX T. U-Net: Convolutional networks for biomedical image segmentation[C]. The 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 2015: 234–241.
    [19] CANNY J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI-8(6): 679–698. doi: 10.1109/TPAMI.1986.4767851
    [20] SIMONYAN K and ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]. The 3rd International Conference on Learning Representations, San Diego, USA, 2015: 1790–2022.
    [21] DENG Jia, DONG Wei, SOCHER R, et al. ImageNet: A large-scale hierarchical image database[C]. 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009: 248–255.
    [22] HU Jie, SHEN Li, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011–2023. doi: 10.1109/TPAMI.2019.2913372
    [23] 倪黎, 邹卫军. 基于SE模块改进Xception的动物种类识别[J]. 导航与控制, 2020, 19(2): 106–111. doi: 10.3969/j.issn.1674-5558.2020.02.015

    NI Li and ZOU Weijun. Recognition of animal species based on improved Xception by SE module[J]. Navigation and Control, 2020, 19(2): 106–111. doi: 10.3969/j.issn.1674-5558.2020.02.015
    [24] CHEN Hao and SHI Zhenwei. A spatial-temporal attention-based method and a new dataset for remote sensing image change detection[J]. Remote Sensing, 2020, 12(10): 1662. doi: 10.3390/rs12101662
  • 加载中
图(6) / 表(3)
计量
  • 文章访问数:  681
  • HTML全文浏览量:  476
  • PDF下载量:  170
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-05-07
  • 修回日期:  2021-09-23
  • 录用日期:  2021-09-23
  • 网络出版日期:  2021-12-24
  • 刊出日期:  2022-05-25

目录

    /

    返回文章
    返回