Turn off MathJax
Article Contents
Article Navigation >  Journal of Radars  > 2024  > Proofreading [2nd]
SUN Xiaokun, YUN Zekai, HU Canbin, et al. End-to-end registration algorithm for high-resolution multi-view SAR images[J]. Journal of Radars, in press. doi: 10.12000/JR24211
Citation: SUN Xiaokun, YUN Zekai, HU Canbin, et al. End-to-end registration algorithm for high-resolution multi-view SAR images[J]. Journal of Radars, in press. doi: 10.12000/JR24211
shu

End-to-end Registration Algorithm for High-resolution Multi-view SAR Images

DOI: 10.12000/JR24211

  • College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China

Funds:  The Fundamental Research Funds for the Central Universities (buctrc202218), The Fundamental Research Funds for the Central Universities of Beijing University of Chemical Technology (ZY2413)
More Information
  • Corresponding author: HU Canbin, canbinhu@163.com
  • Received Date: 2024-10-22
  • Rev Recd Date: 2024-12-12
    • Available Online: 2024-12-14
    Abstract
  • Due to the side-looking and coherent imaging mechanisms, feature differences between high-resolution Synthetic Aperture Radar (SAR) images increase when the imaging viewpoint changes considerably, making image registration highly challenging. Traditional registration techniques for high-resolution multiview SAR images mainly face issues, such as insufficient keypoint localization accuracy and low matching precision. This work designs an end-to-end high-resolution multiview SAR image registration network to address the above challenges. The main contributions of this study include the following: A high-resolution SAR image feature extraction method based on a local pixel offset model is proposed. This method introduces a diversity peak loss to guide response weight allocation in the keypoint extraction network and optimizes keypoint coordinates by detecting pixel offsets. A descriptor extraction method is developed based on adaptive adjustment of convolution kernel sampling positions that utilizes sparse cross-entropy loss to supervise descriptor matching in the network. Experimental results show that compared with other registration methods, the proposed algorithm achieves substantial improvements in the high-resolution adjustment of convolution kernel sampling positions, which utilize sparse cross-entropy loss to supervise descriptor matching in the network. Experimental results illustrate that compared with other registration methods, the proposed algorithm achieves remarkable improvements in high-resolution multiview SAR image registration, with an average error reduction of over 65%, 3–5-fold increases in the number of correctly matched point pairs, and an average reduction of over 50% in runtime.

     

    • FullText(HTML)
  • loading
    • References(42)
  • [1]
    黄钟泠, 姚西文, 韩军伟. 面向SAR图像解译的物理可解释深度学习技术进展与探讨[J]. 雷达学报, 2022, 11(1): 107–125. doi: 10.12000/JR21165.

    HUANG Zhongling, YAO Xiwen, and HAN Junwei. Progress and perspective on physically explainable deep learning for synthetic aperture radar image interpretation[J]. Journal of Radars, 2022, 11(1): 107–125. doi: 10.12000/JR21165.
    [2]
    徐真, 王宇, 李宁, 等. 一种基于CNN的SAR图像变化检测方法[J]. 雷达学报, 2017, 6(5): 483–491. doi: 10.12000/JR17075.

    XU Zhen, WANG R, LI Ning, et al. A novel approach to change detection in SAR images with CNN classification[J]. Journal of Radars, 2017, 6(5): 483–491. doi: 10.12000/JR17075.
    [3]
    王志豪, 李刚, 蒋骁. 基于光学和SAR遥感图像融合的洪灾区域检测方法[J]. 雷达学报, 2020, 9(3): 539–553. doi: 10.12000/JR19095.

    WANG Zhihao, LI Gang, and JIANG Xiao. Flooded area detection method based on fusion of optical and SAR remote sensing images[J]. Journal of Radars, 2020, 9(3): 539–553. doi: 10.12000/JR19095.
    [4]
    洪文, 王彦平, 林赟, 等. 新体制SAR三维成像技术研究进展[J]. 雷达学报, 2018, 7(6): 633–654. doi: 10.12000/JR18109.

    HONG Wen, WANG Yanping, LIN Yun, et al. Research progress on three-dimensional SAR imaging techniques[J]. Journal of Radars, 2018, 7(6): 633–654. doi: 10.12000/JR18109.
    [5]
    丁赤飚, 刘佳音, 雷斌, 等. 高分三号SAR卫星系统级几何定位精度初探[J]. 雷达学报, 2017, 6(1): 11–16. doi: 10.12000/JR17024.

    DING Chibiao, LIU Jiayin, LEI Bin, et al. Preliminary exploration of systematic geolocation accuracy of GF-3 SAR satellite system[J]. Journal of Radars, 2017, 6(1): 11–16. doi: 10.12000/JR17024.
    [6]
    XIANG Yuming, PENG Lingxiao, WANG Feng, et al. Fast registration of multiview slant-range SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19(3): 4007505. doi: 10.1109/LGRS.2020.3045099.
    [7]
    WEI S and LAI Shanghong. Fast template matching based on normalized cross correlation with adaptive multilevel winner update[J]. IEEE Transactions on Image Processing, 2008, 17(11): 2227–2235. doi: 10.1109/TIP.2008.2004615.
    [8]
    WANG Fei and VEMURI B C. Non-rigid multi-modal image registration using cross-cumulative residual entropy[J]. International Journal of Computer Vision, 2007, 74(2): 201–215. doi: 10.1007/s11263-006-0011-2.
    [9]
    DELLINGER F, DELON J, GOUSSEAU Y, et al. SAR-SIFT: A SIFT-like algorithm for SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(1): 453–466. doi: 10.1109/TGRS.2014.2323552.
    [10]
    项德良, 徐益豪, 程建达, 等. 一种基于特征交汇关键点检测和Sim-CSPNet的SAR图像配准算法[J]. 雷达学报, 2022, 11(6): 1081–1097. doi: 10.12000/JR22110.

    XIANG Deliang, XU Yihao, CHENG Jianda, et al. An algorithm based on a feature interaction-based keypoint detector and sim-CSPNet for SAR image registration[J]. Journal of Radars, 2022, 11(6): 1081–1097. doi: 10.12000/JR22110.
    [11]
    LIAO Furong, CHEN Yan, CHEN Yunping, et al. SAR image registration based on optimized ransac algorithm with mixed feature extraction[C]. 2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, USA, 2020: 1153–1156. doi: 10.1109/IGARSS39084.2020.9323180.
    [12]
    DENG Yang and DENG Yunkai. Two-step matching approach to obtain more control points for SIFT-like very-high-resolution SAR image registration[J]. Sensors, 2023, 23(7): 3739. doi: 10.3390/s23073739.
    [13]
    XIANG Deliang, XIE Yuzhen, CHENG Jianda, et al. Optical and SAR image registration based on feature decoupling network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5235913. doi: 10.1109/TGRS.2022.3211858.
    [14]
    XIANG Yuming, JIAO Niangang, LIU Rui, et al. A geometry-aware registration algorithm for multiview high-resolution SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5234818. doi: 10.1109/TGRS.2022.3205382.
    [15]
    GUO Qiangliang, XIAO Jin, HU Xiaoguang, et al. Local convolutional features and metric learning for SAR image registration[J]. Cluster Computing, 2019, 22(2): 3103–3114. doi: 10.1007/s10586-018-1946-0.
    [16]
    FAN Jianwei, WU Yan, WANG Fan, et al. SAR image registration using phase congruency and nonlinear diffusion-based SIFT[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(3): 562–566. doi: 10.1109/LGRS.2014.2351396.
    [17]
    FAN Yibo, WANG Feng, and WANG Haipeng. A transformer-based coarse-to-fine wide-swath SAR image registration method under weak texture conditions[J]. Remote Sensing, 2022, 14(5): 1175. doi: 10.3390/rs14051175.
    [18]
    ELWAN M, AMEIN A S, MOUSA A, et al. SAR image matching based on local feature detection and description using convolutional neural network[J]. Security and Communication Networks, 2022, 2022(1): 5669069. doi: 10.1155/2022/5669069.
    [19]
    MEN Peng, GUO Hao, AN Jubai, et al. An improved L2Net for repetitive texture image registration with intensity difference heterogeneous SAR images[J]. Remote Sensing, 2022, 14(11): 2527. doi: 10.3390/rs14112527.
    [20]
    ZHANG Yifan, LI Zhiwei, WANG Wen, et al. A robust registration method for multi-view SAR images based on best buddy similarity[C]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Changsha, China, 2024: 881–886. doi: 10.5194/isprs-archives-XLVIII-1-2024-881-2024.
    [21]
    LI Zeyi, ZHANG Haitao, and HUANG Yihang. A rotation-invariant optical and SAR image registration algorithm based on deep and Gaussian features[J]. Remote Sensing, 2021, 13(13): 2628. doi: 10.3390/rs13132628.
    [22]
    YU Wei, SUN Xiaohuai, YANG Kuiyuan, et al. Hierarchical semantic image matching using CNN feature pyramid[J]. Computer Vision and Image Understanding, 2018, 169: 40–51. doi: 10.1016/j.cviu.2018.01.001.
    [23]
    SAUVALLE B and DE LA FORTELLE A. Unsupervised multi-object segmentation using attention and soft-argmax[C]. 2023 IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, USA, 2023: 3267–3276. doi: 10.1109/WACV56688.2023.00328.
    [24]
    NUNES C F G and PÁDUA F L C. A local feature descriptor based on log-Gabor filters for keypoint matching in multispectral images[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(10): 1850–1854. doi: 10.1109/LGRS.2017.2738632.
    [25]
    HOSANG J, BENENSON R, and SCHIELE B. Learning non-maximum suppression[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 4507–4515. doi: 10.1109/CVPR.2017.685.
    [26]
    CHUNG S W, CHUNG J S, and KANG H G. Perfect match: Self-supervised embeddings for cross-modal retrieval[J]. IEEE Journal of Selected Topics in Signal Processing, 2020, 14(3): 568–576. doi: 10.1109/JSTSP.2020.2987720.
    [27]
    CHEN Feng, WU Fei, XU Jing, et al. Adaptive deformable convolutional network[J]. Neurocomputing, 2021, 453: 853–864. doi: 10.1016/j.neucom.2020.06.128.
    [28]
    KILIÇARSLAN S and CELIK M. RSigELU: A nonlinear activation function for deep neural networks[J]. Expert Systems with Applications, 2021, 174: 114805. doi: 10.1016/j.eswa.2021.114805.
    [29]
    XU Jin, LI Zishan, DU Bowen, et al. Reluplex made more practical: Leaky ReLU[C]. 2020 IEEE Symposium on Computers and Communications, Rennes, 2020: 1–7. doi: 10.1109/ISCC50000.2020.9219587.
    [30]
    LI Jiayuan, HU Qingwu, and AI Mingyao. RIFT: Multi-modal image matching based on radiation-variation insensitive feature transform[J]. IEEE Transactions on Image Processing, 2020, 29: 3296–3310. doi: 10.1109/TIP.2019.2959244.
    [31]
    GERMAIN H, BOURMAUD G, and LEPETIT V. S2DNet: Learning image features for accurate sparse-to-dense matching[C]. The 16th European Conference on Computer Vision, Glasgow, UK, 2020: 626–643. doi: 10.1007/978-3-030-58580-8_37.
    [32]
    JAMIN A and HUMEAU-HEURTIER A. (Multiscale) cross-entropy methods: A review[J]. Entropy, 2019, 22(1): 45. doi: 10.3390/e22010045.
    [33]
    YAMADA M, SIGAL L, RAPTIS M, et al. Cross-domain matching with squared-loss mutual information[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1764–1776. doi: 10.1109/TPAMI.2014.2388235.
    [34]
    ZHU Li and ZHU Chunqiang. Application of Hausdorff distance in image matching[C]. 2014 IEEE Workshop on Electronics, Computer and Applications, Ottawa, Canada, 2014: 97–100. doi: 10.1109/IWECA.2014.6845566.
    [35]
    HE Yueping, WANG Xueqian, ZHANG Yiming, et al. A novel loss function for optical and SAR image matching: Balanced positive and negative samples[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 4028805. doi: 10.1109/LGRS.2022.3225965.
    [36]
    JIA Weikuan, SUN Meili, LIAN Jian, et al. Feature dimensionality reduction: A review[J]. Complex & Intelligent Systems, 2022, 8(3): 2663–2693. doi: 10.1007/s40747-021-00637-x.
    [37]
    DETONE D, MALISIEWICZ T, and RABINOVICH A. SuperPoint: Self-supervised interest point detection and description[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, USA, 2018: 224–236. doi: 10.1109/CVPRW.2018.00060.
    [38]
    HAN Xufeng, LEUNG T, JIA Yangqing, et al. MatchNet: Unifying feature and metric learning for patch-based matching[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 3279–3286. doi: 10.1109/CVPR.2015.7298948.
    [39]
    HASHIMOTO M, ENOMOTO M, and FUKUSHIMA Y. Coseismic deformation from the 2008 Wenchuan, China, earthquake derived from ALOS/PALSAR images[J]. Tectonophysics, 2010, 491(1/4): 59–71. doi: 10.1016/j.tecto.2009.08.034.
    [40]
    GEUDTNER D, TORRES R, SNOEIJ P, et al. Sentinel-1 system capabilities and applications[C]. 2014 IEEE Geoscience and Remote Sensing Symposium, Quebec City, Canada, 2014: 1457–1460. doi: 10.1109/IGARSS.2014.6946711.
    [41]
    李志远, 郭嘉逸, 张月婷, 等. 基于自适应动量估计优化器与空变最小熵准则的SAR图像船舶目标自聚焦算法[J]. 雷达学报, 2022, 11(1): 83–94. doi: 10.12000/JR21159.

    LI Zhiyuan, GUO Jiayi, ZHANG Yueting, et al. A novel autofocus algorithm of ship target in SAR image based on the adaptive momentum estimation optimizer and space-variant minimum entropy criteria[J]. Journal of Radars, 2022, 11(1): 83–94. doi: 10.12000/JR21159.
    [42]
    苏娟, 李彬, 王延钊. 一种基于封闭均匀区域的SAR图像配准方法[J]. 电子与信息学报, 2016, 38(12): 3282–3288. doi: 10.11999/JEIT160141.

    SU Juan, LI Bin, and WANG Yanzhao. SAR image registration algorithm based on closed uniform regions[J]. Journal of Electronics & Information Technology, 2016, 38(12): 3282–3288. doi: 10.11999/JEIT160141.
    • Relative Articles
    • Supplements(0)
    • Cited By
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索
    Get Citation
    PDF
    XML
    Article views(88) PDF downloads(5) Cited by()
    Proportional views
    Related

    京ICP备20021838号-8   Supported by: Beijing Renhe Information Technology Co. Ltd     百度统计

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return