基于特征分解卷积神经网络的SAR图像目标检测方法

李毅 杜兰 杜宇昂

李毅, 杜兰, 杜宇昂. 基于特征分解卷积神经网络的SAR图像目标检测方法[J]. 雷达学报, 2023, 12(5): 1069–1080. doi: 10.12000/JR23004
引用本文: 李毅, 杜兰, 杜宇昂. 基于特征分解卷积神经网络的SAR图像目标检测方法[J]. 雷达学报, 2023, 12(5): 1069–1080. doi: 10.12000/JR23004
LI Yi, DU Lan, and DU Yuang. Convolutional neural network based on feature decomposition for target detection in SAR images[J]. Journal of Radars, 2023, 12(5): 1069–1080. doi: 10.12000/JR23004
Citation: LI Yi, DU Lan, and DU Yuang. Convolutional neural network based on feature decomposition for target detection in SAR images[J]. Journal of Radars, 2023, 12(5): 1069–1080. doi: 10.12000/JR23004

基于特征分解卷积神经网络的SAR图像目标检测方法

doi: 10.12000/JR23004
基金项目: 国家自然科学基金(U21B2039)
详细信息
    作者简介:

    李 毅,博士生,主要研究方向为SAR图像解译、机器学习与人工智能等

    杜 兰,博士,教授,主要研究方向为雷达目标识别、雷达信号处理、机器学习等

    杜宇昂,博士生,主要研究方向为SAR图像解译、机器学习与人工智能等

    通讯作者:

    杜兰 dulan@mail.xidian.edu.cn

  • 责任主编:朱卫纲 Corresponding Editor: ZHU Weigang
  • 中图分类号: TN957.51

Convolutional Neural Network Based on Feature Decomposition for Target Detection in SAR Images

Funds: The National Natural Science Foundation of China (U21B2039)
More Information
  • 摘要: 真实场景的高分辨率合成孔径雷达(SAR)图像大多是复杂的,对于地物场景来说,其背景中存在草地、树木、道路和建筑物等杂波,这些复杂背景杂波使得传统SAR图像目标检测算法的结果包含大量虚警和漏警,严重影响了SAR目标检测性能。该文提出一种基于特征分解卷积神经网络(CNN)的SAR图像目标检测方法,该方法在特征提取模块对输入图像提取特征后,通过特征分解模块分解出鉴别特征和干扰特征,最后将鉴别特征输入到多尺度检测模块进行目标检测。特征分解后去除的干扰特征是对目标检测不利的部分,其中包括复杂背景杂波,而保留的鉴别特征是对目标检测有利的部分,其中包括感兴趣目标,从而有效降低虚警和漏警,提高SAR目标检测性能。该文所提方法在MiniSAR实测数据集和SAR飞机检测实测数据集(SADD)上的F1-score值分别为0.9357和0.9211,与不加特征分解模块的单步多框检测器相比,所提方法的F1-score值分别提升了0.0613和0.0639。基于实测数据集的实验结果证明了所提方法对复杂场景SAR图像进行目标检测的有效性。

     

  • 图  1  基于特征分解CNN的SAR图像目标检测流程图

    Figure  1.  Flow chart of SAR target detection method based on feature decomposition CNN

    图  2  特征分解模块结构图

    Figure  2.  Structure of feature decomposition module

    图  3  MiniSAR数据集中的两幅SAR图像

    Figure  3.  Two SAR images in the MiniSAR dataset

    图  4  SADD数据集中的样本图像[23]

    Figure  4.  Examples in the SADD[23]

    图  5  不同方法对MiniSAR数据集中第1张测试图片的检测结果

    Figure  5.  Detection results of the first test image in the MiniSAR dataset by different methods

    图  6  不同方法对MiniSAR数据集中第2张测试图片的检测结果

    Figure  6.  Detection results of the second test image in the MiniSAR dataset by different methods

    图  7  不同方法对SADD数据集中部分测试切片的检测结果

    Figure  7.  Detection results of some test chips in the SADD by different methods

    图  8  部分SAR子图像经过特征分解模块得到的鉴别特征图、干扰特征图和重构图

    Figure  8.  The discriminative feature maps and interfering feature maps and reconstruction maps obtained by the feature decomposition module for some SAR sub-images

    表  1  特征提取模块的详细结构

    Table  1.   Detailed structure of feature extraction module

    层数操作超参数
    1卷积,ReLUk = (3,3), s = 1, p = 1, n = 64
    2卷积,ReLUk = (3,3), s = 1, p = 1, n = 64
    3最大池化k = (2,2), s = 2, p = 0
    4卷积,ReLUk = (3,3), s = 1, p = 1, n = 128
    5卷积,ReLUk = (3,3), s = 1, p = 1, n = 128
    6最大池化k = (2,2), s = 2, p = 0
    7卷积,ReLUk = (3,3), s = 1, p = 1, n = 256
    8卷积,ReLUk = (3,3), s = 1, p = 1, n = 256
    9卷积,ReLUk = (3,3), s = 1, p = 1, n = 256
    10最大池化k = (2,2), s = 2, p = 0
    注:k, s, p, n分别为核尺寸、步长、填充数、核个数。
    下载: 导出CSV

    表  2  不同目标检测方法在MiniSAR数据集上的实验结果

    Table  2.   Experimental results of different target detection methods based on the MiniSAR dataset

    方法PrecisionRecallF1-score
    Gaussian-CFAR0.37890.79660.5135
    Faster R-CNN0.83700.91060.8723
    FPN0.86510.88620.8755
    SSD0.86290.88620.8744
    文献[25]的方法0.91340.94310.9280
    文献[26]的方法0.86860.93500.9006
    本文方法0.92060.95120.9357
    下载: 导出CSV

    表  3  不同目标检测方法在SADD数据集上的实验结果

    Table  3.   Experimental results of different target detection methods based on the SADD

    方法PrecisionRecallF1-score
    Gaussian-CFAR0.46100.52720.4919
    Faster R-CNN0.90360.80860.8535
    FPN0.85500.87030.8626
    SSD0.84640.86820.8572
    文献[26]的方法0.90140.87970.8904
    本文方法0.87880.96760.9211
    下载: 导出CSV

    表  4  消融实验结果

    Table  4.   Experimental results of ablation experiments

    实验编号损失定量评价
    正交损失重构损失PrecisionRecallF1-score
    1××0.86290.88620.8744
    2×0.90910.92680.9179
    3×0.89260.90240.8975
    40.92060.95120.9357
    下载: 导出CSV
  • [1] NOVAK L M, BURL M C, and IRVING W W. Optimal polarimetric processing for enhanced target detection[J]. IEEE Transactions on Aerospace and Electronic Systems, 1993, 29(1): 234–244. doi: 10.1109/7.249129
    [2] XING Xiangwei, CHEN Zhenlin, ZOU Huanxin, et al. A fast algorithm based on two-stage CFAR for detecting ships in SAR images[C]. The 2nd Asian-Pacific Conference on Synthetic Aperture Radar, Xi’an, China, 2009: 506–509.
    [3] LENG Xiangguang, JI Kefeng, YANG Kai, et al. A bilateral CFAR algorithm for ship detection in SAR images[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(7): 1536–1540. doi: 10.1109/LGRS.2015.2412174
    [4] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278–2324. doi: 10.1109/5.726791
    [5] HINTON G E and SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504–507. doi: 10.1126/science.1127647
    [6] KRIZHEVSKY A, SUTSKEVER I, and HINTON G E. ImageNet classification with deep convolutional neural networks[C]. The 25th International Conference on Neural Information Processing Systems, Lake Tahoe, USA, 2012: 1097–1105.
    [7] SIMONYAN K and ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]. 3rd International Conference on Learning Representations, San Diego, USA, 2015.
    [8] SZEGEDY C, LIU Wei, JIA Yangqing, et al. Going deeper with convolutions[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 1–9.
    [9] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 770–778.
    [10] GIRSHICK R. Fast R-CNN[C]. 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 1440–1448.
    [11] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]. The 28th International Conference on Neural Information Processing Systems, Montréal, Canada, 2015: 91–99.
    [12] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]. 14th European Conference on Computer Vision, Amsterdam, The Netherlands, 2016: 21–37.
    [13] NEUBECK A and VAN GOOL L. Efficient non-maximum suppression[C]. The 18th International Conference on Pattern Recognition, Hong Kong, China, 2006: 850–855.
    [14] 王思雨, 高鑫, 孙皓, 等. 基于卷积神经网络的高分辨率SAR图像飞机目标检测方法[J]. 雷达学报, 2017, 6(2): 195–203. doi: 10.12000/JR17009

    WANG Siyu, GAO Xin, SUN Hao, et al. An aircraft detection method based on convolutional neural networks in high-resolution SAR images[J]. Journal of Radars, 2017, 6(2): 195–203. doi: 10.12000/JR17009
    [15] WANG Zhaocheng, DU Lan, MAO Jiashun, et al. SAR target detection based on SSD with data augmentation and transfer learning[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(1): 150–154. doi: 10.1109/LGRS.2018.2867242
    [16] 李健伟, 曲长文, 彭书娟, 等. 基于卷积神经网络的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2018, 40(9): 1953–1959. doi: 10.3969/j.issn.1001-506X.2018.09.09

    LI Jianwei, QU Changwen, PENG Shujuan, et al. Ship detection in SAR images based on convolutional neural network[J]. Systems Engineering and Electronics, 2018, 40(9): 1953–1959. doi: 10.3969/j.issn.1001-506X.2018.09.09
    [17] ZHANG Shaoming, WU Ruize, XU Kunyuan, et al. R-CNN-based ship detection from high resolution remote sensing imagery[J]. Remote Sensing, 2019, 11(6): 631. doi: 10.3390/rs11060631
    [18] 陈慧元, 刘泽宇, 郭炜炜, 等. 基于级联卷积神经网络的大场景遥感图像舰船目标快速检测方法[J]. 雷达学报, 2019, 8(3): 413–424. doi: 10.12000/JR19041

    CHEN Huiyuan, LIU Zeyu, GUO Weiwei, et al. Fast detection of ship targets for large-scale remote sensing image based on a cascade convolutional neural network[J]. Journal of Radars, 2019, 8(3): 413–424. doi: 10.12000/JR19041
    [19] WEI Di, DU Yuang, DU Lan, et al. Target detection network for SAR images based on semi-supervised learning and attention mechanism[J]. Remote Sensing, 2021, 13(14): 2686. doi: 10.3390/RS13142686
    [20] GLOROT X, BORDES A, and BENGIO Y. Deep sparse rectifier neural networks[C]. The 14th International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, USA, 2011: 315–323.
    [21] 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.
    [22] GUTIERREZ D. MiniSAR: A review of 4-inch and 1-foot resolution Ku-band imagery[EB/OL]. https://www.sandia.gov/radar/Web/images/SAND2005-3706P-miniSAR-flight-SAR-images.pdf, 2005.
    [23] ZHANG Peng, XU Hao, TIAN Tian, et al. SEFEPNet: Scale expansion and feature enhancement pyramid network for SAR aircraft detection with small sample dataset[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 3365–3375. doi: 10.1109/JSTARS.2022.3169339
    [24] LIN Tsungyi, DOLLÁR Piotr, GIRSHICK Ross, et al. Feature pyramid networks for object detection[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 936–944.
    [25] LI Lu, DU Yuang, and DU Lan. Vehicle target detection network in SAR images based on rectangle-invariant rotatable convolution[J]. Remote Sensing, 2022, 14(13): 3086. doi: 10.3390/rs14133086
    [26] 杜兰, 王梓霖, 郭昱辰, 等. 结合强化学习自适应候选框挑选的SAR目标检测方法[J]. 雷达学报, 2022, 11(5): 884–896. doi: 10.12000/JR22121

    DU Lan, WANG Zilin, GUO Yuchen, et al. Adaptive region proposal selection for SAR target detection using reinforcement learning[J]. Journal of Radars, 2022, 11(5): 884–896. doi: 10.12000/JR22121
  • 加载中
图(8) / 表(4)
计量
  • 文章访问数:  1390
  • HTML全文浏览量:  703
  • PDF下载量:  387
  • 被引次数: 0
出版历程
  • 收稿日期:  2023-01-06
  • 修回日期:  2023-03-25
  • 网络出版日期:  2023-04-18
  • 刊出日期:  2023-10-28

目录

    AI智能问答

        /

        返回文章
        返回