基于距离辅助的超宽带MIMO雷达图像人体姿态重构网络

宋永坤, 金添, 戴永鹏, 宋勇平, 周小龙

宋永坤, 金添, 戴永鹏, 宋勇平, 周小龙. 基于距离辅助的超宽带MIMO雷达图像人体姿态重构网络[J]. 信号处理, 2021, 37(8): 1355-1364. DOI: 10.16798/j.issn.1003-0530.2021.08.002
引用本文: 宋永坤, 金添, 戴永鹏, 宋勇平, 周小龙. 基于距离辅助的超宽带MIMO雷达图像人体姿态重构网络[J]. 信号处理, 2021, 37(8): 1355-1364. DOI: 10.16798/j.issn.1003-0530.2021.08.002
shu
SONG Yongkun, JIN Tian, DAI Yongpeng, SONG Yongping, ZHOU Xiaolong. Human pose reconstruction network based on ultra-wideband MIMO radar image with distance-assisted[J]. JOURNAL OF SIGNAL PROCESSING, 2021, 37(8): 1355-1364. DOI: 10.16798/j.issn.1003-0530.2021.08.002
Citation: SONG Yongkun, JIN Tian, DAI Yongpeng, SONG Yongping, ZHOU Xiaolong. Human pose reconstruction network based on ultra-wideband MIMO radar image with distance-assisted[J]. JOURNAL OF SIGNAL PROCESSING, 2021, 37(8): 1355-1364. DOI: 10.16798/j.issn.1003-0530.2021.08.002
shu

基于距离辅助的超宽带MIMO雷达图像人体姿态重构网络

  • 国防科技大学电子科学学院

  • 空军预警学院

基金项目: 国家自然科学基金（61971430）
详细信息

  • 中图分类号: TN959.1

Human pose reconstruction network based on ultra-wideband MIMO radar image with distance-assisted

  • College of Electronic Science and Technology, National University of Defense Technology

  • Air Force Early Warning Academy

摘要

    摘要
  • 摘要: 超宽带多输入多输出（Multiple-input Multiple-output, MIMO）雷达可以获取目标的多维信息，在目标探测和人体动作分类等方面有很大的优势。然而，在实际应用中，超宽带MIMO雷达获取的人体目标成像结果通常分辨率较低，抽象难懂，且目标距离越远雷达图像分辨率越低。针对以上问题，本文提出了一种基于距离辅助的超宽带MIMO雷达图像人体姿态重构网络，首先使用卷积神经网络提取人体目标成像的信号强度和空间位置特征，然后使用反卷积模块重构出人体目标的各个关节点位置。同时，考虑雷达成像结果随着距离的变远而恶化，本文将目标的距离作为辅助信息来选择合适的网络模型参数，进而提高姿态重构的精度。实验结果表明，本方法可以将抽象的人体目标雷达图像转化为易于理解的人体关节姿态，且有较好的姿态重构性能，极大增强了传统雷达图像的可视化性能。同时，距离信息的引入提高了姿态重构精度，有效克服了距离增大带来的影响。
    Abstract: Ultra-wideband multiple-input multiple-output (MIMO) radar can obtain multi-dimensional information of the target, and has great advantages in target detection and human motion classification. However, in practical application, the human target imaging results obtained by the ultra-wideband MIMO radar are usually low-resolution, and the farther the target distance is, the lower the resolution of radar image is, which is hard to understand. In response to the above problems, this paper proposes a distance-assisted ultra-wideband MIMO radar image human body pose reconstruction method. First, the convolutional neural network is used to extract the signal strength and spatial position characteristics of the human target imaging, and then the deconvolution modules are used to reconstruct the position of each joint point of the human target. At the same time, considering that the result of radar imaging deteriorates as the distance increases, the distance of the target is used as auxiliary information to select the appropriate network model parameters to improve the accuracy of pose reconstruction. Experimental results show that this method can convert abstract human target radar images into easy-to-understand human joint poses, and has excellent pose reconstruction performance, which greatly enhances the visualization performance of traditional radar images. Meanwhile, the introduction of distance information improves the accuracy of pose reconstruction and effectively overcomes the influence of distance increase.
    • HTML全文
    • 参考文献(18)
  • [1] Yarovoy A G , Ligthart L P , Matuzas J , et al. UWB radar for human being detection[J]. IEEE Aerospace & Electronic Systems Magazine, 2008, 23(5):36-40.
    [2] Ma Y , Liang F , Wang P , et al. An Accurate Method to Distinguish Between Stationary Human and Dog Targets Under Through-Wall Condition Using UWB Radar[J]. Remote Sensing, 2019, 11(21).
    [3] Qi F , Lv H , Liang F , et al. MHHT-Based Method for Analysis of Micro-Doppler Signatures for Human Finer-Grained Activity Using Through-Wall SFCW Radar[J]. Remote Sensing, 2017, 9(3):260.
    [4] Hao L , Fugui Q , Yang Z , et al. Improved Detection of Human Respiration Using Data Fusion Basedon a Multistatic UWB Radar[J]. Remote Sensing, 2016, 8(9):773.
    [5] Debes, C, Amin, et al. Target Detection in Single- and Multiple-View Through-the-Wall Radar Imaging[J]. IEEE Trans. Geosci. Remote Sensing, 2009, 47(5):1349-1361.
    [6] F. Ahmad, Y. Zhang, M. G. Amin. Three-dimensional wideband beamforming for imaging through a single wall[J]. IEEE Geoscience and remote sensing letters, 2008, 5(2): 176-179.
    [7] https://www.camero-tech.com/wp-content/uploads/2017/02/camero_XAVER 800_brochure_Enn.pdf[Z]. 2017.
    [8] Kong L, Cui G, Yang X, et al. Three-dimensional human imaging for through-the-wall radar[C]. Radar Conference, IEEE, 2009.
    [9] C. H. Seng, A. Bouzerdoum, M. G. Amin, et al. Probabilistic fuzzy image fusion approach for radar through wall sensing[J]. IEEE Transactions on Image Processing. 2013, 22(12):4938-4951
    [10] Adib F, Hsu C, Mao H, et al. Capturing the human figure through a wall[J]. ACM Transactions on Graphics. 2015, 34(6): 1-13.
    [11] Zhao D, Tian J, Dai Y, et al. A Three-Dimensional Enhanced Imaging Method on Human Body for Ultra-Wideband Multiple-Input Multiple-Output Radar[J]. Electronics. 2018, 7(7): 101.
    [12] Dai Y , Jin T , Li H , et al. Imaging Enhancement via CNN in MIMO Virtual Array-Based Radar[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, PP(99):1-10.
    [13] Dai Y , Jin T , Song Y , et al. Convolutional Neural Network with Spatial-Variant Convolution Kernel[J]. Remote Sensing, 2020, 12(17):2811.
    [14] Guo Y , He D , Chai L . A Machine Vision-Based Method for Monitoring Scene-Interactive Behaviors of Dairy Calf[J]. Animals, 2020, 10(2):190.
    [15] Costa D G . Visual Sensors Hardware Platforms: A Review[J]. IEEE Sensors Journal, 2020, 20(8):4025-4033.
    [16] Zhang F , Zhu X , Ye M . Fast Human Pose Estimation[C] 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2019.
    [17] Hu Z , Zeng Z , Wang K , et al. Design and Analysis of a UWB MIMO Radar System with Miniaturized Vivaldi Antenna for Through- Wall Imaging[J]. Remote Sensing, 2019, 11(16).
    [18] Setlur P , Alli G , Nuzzo L . Multipath Exploitation in Through-Wall Radar Imaging Via Point Spread Functions[J]. IEEE Transactions on Image Processing, 2013, 22(12):4571-4586.
    • 相关文章
    • 施引文献(4)

  • 期刊类型引用(2)

    1. 杨桢，段雨昕，李鑫，吴方泽，纪力文，冯丰. 基于2D-SPWVD与PCA-SSA-RF的超宽带雷达人体跌落动作辨识方法. 电子测量与仪器学报. 2024(10): 147-158 . 百度学术
    2. 戴永鹏，宋少秋，金添，宋永坤，王秀荣. 基于阵列子通道投影图的雷达图像增强算法. 信号处理. 2023(09): 1552-1561 . 本站查看

    其他类型引用(2)

    • 资源附件(0)
计量
  • 文章访问数:  187
  • HTML全文浏览量:  11
  • PDF下载量:  227
  • 被引次数: 4
出版历程
  • 收稿日期:  2021-02-22
  • 修回日期:  2021-05-11
  • 发布日期:  2021-08-24

目录

摘要
HTML全文
    参考文献(18)
    相关文章
    施引文献
    资源附件(0)

    /

    返回文章
    返回

    版权所有 © 2009 《信号处理》 编辑部  京ICP备12041980号-1

    地址：北京市西城区鼓楼西大街41号  电话：010-64010656  Email：xhcl@signal.org.cn

    本系统由 北京仁和汇智信息技术有限公司 开发  百度统计