引用本文
  • 毛强,晋良念,刘庆华. 穿墙雷达多维参数人体姿态识别方法[J]. 雷达科学与技术, 2021, 19(1): 40-47.    [点击复制]
  • MAO Qiang, JIN Liangnian, LIU Qinghua. Human Posture Recognition with Multi Dimensional Parameter for Through the Wall Radar[J]. Radar Science and Technology, 2021, 19(1): 40-47.   [点击复制]
【打印本页】 【HTML】 【下载PDF全文】 查看/发表评论 下载PDF阅读器关闭

←前一篇|后一篇→

过刊浏览    高级检索

本文已被:浏览 47次   下载 56 本文二维码信息
码上扫一扫!
穿墙雷达多维参数人体姿态识别方法
毛强,晋良念,刘庆华
0
(1.桂林电子科技大学信息与通信学院,广西桂林 541004;2.广西无线宽带通信与信号处理重点实验室, 广西桂林541004)
摘要:
现有的人体姿态识别方案大多数是从单一的角度来考察人体的姿态特征,但是仅采用距离像很难体现人体关节的位置信息,仅提取微多普勒特征有时会覆盖掉径向速度不明显的特征。为此,本文首先利用慢时间距离像和慢时间微多普勒谱图构建出人体姿态的三维张量数据集,扩展了人体姿态的特征维度,然后采用改进型瓶颈残差模块构成的神经网络提高了人体姿态的识别率。实验结果表明,通过对4名受试者的8种姿态进行训练和测试,该网络对人体姿态的三维张量数据集的识别率可达97.78%,相比于单一特征数据集的识别率提高了4%~7%。
关键词:  穿墙雷达  人体姿态识别  三维张量数据集  改进型瓶颈残差神经网络
DOI:10.3969/j.issn.1672-2337.2021.01.007
基金项目:国家自然科学基金(No.61861011,61461012); 广西自然科学基金(No.2017GXNSFAA198050); 广西无线宽带通信与信号处理重点实验室2016主任基金项目(No.GXKL06160106)
Human Posture Recognition with Multi Dimensional Parameter for Through the Wall Radar
MAO Qiang, JIN Liangnian, LIU Qinghua
(1.School of Information and Communication , Guilin University of Electronic Technology, Guilin 541004,China;2.Key Laboratory of Guangxi Wireless Broadband Communication and Signal Processing, Guilin 541004,China))
Abstract:
Most of the existing human posture recognition schemes investigate the posture characteristics of the human from a single perspective. However, it is difficult to reflect the position information of human joints only by range map, and sometimes the nonobvious feature of radial velocity will be covered if we only extract microDoppler features. To this end, in the paper we firstly construct a threedimensional tensor dataset of human postures by slow time range map and slow time microDoppler map, which leads to expand the characteristic dimension of human postures. Secondly, the neural network composed of an improved bottleneck residual module is used to improve the recognition rate of human postures. After training and testing eight postures of four human subjects, the experimental results illustrate that the recognition rate of threedimensional tensor dataset of human postures through this network can reach 97.78%, which is 4%~7% higher than the recognition of the single feature dataset.
Key words:  through-the-wall radar  human posture recognition  3D tensor dataset  improved bottleneck residual neural network