期刊文献+

基于EfficientNet模型的毫米波雷达人体行为识别 被引量:1

FMCW Radar Human Action Recognition System Based on EfficientNet Model
下载PDF
导出
摘要 针对基于传统光学摄像头实现人体行为识别系统所带来的隐私暴露,易受光照、遮挡的影响等问题,设计基于EfficientNet模型的FMCW雷达人体行为识别系统。首先对FMCW雷达实测数据采用距离多普勒算法构建每一帧距离-速度图像;接着采用逐帧积累的方法延长观测时间窗口,构建覆盖整个动作过程的距离-速度轨迹;最后采用改进预训练的EfficientNet模型对不同人体行为进行识别。实验结果表明,在5秒观测时间窗口内,改进预训练的EfficientNet-B4模型对已知个体和未知个体9种行为识别准确率达到99.3%与98.2%,均高于传统机器学习方法及经典深度学习方法,进一步缩短观测时间窗口至2.5秒,改进预训练的EfficientNet-B4模型对已知个体和未知个体的9种行为识别准确率仍能达到96.7%与95.4%。除此之外,在5秒观测时间窗口内,所提方法对已知个体和未知个体的9种行为识别准确率比常见利用时间-速度提取行为参数的方法分别提高了3.5%与4.9%,缩短观测时间窗口至2.5秒,所提方法准确率提高了4.2%与4.8%,可见所提方法可以有效地提升FMCW雷达人体行为识别的准确率,且模型的泛化能力较强。 Since using traditional optical camera to realize human action recognition system will bring some problems,such as privacy exposure,easy to be affected by light and occlusion,a FMCW radar human action recognition system based on EfficientNet model is designed.Firstly,range Doppler algorithm is used to construct range-velocity images of each frame from the measured data of FMCW radar.Then the range velocity trajectory covering the whole movement process is constructed by using the method of frame-by-frame accumulation to extend the observation time window.Finally,the improved pre-training EfficientNet model is used to recognize different human actions.The experimental results show that within the 5-second observation time window,the accuracy of the improved pre-training EfficientNet-B4 model for identifying nine actions of known and unknown individuals is 99.3%and 98.2%,which are both higher than that of traditional machine learning methods and classical deep learning methods.When the observation time window was further shortened to 2.5 seconds,the recognition accuracy of the improved pre trained efficientnet-b4 model for 9 behaviors of known and unknown individuals could still reach 96.7%and 95.4%.In addition,within the 5-second observation time window,the accuracy of the proposed method for identifying 9 actions of known and unknown individuals is 3.5%and 4.9%higher than the common methods of extracting behavior parameters by time-velocity.When the observation time window is shortened to 2.5 seconds,the accuracy of the proposed method is improved by 4.2%and 4.8%.It can be seen that the proposed method can effectively improve the accuracy of FMCW radar human action recognition,and the model has strong generalization ability.
作者 陈鑫 叶宁 徐康 王甦 王汝传 CHEN Xin;YE Ning;XU Kang;WANG Su;WANG Ru-chuan(School of Computer Science,School of Software,School of Cyberspace Security,NanjingUniversity of Posts and Telecommunications,Nanjing 210023,China;Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks,Nanjing 210023,China)
出处 《计算机技术与发展》 2022年第9期134-141,共8页 Computer Technology and Development
基金 江苏省科技重点研发资助项目(社会发展)(BE2020713)。
关键词 调频连续波雷达 行为识别 距离多普勒 EfficientNet 深度学习 机器学习 迁移学习 FMCW radar action recognition range Doppler EfficientNet deep learning machine learning transfer learning
  • 相关文献

参考文献7

二级参考文献39

  • 1冯志全,蒋彦.手势识别研究综述[J].济南大学学报(自然科学版),2013,27(4):336-341. 被引量:29
  • 2庄钊文,刘永祥,黎湘.目标微动特性研究进展[J].电子学报,2007,35(3):520-525. 被引量:128
  • 3Chen V C,Li F,Ho S,Wechsler H.Micro-doppler effect in radar-phenomenon,model and simulation Study[J].IEEE Trans on AES,2006,42(1):2-21.
  • 4Chen V C.Micro-Doppler effect of micro-motion dynamics:a review[A].Proceedings of SPIE on Independent Component Analyses,Wavelets,and Neural Networks[C].Orlando,USA:SPIE Press,2003.240-249.
  • 5Nunn E C.The US army white sands missile range development of target motion resolution[A].Proceedings of IEEE Electronics and Aerospace Systems Conventions[C].Arlington,USA:IEEE Press,1980.346-352.
  • 6Camp W W,Mayhan J T,O'Donnell R M.Wideband radar for ballistic missile defense and range Doppler imaging of satellites[J].Lincoln Laboratory Journal,2000,12(2):267-280.
  • 7Hannon S M,Thomson J A.Agile multiple pulse coherent ladar for range and micro-Doppler measurement[A].Proceedings of SPIE on Laser Radar Technology and Applications Ⅲ[C].Orlando,USA:SPIE Press,1998.259-269.
  • 8Rihaczek A W,Hershkowitz S J.Radar Resolution and Complex-Image Analysis[M].Boston:Artech House,1996.24-155.
  • 9S-band radar micro-Doppler signatures for BMD discrimination[DB/OL].http://www.acq.osd.mil/osbp/sbir/solicitations/sbir044/mda044.htm,2003-10-16/2004-08-24.
  • 10Hanson F,Beaghler G.Discriminating interceptor technology program laser radar[A].Proceedings of SPIE on Laser Radar Technology and Applications[C].Orlando,USA:SPIE Press,1999.372-380.

共引文献173

同被引文献13

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部