From Clutter to Clarity: Enhancing Radar-Based Human Activity Recognition with Deep Attention and Feature Denoising

Millimeter-wave radar offers advantages such as insensitivity to lighting conditions, strong environmental adaptability, non-contact sensing, and inherent protection of user privacy. These characteristics have led to its increasing application in human activity recognition, with promising use cases...

Full description

Saved in:
Bibliographic Details
Published in:IEEE sensors journal p. 1
Main Authors: Wang, Huaijun, Li, Shuang, Bai, Bingqian, Li, Junhuai, Fei, Rong, Huang, Tao
Format: Journal Article
Language:English
Published: IEEE 19.11.2025
Subjects:
attention mechanism
Convolutional Autoencoder
human action recognition
millimeter wave radar
ISSN:1530-437X, 1558-1748
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Millimeter-wave radar offers advantages such as insensitivity to lighting conditions, strong environmental adaptability, non-contact sensing, and inherent protection of user privacy. These characteristics have led to its increasing application in human activity recognition, with promising use cases in smart homes, healthcare monitoring, and security systems. However, during radar data acquisition, substantial background interference and noise can significantly reduce recognition accuracy. To address this issue, this paper proposes a human action recognition method that integrates a deep convolutional autoencoder with a multi-scale attention mechanism. In the preprocessing stage, phase mean subtraction and moving average filtering are applied to suppress static background clutter in the radar micro-Doppler features. Subsequently, feature denoising and enhancement are performed using a convolutional autoencoder and attention modules to improve focus on motion-relevant regions. Experimental results demonstrate that the proposed method achieves over 96% accuracy on both a self-constructed dataset and a public benchmark dataset. Furthermore, the model maintains high recognition performance under low signal-to-noise ratio conditions, confirming its robustness and effectiveness in complex environments.
AbstractList Millimeter-wave radar offers advantages such as insensitivity to lighting conditions, strong environmental adaptability, non-contact sensing, and inherent protection of user privacy. These characteristics have led to its increasing application in human activity recognition, with promising use cases in smart homes, healthcare monitoring, and security systems. However, during radar data acquisition, substantial background interference and noise can significantly reduce recognition accuracy. To address this issue, this paper proposes a human action recognition method that integrates a deep convolutional autoencoder with a multi-scale attention mechanism. In the preprocessing stage, phase mean subtraction and moving average filtering are applied to suppress static background clutter in the radar micro-Doppler features. Subsequently, feature denoising and enhancement are performed using a convolutional autoencoder and attention modules to improve focus on motion-relevant regions. Experimental results demonstrate that the proposed method achieves over 96% accuracy on both a self-constructed dataset and a public benchmark dataset. Furthermore, the model maintains high recognition performance under low signal-to-noise ratio conditions, confirming its robustness and effectiveness in complex environments.
Author Bai, Bingqian
Huang, Tao
Fei, Rong
Wang, Huaijun
Li, Shuang
Li, Junhuai
Author_xml – sequence: 1
  givenname: Huaijun
  orcidid: 0000-0002-2933-6566
  surname: Wang
  fullname: Wang, Huaijun
  organization: School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China
– sequence: 2
  givenname: Shuang
  surname: Li
  fullname: Li, Shuang
  organization: School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China
– sequence: 3
  givenname: Bingqian
  surname: Bai
  fullname: Bai, Bingqian
  organization: School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China
– sequence: 4
  givenname: Junhuai
  orcidid: 0000-0001-5483-5175
  surname: Li
  fullname: Li, Junhuai
  email: lijunhuai@xaut.edu.cn
  organization: School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China
– sequence: 5
  givenname: Rong
  orcidid: 0000-0002-7092-4378
  surname: Fei
  fullname: Fei, Rong
  organization: School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China
– sequence: 6
  givenname: Tao
  orcidid: 0000-0002-8098-8906
  surname: Huang
  fullname: Huang, Tao
  email: tao.huang1@jcu.edu.au
  organization: College of Science and Engineering, James Cook University, Cairns, QLD, Australia
BookMark eNpFkN1OAjEQhRuDiYA-gIkXfYHF_uxud71DBNEQTZAL7zbDdoAa6JK2aHh7u0Li1ZzMOXOS-XqkYxuLhNxyNuCclfevH-O3gWAiG8hcSsHYBenyLCsSrtKi02rJklSqzyvS8_6LMV6qTHWJn7hmR0fbQwjoaGiiBGfC8YGO7QZsbeyazkGDSx7Bo6bTww4sHdbBfMcUnWPdrK0JprH0x4QNfULc02Ess387sJpOEMLBYbRsY3wsvCaXK9h6vDnPPllMxovRNJm9P7-MhrOkzmWZFClAKrJaI8OCMQWKxf9W9TLPoyN0pvNSc5aWSqUpx0wstQIsoIipgmsm-4SfamvXeO9wVe2d2YE7VpxVLbSqhVa10KoztHhzd7oxiPif5yIXKi_lL-jdayE
CODEN ISJEAZ
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/JSEN.2025.3633200
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Geography
Engineering
EISSN 1558-1748
EndPage 1
ExternalDocumentID 10_1109_JSEN_2025_3633200
11262769
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62571428; 65271427
  funderid: 10.13039/501100001809
GroupedDBID -~X
0R~
29I
4.4
5GY
6IK
97E
AAJGR
AASAJ
AAWTH
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AGQYO
AHBIQ
AJQPL
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
EBS
F5P
HZ~
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
TWZ
5VS
AAYXX
AETIX
AGSQL
AIBXA
CITATION
EJD
H~9
ZY4
ID FETCH-LOGICAL-c639-84aa425cde0e8007a70202fcb664aa2d5d69d104977441e52bd7ae8a820281d03
IEDL.DBID RIE
ISSN 1530-437X
IngestDate Thu Nov 27 00:56:44 EST 2025
Wed Nov 26 07:22:39 EST 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c639-84aa425cde0e8007a70202fcb664aa2d5d69d104977441e52bd7ae8a820281d03
ORCID 0000-0001-5483-5175
0000-0002-8098-8906
0000-0002-2933-6566
0000-0002-7092-4378
PageCount 1
ParticipantIDs ieee_primary_11262769
crossref_primary_10_1109_JSEN_2025_3633200
PublicationCentury 2000
PublicationDate 20251119
PublicationDateYYYYMMDD 2025-11-19
PublicationDate_xml – month: 11
  year: 2025
  text: 20251119
  day: 19
PublicationDecade 2020
PublicationTitle IEEE sensors journal
PublicationTitleAbbrev JSEN
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0019757
Score 2.444596
SecondaryResourceType online_first
Snippet Millimeter-wave radar offers advantages such as insensitivity to lighting conditions, strong environmental adaptability, non-contact sensing, and inherent...
SourceID crossref
ieee
SourceType Index Database
Publisher
StartPage 1
SubjectTerms attention mechanism
Convolutional Autoencoder
human action recognition
millimeter wave radar
Title From Clutter to Clarity: Enhancing Radar-Based Human Activity Recognition with Deep Attention and Feature Denoising
URI https://ieeexplore.ieee.org/document/11262769
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-1748
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0019757
  issn: 1530-437X
  databaseCode: RIE
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT8IwFG-UmKgHPxAjfqUHTyaFrevW1RsixBhDDHLgtnRtJyS6kQEm_ve-lqFcPHhb1m5Z3lvb3_v4vYfQTRhlAfW1JlJyTVioUyJgLgklbJhKgpGRujqzz3wwiMdj8VKR1R0Xxhjjks9My166WL4u1NK6ytqW7kJ5JLbRNud8Rdb6CRkI7sp6wgr2CAv4uAph-p5oP732BmAK0rAVREFALZtt4xDa6KriDpX-4T8_5wgdVOgRd1bqPkZbJq-j_Y2agnW0W7U1n3ydoHm_LD5w9901o8aLAttsHIDdd7iXT2yhjfwND6WWJbmHw0xj59HHHbXqKIGH6-SiIsfWX4sfjJnhDrzMpUhimWtsIeSyNDCUF1Prd2igUb836j6SqssCUYBOSMykhHWrtPEMgEcuOQBImqk0imCE6lBHQoPNZnEi801IU82liSUgBwpY1wtOUS0vcnOGMItZ5jHYI3RGGVeZpGnGIi-1JqHKqN9Et2upJ7NVLY3E2SCeSKyKEquipFJREzWsxH8nVsI-_-P-Bdqzj1uaoC8uUW1RLs0V2lGfi-m8vHa_yjf1GryC
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED7xkoCBZxFvPDAhGRLHiRu2Aq0KlApBh26RYzu0EiQotEj8e85uCl0Y2KLYsiJf7Pvu8d0BnIZRFjBfayql0JSHOqUxzqWhxAtTSTQyUldntiO63Xq_Hz9WZHXHhTHGuOQzc24fXSxfF2psXWUXlu7CRBTPw2LIOfMndK2foEEsXGFPPMMe5YHoV0FM34sv7p6bXTQGWXgeREHALJ9tRg3N9FVxaqW1_s8P2oC1Cj-SxkTgmzBn8i1YnakquAXLVWPzwdc2fLTK4o1cv7p21GRUEJuPg8D7kjTzgS21kb-QJ6llSa9QnWnifPqkoSY9JcjTNL2oyIn12JIbY95JAxdzSZJE5ppYEDkuDQ7lxdB6HmrQazV7121a9VmgCvEJrXMp8eQqbTyD8FFIgRCSZSqNIhxhOtRRrNFqs0iR-yZkqRbS1CViB4Zo1wt2YCEvcrMLhNd55nG8JXTGuFCZZGnGIy-1RqHKmL8HZ9NdT94n1TQSZ4V4cWJFlFgRJZWI9qBmd_x3YrXZ-3-8P4Hldu-hk3Ruu_cHsGKXsqRBPz6EhVE5NkewpD5Hw4_y2P023_Cfv8k
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=From+Clutter+to+Clarity%3A+Enhancing+Radar-Based+Human+Activity+Recognition+with+Deep+Attention+and+Feature+Denoising&rft.jtitle=IEEE+sensors+journal&rft.au=Wang%2C+Huaijun&rft.au=Li%2C+Shuang&rft.au=Bai%2C+Bingqian&rft.au=Li%2C+Junhuai&rft.date=2025-11-19&rft.issn=1530-437X&rft.eissn=1558-1748&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FJSEN.2025.3633200&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSEN_2025_3633200
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-437X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-437X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-437X&client=summon