3-D Object Detection for Multiframe 4-D Automotive Millimeter-Wave Radar Point Cloud

Object detection is a crucial task in autonomous driving. Currently, object-detection methods for autonomous driving systems are primarily based on information from cameras and light detection and ranging (LiDAR), which may experience interference from complex lighting or poor weather. At present, t...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE sensors journal Vol. 23; no. 11; pp. 11125 - 11138
Main Authors:	Tan, Bin, Ma, Zhixiong, Zhu, Xichan, Li, Sen, Zheng, Lianqing, Chen, Sihan, Huang, Libo, Bai, Jie
Format:	Journal Article
Language:	English
Published:	New York The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 01.06.2023
Subjects:	Algorithms Driving Lidar Millimeter waves Object recognition Radar detection Three dimensional models Velocity
ISSN:	1530-437X, 1558-1748
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Object detection is a crucial task in autonomous driving. Currently, object-detection methods for autonomous driving systems are primarily based on information from cameras and light detection and ranging (LiDAR), which may experience interference from complex lighting or poor weather. At present, the 4-D ([Formula Omitted], [Formula Omitted], [Formula Omitted], [Formula Omitted] millimeter-wave radar can provide a denser point cloud to achieve 3-D object-detection tasks that are difficult to complete with traditional millimeter-wave radar. Existing 3-D object point-cloud-detection algorithms are mostly based on 3-D LiDAR; these methods are not necessarily applicable to millimeter-wave radars, which have sparser data and more noise and include velocity information. This study proposes a 3-D object-detection framework based on a multiframe 4-D millimeter-wave radar point cloud. First, the ego vehicle velocity information is estimated by the millimeter-wave radar, and the relative velocity information of the millimeter-wave radar point cloud is compensated for the absolute velocity. Second, by matching between millimeter-wave radar frames, the multiframe millimeter-wave radar point cloud is matched to the last frame. Finally, the object is detected by the proposed multiframe millimeter-wave radar point-cloud-detection network. Experiments are performed using our newly recorded TJ4DRadSet dataset in a complex traffic environment. The results showed that the proposed object-detection framework outperformed the comparison methods based on the 3-D mean average precision. The experimental results and methods can be used as the baseline for other multiframe 4-D millimeter-wave radar-detection algorithms.
AbstractList	Object detection is a crucial task in autonomous driving. Currently, object-detection methods for autonomous driving systems are primarily based on information from cameras and light detection and ranging (LiDAR), which may experience interference from complex lighting or poor weather. At present, the 4-D ([Formula Omitted], [Formula Omitted], [Formula Omitted], [Formula Omitted] millimeter-wave radar can provide a denser point cloud to achieve 3-D object-detection tasks that are difficult to complete with traditional millimeter-wave radar. Existing 3-D object point-cloud-detection algorithms are mostly based on 3-D LiDAR; these methods are not necessarily applicable to millimeter-wave radars, which have sparser data and more noise and include velocity information. This study proposes a 3-D object-detection framework based on a multiframe 4-D millimeter-wave radar point cloud. First, the ego vehicle velocity information is estimated by the millimeter-wave radar, and the relative velocity information of the millimeter-wave radar point cloud is compensated for the absolute velocity. Second, by matching between millimeter-wave radar frames, the multiframe millimeter-wave radar point cloud is matched to the last frame. Finally, the object is detected by the proposed multiframe millimeter-wave radar point-cloud-detection network. Experiments are performed using our newly recorded TJ4DRadSet dataset in a complex traffic environment. The results showed that the proposed object-detection framework outperformed the comparison methods based on the 3-D mean average precision. The experimental results and methods can be used as the baseline for other multiframe 4-D millimeter-wave radar-detection algorithms.
Author	Zhu, Xichan Li, Sen Ma, Zhixiong Zheng, Lianqing Bai, Jie Huang, Libo Chen, Sihan Tan, Bin
Author_xml	– sequence: 1 givenname: Bin surname: Tan fullname: Tan, Bin organization: School of Automotive Studies, Tongji University, Shanghai, China – sequence: 2 givenname: Zhixiong orcidid: 0000-0002-6060-5592 surname: Ma fullname: Ma, Zhixiong organization: School of Automotive Studies, Tongji University, Shanghai, China – sequence: 3 givenname: Xichan surname: Zhu fullname: Zhu, Xichan organization: School of Automotive Studies, Tongji University, Shanghai, China – sequence: 4 givenname: Sen surname: Li fullname: Li, Sen organization: School of Automotive Studies, Tongji University, Shanghai, China – sequence: 5 givenname: Lianqing orcidid: 0000-0002-7186-4055 surname: Zheng fullname: Zheng, Lianqing organization: School of Automotive Studies, Tongji University, Shanghai, China – sequence: 6 givenname: Sihan orcidid: 0000-0002-8394-9232 surname: Chen fullname: Chen, Sihan organization: School of Automotive Studies, Tongji University, Shanghai, China – sequence: 7 givenname: Libo surname: Huang fullname: Huang, Libo organization: School of Information and Electricity, Zhejiang University City College, Hangzhou, Zhejiang, China – sequence: 8 givenname: Jie surname: Bai fullname: Bai, Jie organization: School of Information and Electricity, Zhejiang University City College, Hangzhou, Zhejiang, China
BookMark	eNp9kMtKAzEUhoNUsK0-gLuA66m5TJLJsrT1RmtFK7oLaSYDKdNJzWQE394M7cqFq3Ph-8-BbwQGjW8sANcYTTBG8vbpbfE8IYiQCSVY8pyegSFmrMiwyItB31OU5VR8XoBR2-4QwlIwMQQbms3heruzJsK5jak438DKB7jq6uiqoPcW5omZdtHvfXTfFq5cXbt9gkP2odP8qksd4It3TYSz2nflJTivdN3aq1Mdg_e7xWb2kC3X94-z6TIzRNCYWSxzai2jRaVZSQ3VgmjBLOdGS0MwZogbXuZpha3c2hILJjkptrTkVGJLx-DmePcQ_Fdn26h2vgtNeqlIQTDihURFovCRMsG3bbCVOgS31-FHYaR6eaqXp3p56iQvZcSfjHFR925i0K7-J_kLigJ0Fw
CitedBy_id	crossref_primary_10_1016_j_eswa_2025_127515 crossref_primary_10_1016_j_measurement_2024_116568 crossref_primary_10_1109_JSEN_2024_3382669 crossref_primary_10_1109_JSEN_2024_3465019 crossref_primary_10_1109_JSEN_2025_3540660 crossref_primary_10_1109_TAES_2024_3484391 crossref_primary_10_1109_TIV_2024_3424942 crossref_primary_10_1109_JIOT_2025_3579892 crossref_primary_10_1109_TIM_2025_3562250 crossref_primary_10_1109_TIV_2024_3380244 crossref_primary_10_3390_s23239429 crossref_primary_10_1109_TITS_2025_3554781 crossref_primary_10_3390_rs16142640 crossref_primary_10_1016_j_cja_2025_103560 crossref_primary_10_1109_TITS_2025_3554313 crossref_primary_10_1016_j_neucom_2024_127635 crossref_primary_10_1109_JSEN_2024_3479214 crossref_primary_10_1109_JSEN_2025_3564825 crossref_primary_10_1109_JSEN_2024_3471650 crossref_primary_10_1109_JSEN_2025_3528986 crossref_primary_10_1016_j_engappai_2025_110747 crossref_primary_10_1109_JSEN_2024_3393030 crossref_primary_10_1109_JSEN_2024_3459468 crossref_primary_10_1016_j_compeleceng_2025_110696 crossref_primary_10_1109_TIV_2023_3319546 crossref_primary_10_1109_COMST_2024_3409556 crossref_primary_10_1109_LSENS_2024_3456840 crossref_primary_10_1109_LRA_2025_3536840 crossref_primary_10_1038_s41597_025_04698_2 crossref_primary_10_1109_JSEN_2024_3410271 crossref_primary_10_1109_JSEN_2024_3516786 crossref_primary_10_1109_TIV_2023_3307157 crossref_primary_10_1109_JSEN_2023_3347893 crossref_primary_10_3390_rs16203907 crossref_primary_10_1109_JSEN_2024_3421671 crossref_primary_10_1109_JSEN_2023_3260193 crossref_primary_10_3390_s25185857 crossref_primary_10_1109_JSEN_2025_3556518 crossref_primary_10_3390_rs16020366 crossref_primary_10_1007_s11370_024_00563_0 crossref_primary_10_3390_rs16234508
Cites_doi	10.1109/ITSC.2016.7795967 10.1109/CVPR.2018.00472 10.1109/ICCV48922.2021.00274 10.1109/ITSC55140.2022.9922539 10.1109/IM.2001.924423 10.1109/ICMIM.2017.7918863 10.1109/ITSC48978.2021.9564754 10.1007/978-3-030-58523-5_16 10.1109/CVPR42600.2020.01151 10.1109/LRA.2022.3147324 10.23919/ICIF.2018.8455344 10.1016/j.sna.2021.112566 10.1109/CVPR.2019.00086 10.1109/ICRA.2019.8794264 10.1109/ITSC.2013.6728341 10.3390/s18103337 10.1109/CVPR42600.2020.01054 10.1109/IVS.2018.8500607 10.1109/ICCV.2019.00204 10.1109/CVPR42600.2020.01140 10.1609/aaai.v34i07.6837 10.1109/JSEN.2020.3023243 10.1016/j.neucom.2021.08.155 10.1007/978-3-030-58523-5_29 10.1016/j.inffus.2020.11.002 10.1109/ITSC.2019.8917000 10.1109/ICIP40778.2020.9191134 10.1109/CVPR46437.2021.01161 10.1109/CVPR42600.2020.01105 10.1109/ACCESS.2020.3032034 10.1109/IVS.2019.8813841 10.1109/CVPR.2019.01298 10.1109/SDF.2017.8126350 10.1109/ICMIM.2016.7533931
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	AAYXX CITATION 7SP 7U5 8FD L7M
DOI	10.1109/JSEN.2022.3219643
DatabaseName	CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Solid State and Superconductivity Abstracts
DeliveryMethod	fulltext_linktorsrc
Discipline	Geography Engineering
EISSN	1558-1748
EndPage	11138
ExternalDocumentID	10_1109_JSEN_2022_3219643
GroupedDBID	-~X 0R~ 29I 4.4 5GY 6IK 97E AAJGR AASAJ AAWTH AAYXX ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AGQYO AHBIQ AJQPL AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CITATION CS3 EBS F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TWZ 7SP 7U5 8FD AARMG ABAZT L7M
ID	FETCH-LOGICAL-c273t-e1943ee538fa5d3c3a72a75e66ca9c211506c6d475e1e9bed1759628b3d6391e3
ISICitedReferencesCount	53
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001003468000004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1530-437X
IngestDate	Mon Jun 30 08:29:30 EDT 2025 Tue Nov 18 22:14:45 EST 2025 Sat Nov 29 06:39:24 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	11
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	OpenURL
MergedId	FETCHMERGED-LOGICAL-c273t-e1943ee538fa5d3c3a72a75e66ca9c211506c6d475e1e9bed1759628b3d6391e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-7186-4055 0000-0002-6060-5592 0000-0002-8394-9232
PQID	2821068908
PQPubID	75733
PageCount	14
ParticipantIDs	proquest_journals_2821068908 crossref_primary_10_1109_JSEN_2022_3219643 crossref_citationtrail_10_1109_JSEN_2022_3219643
PublicationCentury	2000
PublicationDate	2023-06-01
PublicationDateYYYYMMDD	2023-06-01
PublicationDate_xml	– month: 06 year: 2023 text: 2023-06-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE sensors journal
PublicationYear	2023
Publisher	The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref35 ref12 ref34 ref15 ref37 ref14 ref36 ref31 meyer (ref7) 2019 ref30 ref11 ref33 meyer (ref9) 2019 ref10 derpanis (ref32) 2010; 4 ref2 ref1 ref17 ref16 ref19 ref18 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 ref8 ref4 ref3 ref6 ref5
References_xml	– ident: ref30 doi: 10.1109/ITSC.2016.7795967 – ident: ref14 doi: 10.1109/CVPR.2018.00472 – ident: ref36 doi: 10.1109/ICCV48922.2021.00274 – ident: ref11 doi: 10.1109/ITSC55140.2022.9922539 – ident: ref33 doi: 10.1109/IM.2001.924423 – start-page: 129 year: 2019 ident: ref7 article-title: Automotive radar dataset for deep learning based 3D object detection publication-title: Proc Eur Radar Conf (EuRAD) – ident: ref3 doi: 10.1109/ICMIM.2017.7918863 – ident: ref10 doi: 10.1109/ITSC48978.2021.9564754 – ident: ref21 doi: 10.1007/978-3-030-58523-5_16 – ident: ref23 doi: 10.1109/CVPR42600.2020.01151 – ident: ref8 doi: 10.1109/LRA.2022.3147324 – ident: ref6 doi: 10.23919/ICIF.2018.8455344 – ident: ref1 doi: 10.1016/j.sna.2021.112566 – ident: ref19 doi: 10.1109/CVPR.2019.00086 – ident: ref22 doi: 10.1109/ICRA.2019.8794264 – ident: ref27 doi: 10.1109/ITSC.2013.6728341 – volume: 4 start-page: 2 year: 2010 ident: ref32 publication-title: Overview of the RANSAC Algorithm – start-page: 133 year: 2019 ident: ref9 article-title: Deep learning based 3D object detection for automotive radar and camera publication-title: Proc Eur Radar Conf (EuRAD) – ident: ref15 doi: 10.3390/s18103337 – ident: ref17 doi: 10.1109/CVPR42600.2020.01054 – ident: ref4 doi: 10.1109/IVS.2018.8500607 – ident: ref20 doi: 10.1109/ICCV.2019.00204 – ident: ref24 doi: 10.1109/CVPR42600.2020.01140 – ident: ref35 doi: 10.1609/aaai.v34i07.6837 – ident: ref28 doi: 10.1109/JSEN.2020.3023243 – ident: ref12 doi: 10.1016/j.neucom.2021.08.155 – ident: ref31 doi: 10.1007/978-3-030-58523-5_29 – ident: ref13 doi: 10.1016/j.inffus.2020.11.002 – ident: ref5 doi: 10.1109/ITSC.2019.8917000 – ident: ref37 doi: 10.1109/ICIP40778.2020.9191134 – ident: ref34 doi: 10.1109/CVPR46437.2021.01161 – ident: ref18 doi: 10.1109/CVPR42600.2020.01105 – ident: ref26 doi: 10.1109/ACCESS.2020.3032034 – ident: ref29 doi: 10.1109/IVS.2019.8813841 – ident: ref16 doi: 10.1109/CVPR.2019.01298 – ident: ref2 doi: 10.1109/SDF.2017.8126350 – ident: ref25 doi: 10.1109/ICMIM.2016.7533931
SSID	ssj0019757
Score	2.561813
Snippet	Object detection is a crucial task in autonomous driving. Currently, object-detection methods for autonomous driving systems are primarily based on information...
SourceID	proquest crossref
SourceType	Aggregation Database Enrichment Source Index Database
StartPage	11125
SubjectTerms	Algorithms Driving Lidar Millimeter waves Object recognition Radar detection Three dimensional models Velocity
Title	3-D Object Detection for Multiframe 4-D Automotive Millimeter-Wave Radar Point Cloud
URI	https://www.proquest.com/docview/2821068908
Volume	23
WOSCitedRecordID	wos001003468000004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
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/eLvHCXMwtV3Nb9MwFLfKQGIcEAzQBgP5wIkoENtJbB-nMUAIysSKqLhEieOwSl06tenU_2H_9J4_krSbQOzAJWqf0ien75f3Yb8PhF4XvIpUTFQomVBhnBMJ71wpQvAeZFTIIuWVbZn_hQ-HYjyWx4PBZVsLczHldS1WK3n-X0UNNBC2KZ29hbg7pkCAzyB0uILY4fpPgmfh--BbYbZXQJk0WnXJhLbWtjLJWEEM9xwsG5uJZ6YPmU2XM5MYE_4004i-52U-D45nk7oJDqez5cYwTxMeBguIfs2YnvUV2fjfTX-fdJD7ap3TX6eTFSzjd79NvTTkscnZ73OCbGLBia9N8zsRlPUZU53yjMKY8bGzLZ6WQJTKXTfNVuO6CuMWWWRNf4LmdXXQ3hjDd9f85aamt41SP58cDSHIp_Qto7a1WG_W2qP8a9auy0G00U8kM8MiMywyz-IOukt5IokrBuyOpCS3bWO7h_RH5MDi3Y1VbDo5mzbeOi6jR-ihjzjwgUPKYzTQ9Q56sNaHcgfd_6h95_InaAT4wQ4_uMMPBvzgHj8Y8IN7_OBr-MEWP9jiB1v8PEU_PhyNDj-FfvRGqMCfbUJNZMy0BmtY5UnJFMs5zXmi01TlUlETRqQqLWMgES0LXYIXKlMqClaCy0s0e4a26lmtdxGuIirzqEoqoqo4lUqUFXjxUuRlIsB9LvdQ1P5XmfJ96c14lGn2RwntoTfdT85dU5a_3bzfCiDzL8Uio4KSKBUyEs9vw-sF2u6Bv4-2mvlSv0T31EUzWcxfWbxcAW3Yhd0
linkProvider	IEEE
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=3-D+Object+Detection+for+Multiframe+4-D+Automotive+Millimeter-Wave+Radar+Point+Cloud&rft.jtitle=IEEE+sensors+journal&rft.au=Tan%2C+Bin&rft.au=Ma%2C+Zhixiong&rft.au=Zhu%2C+Xichan&rft.au=Li%2C+Sen&rft.date=2023-06-01&rft.issn=1530-437X&rft.eissn=1558-1748&rft.volume=23&rft.issue=11&rft.spage=11125&rft.epage=11138&rft_id=info:doi/10.1109%2FJSEN.2022.3219643&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSEN_2022_3219643
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