PE-MCAT: Leveraging Image Sensor Fusion and Adaptive Thresholds for Semi-Supervised 3D Object Detection

Existing 3D object detection frameworks in sensor-based applications heavily rely on large-scale annotated data to achieve optimal performance. However, obtaining such annotations from sensor data—like LiDAR or image sensors—is both time-consuming and costly. Semi-supervised learning offers an effic...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Sensors (Basel, Switzerland) Ročník 24; číslo 21; s. 6940
Hlavní autori:	Li, Bohao, Song, Shaojing, Ai, Luxia
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Switzerland MDPI AG 29.10.2024 MDPI
Predmet:	Accuracy adaptive threshold Algorithms Artificial intelligence Equipment and supplies Image processing Learning Localization Methods multi-feature fusion Optical radar point enrichment pseudo-label Remote sensing Semantics semi-supervised learning Sensors Teachers pseudo-label semi-supervised learning multi-feature fusion point enrichment adaptive threshold
ISSN:	1424-8220, 1424-8220
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Existing 3D object detection frameworks in sensor-based applications heavily rely on large-scale annotated data to achieve optimal performance. However, obtaining such annotations from sensor data—like LiDAR or image sensors—is both time-consuming and costly. Semi-supervised learning offers an efficient solution to this challenge and holds significant potential for sensor-driven artificial intelligence (AI) applications. While it reduces the need for labeled data, semi-supervised learning still depends on a small amount of labeled samples for training. In the initial stages, relying on such limited samples can adversely affect the effective training of student–teacher networks. In this paper, we propose PE-MCAT, a semi-supervised 3D object detection method that generates high-precision pseudo-labels. First, to address the challenges of insufficient local feature capture and poor robustness in point cloud data, we introduce a point enrichment module. This module incorporates information from image sensors and combines multiple feature fusion methods of local and self-features to directly enhance the quality of point clouds and pseudo-labels, compensating for the limitations posed by using only a few labeled samples. Second, we explore the relationship between the teacher network and the pseudo-labels it generates. We propose a multi-class adaptive threshold strategy to initially filter and create a high-quality pseudo-label set. Furthermore, a joint variable threshold strategy is introduced to refine this set further, enhancing the selection of superior pseudo-labels.Extensive experiments demonstrate that PE-MCAT consistently outperforms recent state-of-the-art methods across different datasets. Specifically, on the KITTI dataset and using only 2% of labeled samples, our method improved the mean Average Precision (mAP) by 0.7% for cars, 3.7% for pedestrians, and 3.0% for cyclists.
AbstractList	Existing 3D object detection frameworks in sensor-based applications heavily rely on large-scale annotated data to achieve optimal performance. However, obtaining such annotations from sensor data—like LiDAR or image sensors—is both time-consuming and costly. Semi-supervised learning offers an efficient solution to this challenge and holds significant potential for sensor-driven artificial intelligence (AI) applications. While it reduces the need for labeled data, semi-supervised learning still depends on a small amount of labeled samples for training. In the initial stages, relying on such limited samples can adversely affect the effective training of student–teacher networks. In this paper, we propose PE-MCAT, a semi-supervised 3D object detection method that generates high-precision pseudo-labels. First, to address the challenges of insufficient local feature capture and poor robustness in point cloud data, we introduce a point enrichment module. This module incorporates information from image sensors and combines multiple feature fusion methods of local and self-features to directly enhance the quality of point clouds and pseudo-labels, compensating for the limitations posed by using only a few labeled samples. Second, we explore the relationship between the teacher network and the pseudo-labels it generates. We propose a multi-class adaptive threshold strategy to initially filter and create a high-quality pseudo-label set. Furthermore, a joint variable threshold strategy is introduced to refine this set further, enhancing the selection of superior pseudo-labels.Extensive experiments demonstrate that PE-MCAT consistently outperforms recent state-of-the-art methods across different datasets. Specifically, on the KITTI dataset and using only 2% of labeled samples, our method improved the mean Average Precision (mAP) by 0.7% for cars, 3.7% for pedestrians, and 3.0% for cyclists. Existing 3D object detection frameworks in sensor-based applications heavily rely on large-scale annotated data to achieve optimal performance. However, obtaining such annotations from sensor data-like LiDAR or image sensors-is both time-consuming and costly. Semi-supervised learning offers an efficient solution to this challenge and holds significant potential for sensor-driven artificial intelligence (AI) applications. While it reduces the need for labeled data, semi-supervised learning still depends on a small amount of labeled samples for training. In the initial stages, relying on such limited samples can adversely affect the effective training of student-teacher networks. In this paper, we propose PE-MCAT, a semi-supervised 3D object detection method that generates high-precision pseudo-labels. First, to address the challenges of insufficient local feature capture and poor robustness in point cloud data, we introduce a point enrichment module. This module incorporates information from image sensors and combines multiple feature fusion methods of local and self-features to directly enhance the quality of point clouds and pseudo-labels, compensating for the limitations posed by using only a few labeled samples. Second, we explore the relationship between the teacher network and the pseudo-labels it generates. We propose a multi-class adaptive threshold strategy to initially filter and create a high-quality pseudo-label set. Furthermore, a joint variable threshold strategy is introduced to refine this set further, enhancing the selection of superior pseudo-labels.Extensive experiments demonstrate that PE-MCAT consistently outperforms recent state-of-the-art methods across different datasets. Specifically, on the KITTI dataset and using only 2% of labeled samples, our method improved the mean Average Precision (mAP) by 0.7% for cars, 3.7% for pedestrians, and 3.0% for cyclists.Existing 3D object detection frameworks in sensor-based applications heavily rely on large-scale annotated data to achieve optimal performance. However, obtaining such annotations from sensor data-like LiDAR or image sensors-is both time-consuming and costly. Semi-supervised learning offers an efficient solution to this challenge and holds significant potential for sensor-driven artificial intelligence (AI) applications. While it reduces the need for labeled data, semi-supervised learning still depends on a small amount of labeled samples for training. In the initial stages, relying on such limited samples can adversely affect the effective training of student-teacher networks. In this paper, we propose PE-MCAT, a semi-supervised 3D object detection method that generates high-precision pseudo-labels. First, to address the challenges of insufficient local feature capture and poor robustness in point cloud data, we introduce a point enrichment module. This module incorporates information from image sensors and combines multiple feature fusion methods of local and self-features to directly enhance the quality of point clouds and pseudo-labels, compensating for the limitations posed by using only a few labeled samples. Second, we explore the relationship between the teacher network and the pseudo-labels it generates. We propose a multi-class adaptive threshold strategy to initially filter and create a high-quality pseudo-label set. Furthermore, a joint variable threshold strategy is introduced to refine this set further, enhancing the selection of superior pseudo-labels.Extensive experiments demonstrate that PE-MCAT consistently outperforms recent state-of-the-art methods across different datasets. Specifically, on the KITTI dataset and using only 2% of labeled samples, our method improved the mean Average Precision (mAP) by 0.7% for cars, 3.7% for pedestrians, and 3.0% for cyclists.
Audience	Academic
Author	Song, Shaojing Ai, Luxia Li, Bohao
AuthorAffiliation	1 School of Intelligent Manufacturing and Control Engineering, Shanghai Polytechnic University, Shanghai 201209, China; 20221513056@stu.sspu.edu.cn 2 School of Computer and Information Engineering, Shanghai Polytechnic University, Shanghai 201209, China 3 School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China; luxiaai@hust.edu.cn
AuthorAffiliation_xml	– name: 1 School of Intelligent Manufacturing and Control Engineering, Shanghai Polytechnic University, Shanghai 201209, China; 20221513056@stu.sspu.edu.cn – name: 3 School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China; luxiaai@hust.edu.cn – name: 2 School of Computer and Information Engineering, Shanghai Polytechnic University, Shanghai 201209, China
Author_xml	– sequence: 1 givenname: Bohao surname: Li fullname: Li, Bohao – sequence: 2 givenname: Shaojing orcidid: 0000-0002-1194-6390 surname: Song fullname: Song, Shaojing – sequence: 3 givenname: Luxia surname: Ai fullname: Ai, Luxia
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/39517835$$D View this record in MEDLINE/PubMed
BookMark	eNpdkk1vEzEQhleoiH7AgT-ALHGBwxZ_xWtzQVHaQqSgIiWcV157duNoYwd7NxL_Hqdpoxb5MNb4mXdmPHNZnPngoSjeE3zNmMJfEuWUCMXxq-KCcMpLSSk-e3Y_Ly5T2mBMGWPyTXHO1IRUkk0uiu7XbflzNl19RQvYQ9Sd8x2ab3UHaAk-hYjuxuSCR9pbNLV6N7g9oNU6QlqH3ibUZmQJW1cuxx3EvUtgEbtB980GzIBuYMgmx78tXre6T_Du0V4Vv-9uV7Mf5eL--3w2XZSGCzWUXBpiObNGWslFI4UFyVrDCGlbLLCpJo0RBDfCcmW5FlxpoRWpNJYYqglmV8X8qGuD3tS76LY6_q2DdvWDI8Su1nFwpodaE0E10Q2BBjjWVDPdUqZUm5M1WTJrfTtq7cZmC9aAH6LuX4i-fPFuXXdhXxMy4ZJJmhU-PSrE8GeENNRblwz0vfYQxlQzQmXFcR5RRj_-h27CGH3-qwMlaCWVOrR3faQ6nTtwvg05scnH5hGYvBWty_6pzAVQStgh4MPzHk7FP21ABj4fARNDShHaE0Jwfdiu-rRd7B_8Yb7v
Cites_doi	10.1109/ACCESS.2021.3070379 10.1109/CVPR42600.2020.00178 10.1016/j.patrec.2009.09.011 10.1109/ITSC48978.2021.9564951 10.1109/ICCV48922.2021.00305 10.1109/CVPR.2012.6248074 10.3390/s18103337 10.1109/ICCV.2019.00204 10.1109/CVPR42600.2020.00466 10.1609/aaai.v35i4.16456 10.1109/CVPR.2019.01298 10.3390/rs15235612 10.1007/978-3-030-01234-2_49 10.1109/CVPR42600.2020.01105 10.1109/CVPR46437.2021.01438 10.1109/CVPR52688.2022.00823 10.1109/CVPR.2018.00033 10.1109/TPAMI.2017.2699184 10.1109/CVPR42600.2020.01054 10.1609/aaai.v35i2.16207 10.1109/ICCV48922.2021.00717 10.1109/CVPR52688.2022.02067 10.1109/MFI49285.2020.9235240 10.1109/CVPR.2015.7298965 10.1007/978-3-031-20080-9_22 10.1109/CVPR.2019.00086 10.1109/CVPR46437.2021.01162 10.1109/CVPR42600.2020.01109 10.1016/j.autcon.2023.105262 10.1109/ICRA48891.2023.10160489 10.1109/CVPR46437.2021.00454 10.1109/CVPR52729.2023.02281
ContentType	Journal Article
Copyright	COPYRIGHT 2024 MDPI AG 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2024 by the authors. 2024
Copyright_xml	– notice: COPYRIGHT 2024 MDPI AG – notice: 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2024 by the authors. 2024
DBID	AAYXX CITATION NPM 3V. 7X7 7XB 88E 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU DWQXO FYUFA GHDGH K9. M0S M1P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 5PM DOA
DOI	10.3390/s24216940
DatabaseName	CrossRef PubMed ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One Community College ProQuest Central Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) Health & Medical Collection (Alumni Edition) PML(ProQuest Medical Library) ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef PubMed Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Central China ProQuest Central ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Health & Medical Research Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic
DatabaseTitleList	CrossRef PubMed MEDLINE - Academic Publicly Available Content Database
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1424-8220
ExternalDocumentID	oai_doaj_org_article_a162a1ab1ebe40a2a3af2399f11fb17a PMC11548382 A815422130 39517835 10_3390_s24216940
Genre	Journal Article
GroupedDBID	--- 123 2WC 53G 5VS 7X7 88E 8FE 8FG 8FI 8FJ AADQD AAHBH AAYXX ABDBF ABUWG ACUHS ADBBV ADMLS AENEX AFFHD AFKRA AFZYC ALMA_UNASSIGNED_HOLDINGS BENPR BPHCQ BVXVI CCPQU CITATION CS3 D1I DU5 E3Z EBD ESX F5P FYUFA GROUPED_DOAJ GX1 HH5 HMCUK HYE IAO ITC KQ8 L6V M1P M48 MODMG M~E OK1 OVT P2P P62 PHGZM PHGZT PIMPY PJZUB PPXIY PQQKQ PROAC PSQYO RNS RPM TUS UKHRP XSB ~8M 3V. ABJCF ALIPV ARAPS HCIFZ KB. M7S NPM PDBOC 7XB 8FK AZQEC DWQXO K9. PKEHL PQEST PQUKI PRINS 7X8 PUEGO 5PM
ID	FETCH-LOGICAL-c469t-48c1d43dc8d846b86de83fc311ff060c75bc610b6d49d4a649a6a917a080e7503
IEDL.DBID	DOA
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001351066000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1424-8220
IngestDate	Fri Oct 03 12:39:26 EDT 2025 Tue Nov 04 02:05:30 EST 2025 Thu Sep 04 19:48:22 EDT 2025 Tue Oct 07 07:39:18 EDT 2025 Tue Nov 04 18:13:26 EST 2025 Wed Feb 19 02:03:09 EST 2025 Sat Nov 29 07:20:42 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	21
Keywords	pseudo-label semi-supervised learning multi-feature fusion point enrichment adaptive threshold
Language	English
License	Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c469t-48c1d43dc8d846b86de83fc311ff060c75bc610b6d49d4a649a6a917a080e7503
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-1194-6390
OpenAccessLink	https://doaj.org/article/a162a1ab1ebe40a2a3af2399f11fb17a
PMID	39517835
PQID	3126278990
PQPubID	2032333
ParticipantIDs	doaj_primary_oai_doaj_org_article_a162a1ab1ebe40a2a3af2399f11fb17a pubmedcentral_primary_oai_pubmedcentral_nih_gov_11548382 proquest_miscellaneous_3128740822 proquest_journals_3126278990 gale_infotracacademiconefile_A815422130 pubmed_primary_39517835 crossref_primary_10_3390_s24216940
PublicationCentury	2000
PublicationDate	20241029
PublicationDateYYYYMMDD	2024-10-29
PublicationDate_xml	– month: 10 year: 2024 text: 20241029 day: 29
PublicationDecade	2020
PublicationPlace	Switzerland
PublicationPlace_xml	– name: Switzerland – name: Basel
PublicationTitle	Sensors (Basel, Switzerland)
PublicationTitleAlternate	Sensors (Basel)
PublicationYear	2024
Publisher	MDPI AG MDPI
Publisher_xml	– name: MDPI AG – name: MDPI
References	ref_14 ref_13 ref_35 ref_12 ref_11 ref_33 ref_10 ref_32 ref_31 ref_30 ref_19 ref_18 ref_17 ref_39 ref_16 ref_38 ref_15 ref_37 Jain (ref_36) 2010; 31 ref_25 Chen (ref_24) 2021; 9 ref_23 ref_22 ref_21 ref_20 ref_40 ref_1 ref_3 ref_2 ref_28 ref_27 ref_26 Chen (ref_29) 2017; 40 ref_9 Sohn (ref_34) 2020; Volume 33 ref_8 ref_5 Hu (ref_7) 2024; 159 ref_4 ref_6
References_xml	– volume: 9 start-page: 51710 year: 2021 ident: ref_24 article-title: RoIFusion: 3D object detection from LiDAR and vision publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3070379 – ident: ref_30 – ident: ref_4 doi: 10.1109/CVPR42600.2020.00178 – volume: 31 start-page: 651 year: 2010 ident: ref_36 article-title: Data clustering: 50 years beyond K-means publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2009.09.011 – ident: ref_39 – ident: ref_40 – ident: ref_23 doi: 10.1109/ITSC48978.2021.9564951 – ident: ref_14 – ident: ref_33 doi: 10.1109/ICCV48922.2021.00305 – ident: ref_37 doi: 10.1109/CVPR.2012.6248074 – ident: ref_18 doi: 10.3390/s18103337 – ident: ref_35 – ident: ref_6 doi: 10.1109/ICCV.2019.00204 – ident: ref_20 doi: 10.1109/CVPR42600.2020.00466 – ident: ref_15 doi: 10.1609/aaai.v35i4.16456 – ident: ref_17 doi: 10.1109/CVPR.2019.01298 – ident: ref_19 doi: 10.3390/rs15235612 – ident: ref_26 doi: 10.1007/978-3-030-01234-2_49 – ident: ref_5 doi: 10.1109/CVPR42600.2020.01105 – ident: ref_9 doi: 10.1109/CVPR46437.2021.01438 – ident: ref_16 doi: 10.1109/CVPR52688.2022.00823 – ident: ref_31 – volume: Volume 33 start-page: 596 year: 2020 ident: ref_34 article-title: Fixmatch: Simplifying semi-supervised learning with consistency and confidence publication-title: Advances in Neural Information Processing Systems – ident: ref_22 doi: 10.1109/CVPR.2018.00033 – volume: 40 start-page: 834 year: 2017 ident: ref_29 article-title: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2017.2699184 – ident: ref_3 doi: 10.1109/CVPR42600.2020.01054 – ident: ref_2 doi: 10.1609/aaai.v35i2.16207 – ident: ref_28 doi: 10.1109/ICCV48922.2021.00717 – ident: ref_38 doi: 10.1109/CVPR52688.2022.02067 – ident: ref_25 doi: 10.1109/MFI49285.2020.9235240 – ident: ref_27 doi: 10.1109/CVPR.2015.7298965 – ident: ref_10 doi: 10.1007/978-3-031-20080-9_22 – ident: ref_13 – ident: ref_1 doi: 10.1109/CVPR.2019.00086 – ident: ref_21 doi: 10.1109/CVPR46437.2021.01162 – ident: ref_8 doi: 10.1109/CVPR42600.2020.01109 – volume: 159 start-page: 105262 year: 2024 ident: ref_7 article-title: 3D vision technologies for a self-developed structural external crack damage recognition robot publication-title: Autom. Constr. doi: 10.1016/j.autcon.2023.105262 – ident: ref_11 doi: 10.1109/ICRA48891.2023.10160489 – ident: ref_32 doi: 10.1109/CVPR46437.2021.00454 – ident: ref_12 doi: 10.1109/CVPR52729.2023.02281
SSID	ssj0023338
Score	2.4335163
Snippet	Existing 3D object detection frameworks in sensor-based applications heavily rely on large-scale annotated data to achieve optimal performance. However,...
SourceID	doaj pubmedcentral proquest gale pubmed crossref
SourceType	Open Website Open Access Repository Aggregation Database Index Database
StartPage	6940
SubjectTerms	Accuracy adaptive threshold Algorithms Artificial intelligence Equipment and supplies Image processing Learning Localization Methods multi-feature fusion Optical radar point enrichment pseudo-label Remote sensing Semantics semi-supervised learning Sensors Teachers
SummonAdditionalLinks	– databaseName: Publicly Available Content Database dbid: PIMPY link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3Nb9MwFH-CjgMcxucgMJBBSJyiJrbr2lxQ2VYxaRuVVtA4RY7tjB6Wdk3L3897SRpaIXHimvjwrPfh33vP_j2A9544zga-iFXBVSyLgYyt1ETjGookCc6K-m3V97PhxYW-ujKT9nl01V6r3MTEOlA3bM90bxuDcN_PHVXM-yLlit5wmuTT4jamGVLUa20HatyFPSLeSnqwNzk9n_zoEjCB-VjDLiQw1e9X1A5VhuoeW2dSTd3_d4DeOqF2b09uHUfjh_93I49gv4WlbNTY0WO4E8on8GCLrPApXE9O4vOj0fQjOwto__V0I3Z6g_GIXWIuPF-y8ZpKb8yWno28XVAgZVO0lYpaXBVDeIwrb2bx5XpBEaoKnolj9jWnUhA7Dqv6Vlj5DL6NT6ZHX-J2TEPsMLdexVK71EvhnfYIZnKtfNCicCJNiyJRiRsOcocgLVdeGi-tksYqi1miRbAaqI16AL1yXoYXwDB85kIliKF0LnPuTVBGeWWGA8Rt3vAI3m0UlS0aNo4MsxjSZtZpM4LPpMJuARFo1x_my-us9cfMporb1OYpGrFMLLfCFvTMt0Cpc5Qtgg9kABm5OWrZ2fa1AspJhFnZSCP25BwRQASHGz1nrf9X2R-1RvC2-42eS-0YW4b5ul5D8xARoUXwvDGpTmaBwJdqchHoHWPb2dTun3L2s2YHJ34lLTR_-W-5XsF9jviMjmFuDqG3Wq7Da7jnfq1m1fJN6zm_AWwSKb4 priority: 102 providerName: ProQuest
Title	PE-MCAT: Leveraging Image Sensor Fusion and Adaptive Thresholds for Semi-Supervised 3D Object Detection
URI	https://www.ncbi.nlm.nih.gov/pubmed/39517835 https://www.proquest.com/docview/3126278990 https://www.proquest.com/docview/3128740822 https://pubmed.ncbi.nlm.nih.gov/PMC11548382 https://doaj.org/article/a162a1ab1ebe40a2a3af2399f11fb17a
Volume	24
WOSCitedRecordID	wos001351066000001&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: DOA dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: M~E dateStart: 20010101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: 7X7 dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central (subscription) customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: BENPR dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: PIMPY dateStart: 20010101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nj9MwEB3BwgEOiM8lsFQGIXGKNrFdx-bW3W3FStsSsQWVU-TEDvSwadW0e9zfzkySVq04cOHig20pzow982ZsPwN8dMRx1ndlqEquQln2ZWilJhpXX0aRL6xo7lb9uEomEz2bmXTvqS86E9bSA7eCO7Wx4ja2eYxfk5HlVtiS7mOWcVzmcdJAoygx22CqC7UERl4tj5DAoP60po1PZSjDsed9GpL-v03xni86PCe553hGT-FJhxjZoB3pM7jnq-fweI9H8AX8Sofh-Hww_cyuPE7N5uEhdnmDpoJdY5i6WLHRhrJizFaODZxdko1jU1RjTbtPNUPkij1v5uH1ZknGo_aOiQv2NacsDbvw6-bAVvUSvo-G0_MvYfeCQlhg2LsOpS5iJ4UrtEOckWvlvBZlIVB2ZaSiIunnBeKnXDlpnLRKGqssBnAWcaSnHc5XcFQtKv8aGFq2XKgI4Y3OZc6d8coop0zSR0jlDA_gw1ay2bIlysgwwCDxZzvxB3BGMt91IG7rpgI1nnUaz_6l8QA-kcYyWoGolsJ2FwlwnMRllQ00wkLO0TkHcLJVatYtzToTMVd0_ddg8_tdMy4q2imxlV9smj70VCGCpwCO2zmwG7NATErpsgD0wew4-KnDlmr-uyHuJuojLTR_8z_E8BYecQRY5Ee5OYGj9Wrj38HD4nY9r1c9uJ_MkqbUPXhwNpyk33rNEsFyfDfEuvRynP78A9vQFe8
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB6VFAk48H4YCiwIxMmqvbvZeJEQCk2jRk1CpKaonMzauy451AlxAuJP8RuZsZ2QCIlbD1ztlTW2v535ZmZnBuCVpR5nTZv5KuPKl1lT-kZG1MbVZUHgUiPK2qpP_dZwGJ2d6dEO_FrVwtCxypVOLBW1naYUI98XIVdUtamD97NvPk2NouzqaoRGBYtj9_MHumzFu14H_-9rzruH44Mjv54q4KfoCi58GaWhlcKmkUXbm0TKukhkqQjDLAtUkLaaSYqcIlFWaiuNktoog06NQW7lKOuHz70CuxLBHjRgd9QbjD6vXTyBHl_Vv0gIHewXlHBVmiIrG1avHA7wtwnYsIHb5zM3DF731v_2qW7DzZpas3a1F-7Ajsvvwo2Nhov34Hx06A8O2uO3rO9wD5cTmljvAnUqO0F_fjpn3SWFD5nJLWtbMyNjwMaI94LSdAVDio8rLyb-yXJGWrZwlokO-5hQOIt13KI82Zbfh9NLedMH0MinuXsEDE1AIlSAPDBKZMKtdkorq3SridzTau7ByxUU4lnVUSRGT4zwEq_x4sEHAsl6ATUBLy9M5-dxrVNiEypuQpOEuBFlYLgRJqNS5QylTlA2D94QxGJSVYij1NQVFygnNf2K2xHyZ86RxXiwt0JSXOuwIv4DIw9erG-j9qGUksnddFmuoZmOyDI9eFiBdi2zQPJOcUUPoi04b73U9p188rXscE49oiIR8cf_lus5XDsaD_pxvzc8fgLXOfJNohVc70FjMV-6p3A1_b6YFPNn9T5l8OWy8f4bXhF6dA
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9NAEB2VFKFy4JtiKLAgECer9q6zWSMhlDaJiBpCRAPqzay965JD7RAnIP4av44ZxzaJkLj1wNVeWWP7zcybnZ0ZgBeGepy1TerKlEs3SNuBqwNFbVxt6nk20aKsrfo86ozH6uwsnOzAr7oWho5V1jaxNNQmT2iP_FD4XFLVZugdptWxiElv8Hb-zaUJUpRprcdprCFyYn_-wPCteDPs4b9-yfmgPz1-51YTBtwEw8KlG6jEN4EwiTLoh2MljVUiTYTvp6knvaTTjhPkF7E0QWgCLYNQS40BjkaeZSkDiM-9ArsdgddasHvUH08-NuGewOhv3ctICJS6oOSrDGmXZcMDloMC_nYHG_5w-6zmhvMb3PyfP9stuFFRbtZd68ht2LHZHbi-0YjxLpxP-u774-70NRtZ1O1ychMbXqCtZacY5-cLNljRtiLTmWFdo-fkJNgU9aCg9F3BkPrjyouZe7qak_UtrGGixz7EtM3FenZZnnjL7sGnS3nT-9DK8sw-AIauIRbSQ36o4iDmJrQylEaGnTZyUhNyB57XsIjm604jEUZohJ2owY4DRwSYZgE1By8v5IvzqLI1kfYl176OfVTQwNNcC51SCXOKUscomwOvCG4RmTDEVKKrSgyUk5qBRV2FvJpzZDcOHNSoiirbVkR_IOXAs-Y2WiVKNenM5qtyDc16RPbpwP4awI3MAkk97Tc6oLagvfVS23ey2dey8zn1jlJC8Yf_luspXEOQR6Ph-OQR7HGkocQ2eHgAreViZR_D1eT7clYsnlQqy-DLZcP9NznNgw4
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=PE-MCAT%3A+Leveraging+Image+Sensor+Fusion+and+Adaptive+Thresholds+for+Semi-Supervised+3D+Object+Detection&rft.jtitle=Sensors+%28Basel%2C+Switzerland%29&rft.au=Li%2C+Bohao&rft.au=Song%2C+Shaojing&rft.au=Ai%2C+Luxia&rft.date=2024-10-29&rft.issn=1424-8220&rft.eissn=1424-8220&rft.volume=24&rft.issue=21&rft.spage=6940&rft_id=info:doi/10.3390%2Fs24216940&rft.externalDBID=n%2Fa&rft.externalDocID=10_3390_s24216940
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1424-8220&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1424-8220&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1424-8220&client=summon