Monocular Visual Simultaneous Localization and Mapping: (R)Evolution From Geometry to Deep Learning-Based Pipelines

With the rise of deep learning, there is a fundamental change in visual simultaneous localization and mapping (SLAM) algorithms toward developing different modules trained as end-to-end pipelines. However, regardless of the implementation domain, visual SLAM's performance is subject to diverse...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on artificial intelligence Ročník 5; číslo 5; s. 1990 - 2010
Hlavní autoři:	Alvarez-Tunon, Olaya, Brodskiy, Yury, Kayacan, Erdal
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	IEEE 01.05.2024
Témata:	Cameras Deep learning Feature extraction Optimization Pipelines robot vision systems Simultaneous localization and mapping Surveys visual odometry Visualization
ISSN:	2691-4581, 2691-4581
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	With the rise of deep learning, there is a fundamental change in visual simultaneous localization and mapping (SLAM) algorithms toward developing different modules trained as end-to-end pipelines. However, regardless of the implementation domain, visual SLAM's performance is subject to diverse environmental challenges, such as dynamic elements in outdoor environments, harsh imaging conditions in underwater environments, or blurriness in high-speed setups. These environmental challenges need to be identified to study the real-world viability of SLAM implementations. Motivated by the aforementioned challenges, this article surveys the current state of visual SLAM algorithms according to the two main frameworks: geometry-based and learning-based SLAM. First, we introduce a general formulation of the SLAM pipeline that includes most of the implementations in the literature. Second, those implementations are classified and surveyed for geometry and learning-based SLAM. After that, environment-specific challenges are formulated to enable experimental evaluation of the resilience of different visual SLAM classes to varying imaging conditions. We address two significant issues in surveying visual SLAM, providing a consistent classification of visual SLAM pipelines and a robust evaluation of their performance under different deployment conditions. Finally, we give our take on future opportunities for visual SLAM implementations.
AbstractList	With the rise of deep learning, there is a fundamental change in visual simultaneous localization and mapping (SLAM) algorithms toward developing different modules trained as end-to-end pipelines. However, regardless of the implementation domain, visual SLAM's performance is subject to diverse environmental challenges, such as dynamic elements in outdoor environments, harsh imaging conditions in underwater environments, or blurriness in high-speed setups. These environmental challenges need to be identified to study the real-world viability of SLAM implementations. Motivated by the aforementioned challenges, this article surveys the current state of visual SLAM algorithms according to the two main frameworks: geometry-based and learning-based SLAM. First, we introduce a general formulation of the SLAM pipeline that includes most of the implementations in the literature. Second, those implementations are classified and surveyed for geometry and learning-based SLAM. After that, environment-specific challenges are formulated to enable experimental evaluation of the resilience of different visual SLAM classes to varying imaging conditions. We address two significant issues in surveying visual SLAM, providing a consistent classification of visual SLAM pipelines and a robust evaluation of their performance under different deployment conditions. Finally, we give our take on future opportunities for visual SLAM implementations.
Author	Alvarez-Tunon, Olaya Brodskiy, Yury Kayacan, Erdal
Author_xml	– sequence: 1 givenname: Olaya orcidid: 0000-0003-3581-9481 surname: Alvarez-Tunon fullname: Alvarez-Tunon, Olaya email: olaya@ece.au.dk organization: Artificial Intelligence in Robotics Laboratory (AiRLab), the Department of Electrical and Computer Engineering, Aarhus University, Aarhus, Denmark – sequence: 2 givenname: Yury orcidid: 0009-0002-0445-8126 surname: Brodskiy fullname: Brodskiy, Yury email: ybr@eiva.com organization: EIVA a/s, Skanderborg, Denmark – sequence: 3 givenname: Erdal orcidid: 0000-0002-7143-8777 surname: Kayacan fullname: Kayacan, Erdal email: erdal.kayacan@uni-paderborn.de organization: Automatic Control Group (RAT), Paderborn University, Paderborn, Germany
BookMark	eNp9kDtPwzAURi1UJErpzsDgEYYUP-I82EppS6VUIKhYI8e5QUapHdkJUvn19DVUDEz3k-53rnTPJeoZawCha0pGlJL0fjVejBhhfMQ5o4SzM9RnUUqDUCS0d5Iv0ND7L0IIE5QxFveRX1pjVVdLhz-072SN3_W6q1tpwHYeZ1bJWv_IVluDpSnxUjaNNp8P-Pbtbvpt626_mTm7xnOwa2jdBrcWPwE0OAPpzLYcPEoPJX7VDdTagL9C55WsPQyPc4BWs-lq8hxkL_PFZJwFisZpG4DggrBUsUJFwGWqaJWSqCyKilFgIqZFQaIqFKEq4qQoyypNuJCRLEVM0jDhAxQdzipnvXdQ5Uq3-09aJ3WdU5Lv5OVbeflOXn6UtwXJH7Bxei3d5j_k5oBoADipsyghIua_A859cg
CODEN	ITAICB
CitedBy_id	crossref_primary_10_3390_jmse12030428 crossref_primary_10_1109_TIM_2024_3462997 crossref_primary_10_1111_mice_13403
Cites_doi	10.1109/CVPR.2017.690 10.1145/3503250 10.1007/BF00131148 10.1109/TAI.2022.3170001 10.5555/777092.777184 10.1177/0278364918784361 10.1016/j.patcog.2021.108225 10.1007/978-3-030-01270-0_50 10.1177/0278364908090961 10.1109/IROS.2012.6385773 10.1109/TSMC.2018.2804766 10.1109/ACCESS.2019.2928578 10.1109/ACCESS.2020.2983121 10.1007/BF00129684 10.1109/ICCRE49379.2020.9096497 10.1109/AINL-ISMW-FRUCT.2015.7382963 10.1109/TRO.2017.2705103 10.5244/c.27.13 10.1109/ICRA40945.2020.9197374 10.1109/CVPR.2017.699 10.4324/9781410605337-29 10.1109/34.601246 10.1109/TPAMI.2011.222 10.1109/CVPR.2017.695 10.1109/TAI.2021.3076021 10.1145/504729.504754 10.1109/ICCV.2003.1238663 10.1007/978-3-031-31438-4_5 10.1007/s10846-014-0029-6 10.1109/TPAMI.2007.1049 10.1109/ICRA.2014.6906584 10.1109/IROS40897.2019.8967726 10.1109/ICRA40945.2020.9196638 10.1109/LRA.2022.3142901 10.1007/978-3-030-69538-5_21 10.1109/ACCTCS52002.2021.00047 10.1145/3240508.3240525 10.1109/CVPR.2019.00342 10.1109/LRA.2021.3094228 10.1001/jama.284.15.1980 10.1007/978-3-319-46466-4_28 10.1109/TPAMI.2017.2658577 10.1109/IROS.2018.8593691 10.1109/CVPR46437.2021.00284 10.1109/34.206955 10.48550/ARXIV.1706.03762 10.1109/3DV53792.2021.00025 10.1109/TITS.2018.2866637 10.1007/978-3-319-10605-2_54 10.1109/ICRA40945.2020.9196900 10.1109/ICCV48922.2021.00617 10.1109/ACCESS.2019.2952161 10.3390/rs14081854 10.1177/0278364919883346 10.1109/ICPR.2014.698 10.1007/s12559-018-9591-8 10.1109/lcsys.2023.3340619 10.1109/iros55552.2023.10341922 10.1109/ICRA48506.2021.9561230 10.1109/IROS45743.2020.9341801 10.1109/ACCESS.2019.2904512 10.48550/ARXIV.1807.06521 10.1109/CVPR42600.2020.00917 10.1109/IROS40897.2019.8967919 10.1109/IROS40897.2019.8967590 10.1007/978-3-030-30683-0_11 10.1109/TRO.2021.3075644 10.1109/CVPR.2019.01238 10.1109/CVPR.2004.1315094 10.1109/ICRA.2017.7989236 10.1016/j.neucom.2021.05.027 10.1109/MRA.2011.943233 10.1109/CVPR.2019.00987 10.1109/ICCV.2015.316 10.1609/aaai.v34i06.6608 10.1109/ACCESS.2021.3050617 10.1145/358669.358692 10.1109/icra40945.2020.9197519 10.1109/CVPR.2018.00931 10.1007/s41651-020-00048-5 10.1109/LRA.2022.3150854 10.1109/ICCV.2019.00393 10.1109/LRA.2018.2859916 10.1177/0278364916679498 10.1109/ICCV.2011.6126544 10.1109/IROS40897.2019.8968008 10.1109/ICRA.2018.8460816 10.1145/3177853 10.1109/9.855552 10.1109/MAJICC53071.2021.9526266 10.1007/s11263-008-0152-6 10.1109/LRA.2018.2849609 10.1109/icra46639.2022.9812162 10.1109/ICAIBD51990.2021.9459086 10.1109/TPAMI.2016.2644615 10.1177/02783649221078612 10.1016/j.robot.2017.09.010 10.1007/978-3-031-20080-9_14 10.1109/TRO.2015.2463671 10.1177/1729881420919185 10.1109/TRO.2018.2853729 10.1109/TAI.2022.3194869 10.1109/TITS.2022.3175656 10.1109/IROS.2018.8593376 10.1007/s10851-009-0161-2 10.1109/ROBIO55434.2022.10011660 10.1109/CVPR52688.2022.00675 10.1109/TCDS.2020.3038898 10.1109/TPAMI.2003.1217599 10.1177/0278364915620033 10.1109/ICCV.2019.00775 10.1109/TPAMI.2004.17 10.1109/ROBOT.2010.5509636 10.1016/j.patcog.2019.107193 10.1109/CVPR.2019.00589 10.1016/j.neucom.2022.06.118 10.1007/978-3-030-20876-9_19 10.1109/CVPR.2016.572 10.1007/978-981-10-6370-1_41 10.1109/TRO.2012.2197158 10.1109/ICCV48922.2021.00619 10.1109/ICCV.2017.322 10.1007/978-3-030-27532-7_14 10.1109/CVPR.2018.00021 10.1109/ICRA.2019.8793836 10.1109/ICCV.2011.6126513 10.1109/CVPR.2018.00884 10.1109/ICRA.2018.8461251 10.1109/MRA.2014.2322282 10.1109/CVPR.2012.6248074 10.1109/ICCV.2017.447 10.1109/ICRA.2019.8793749 10.1109/ISMAR.2007.4538852 10.1109/TRO.2019.2909168 10.1186/s41074-017-0027-2 10.1109/TRO.2016.2624754 10.1109/ICCV48922.2021.00584 10.1109/LRA.2021.3058069 10.1109/TITS.2021.3074520 10.1109/LRA.2018.2803211 10.1109/CVPRW.2018.00060 10.1109/LRA.2018.2860039 10.1109/iros55552.2023.10341436 10.1016/j.vrih.2019.09.001 10.1109/LRA.2018.2793349 10.1109/IROS45743.2020.9340907 10.1109/ICRA.2015.7139836 10.1109/IROS.2015.7353389 10.1109/CVPR42600.2020.00136 10.5244/C.19.50 10.1109/CVPR.2017.700 10.1109/LRA.2020.2965415 10.1109/LRA.2020.2965893 10.1109/ICIP.2019.8802931
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION
DOI	10.1109/TAI.2023.3321032
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
Database_xml	– sequence: 1 dbid: RIE name: IEEE/IET Electronic Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	2691-4581
EndPage	2010
ExternalDocumentID	10_1109_TAI_2023_3321032 10268057
Genre	orig-research
GrantInformation_xml	– fundername: European Union's EU Framework Programme for Research and Innovation Horizon 2020 through REMARO Project grantid: 956200
GroupedDBID	0R~ 97E AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS IEDLZ IFIPE JAVBF M~E OCL RIA RIE AAYXX CITATION
ID	FETCH-LOGICAL-c179t-e535029c2bc6e3a9c1f906dbbf21e2571bb06f454cb78bddf9835a6ad5709483
IEDL.DBID	RIE
ISSN	2691-4581
IngestDate	Sat Nov 29 07:41:00 EST 2025 Tue Nov 18 22:31:16 EST 2025 Wed Aug 27 07:40:20 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	5
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-c179t-e535029c2bc6e3a9c1f906dbbf21e2571bb06f454cb78bddf9835a6ad5709483
ORCID	0000-0003-3581-9481 0000-0002-7143-8777 0009-0002-0445-8126
PageCount	21
ParticipantIDs	crossref_citationtrail_10_1109_TAI_2023_3321032 ieee_primary_10268057 crossref_primary_10_1109_TAI_2023_3321032
PublicationCentury	2000
PublicationDate	2024-May 2024-5-00
PublicationDateYYYYMMDD	2024-05-01
PublicationDate_xml	– month: 05 year: 2024 text: 2024-May
PublicationDecade	2020
PublicationTitle	IEEE transactions on artificial intelligence
PublicationTitleAbbrev	TAI
PublicationYear	2024
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref56 Lucas (ref41) 1981 ref59 ref58 ref53 ref52 ref55 ref168 ref54 ref169 Christiansen (ref32) 2019 Simonyan (ref119) 2014 Grisetti (ref155) 2011 ref170 ref177 ref178 ref51 Velikovi (ref114) 2017 ref175 ref50 ref176 ref173 ref174 ref172 ref46 Tomasi (ref42) 1991; 9 ref45 ref48 ref47 ref44 ref43 ref49 ref8 ref180 ref7 ref9 ref3 ref6 ref5 ref100 ref101 ref40 Jaderberg (ref163) 2015; 28 ref35 ref34 ref37 Zhang (ref70) 2020 ref36 ref31 ref148 ref30 ref149 ref33 ref147 ref39 ref38 Cohen (ref105) 2016 ref156 ref153 ref154 ref151 ref152 ref150 ref24 Cohen (ref106) 2018 ref23 ref26 ref25 ref20 ref159 ref22 ref157 ref21 ref158 ref28 ref27 Hutchinson (ref109) ref29 ref166 Tun (ref146) 2023 ref167 ref164 (ref171) 2021 Krizhevsky (ref118) 2012; 25 ref165 ref162 ref160 ref161 ref13 ref12 ref15 ref128 ref14 ref129 ref97 Welling (ref115) 2016 ref126 ref96 ref127 ref11 ref99 ref124 ref10 ref98 Aulinas (ref4); 184 ref17 ref16 ref19 ref18 Heyden (ref57) 2005; 3 Teed (ref139) 2021; 34 ref93 ref133 ref92 ref134 ref95 ref131 ref132 Tallec (ref107) 2018 ref91 ref90 ref89 ref86 ref137 ref85 ref138 ref88 ref87 Bian (ref94) 2019; 32 ref136 Grupp (ref179) 2017 ref82 ref144 ref81 ref145 ref84 ref142 ref83 Wang (ref130) 2020 ref143 ref140 ref141 ref80 ref79 ref108 ref78 ref75 ref74 ref77 ref102 ref76 ref103 Keriven (ref111) 2019; 32 ref2 ref1 Eigen (ref181) 2014; 27 Bronstein (ref104) 2021 ref71 ref112 ref73 ref72 ref110 He (ref135) 2015; 3385 Li (ref125) 2021 ref68 ref67 Yuan (ref116) 2020 ref117 ref69 ref64 ref63 ref66 ref113 ref65 ref60 ref122 ref123 ref62 ref120 ref61 ref121
References_xml	– year: 2021 ident: ref104 article-title: Geometric deep learning: Grids, groups, graphs, geodesics, and gauges – ident: ref46 doi: 10.1109/CVPR.2017.690 – ident: ref158 doi: 10.1145/3503250 – ident: ref100 doi: 10.1007/BF00131148 – ident: ref113 doi: 10.1109/TAI.2022.3170001 – ident: ref162 doi: 10.5555/777092.777184 – ident: ref102 doi: 10.1177/0278364918784361 – ident: ref72 doi: 10.1016/j.patcog.2021.108225 – ident: ref138 doi: 10.1007/978-3-030-01270-0_50 – ident: ref74 doi: 10.1177/0278364908090961 – ident: ref167 doi: 10.1109/IROS.2012.6385773 – ident: ref174 doi: 10.1109/TSMC.2018.2804766 – ident: ref36 doi: 10.1109/ACCESS.2019.2928578 – ident: ref25 doi: 10.1109/ACCESS.2020.2983121 – volume: 27 start-page: 2366 volume-title: Proc. 28th Annu. Conf. Neural Inf. Process. Syst. year: 2014 ident: ref181 article-title: Depth map prediction from a single image using a multi-scale deep network – volume: 9 start-page: 137 year: 1991 ident: ref42 article-title: Detection and tracking of point publication-title: Int. J. Comput. Vis. doi: 10.1007/BF00129684 – ident: ref58 doi: 10.1109/ICCRE49379.2020.9096497 – ident: ref81 doi: 10.1109/AINL-ISMW-FRUCT.2015.7382963 – ident: ref96 doi: 10.1109/TRO.2017.2705103 – ident: ref23 doi: 10.5244/c.27.13 – ident: ref61 doi: 10.1109/ICRA40945.2020.9197374 – ident: ref93 doi: 10.1109/CVPR.2017.699 – ident: ref128 doi: 10.4324/9781410605337-29 – ident: ref56 doi: 10.1109/34.601246 – ident: ref21 doi: 10.1109/TPAMI.2011.222 – ident: ref71 doi: 10.1109/CVPR.2017.695 – volume: 34 start-page: 16558 volume-title: Proc. Neural Inf. Process. Syst. year: 2021 ident: ref139 article-title: Droid-SLAM: Deep visual SLAM for monocular, stereo, and RGB-D cameras – ident: ref110 doi: 10.1109/TAI.2021.3076021 – ident: ref77 doi: 10.1145/504729.504754 – ident: ref62 doi: 10.1109/ICCV.2003.1238663 – ident: ref144 doi: 10.1007/978-3-031-31438-4_5 – ident: ref82 doi: 10.1007/s10846-014-0029-6 – ident: ref40 doi: 10.1109/TPAMI.2007.1049 – year: 2017 ident: ref114 article-title: Graph attention networks – ident: ref38 doi: 10.1109/ICRA.2014.6906584 – ident: ref65 doi: 10.1109/IROS40897.2019.8967726 – ident: ref169 doi: 10.1109/ICRA40945.2020.9196638 – start-page: 1 volume-title: Proc. 8th Int. Conf. Learn. Representations year: 2020 ident: ref116 article-title: StructPool: Structured graph pooling via conditional random fields – ident: ref122 doi: 10.1109/LRA.2022.3142901 – ident: ref143 doi: 10.1007/978-3-030-69538-5_21 – ident: ref47 doi: 10.1109/ACCTCS52002.2021.00047 – start-page: 9 volume-title: Proc. IEEE Int. Conf. Robot. Automat. year: 2011 ident: ref155 article-title: g2o: A general framework for (hyper) graph optimization – ident: ref120 doi: 10.1145/3240508.3240525 – ident: ref141 doi: 10.1109/CVPR.2019.00342 – ident: ref67 doi: 10.1109/LRA.2021.3094228 – ident: ref127 doi: 10.1001/jama.284.15.1980 – volume-title: Proc. Int. Symp. Robot. year: 2023 ident: ref146 article-title: Loss it right: Euclidean and Riemannian metrics in learning-based visual odometry – ident: ref29 doi: 10.1007/978-3-319-46466-4_28 – ident: ref39 doi: 10.1109/TPAMI.2017.2658577 – ident: ref48 doi: 10.1109/IROS.2018.8593691 – ident: ref161 doi: 10.1109/CVPR46437.2021.00284 – ident: ref34 doi: 10.1109/34.206955 – ident: ref108 doi: 10.48550/ARXIV.1706.03762 – ident: ref124 doi: 10.1109/3DV53792.2021.00025 – ident: ref85 doi: 10.1109/TITS.2018.2866637 – ident: ref35 doi: 10.1007/978-3-319-10605-2_54 – ident: ref92 doi: 10.1109/ICRA40945.2020.9196900 – ident: ref159 doi: 10.1109/ICCV48922.2021.00617 – ident: ref49 doi: 10.1109/ACCESS.2019.2952161 – ident: ref148 doi: 10.3390/rs14081854 – ident: ref175 doi: 10.1177/0278364919883346 – ident: ref97 doi: 10.1109/ICPR.2014.698 – year: 2021 ident: ref125 article-title: TranscCamp: Graph transformer for 6-dof camera pose estimation – ident: ref17 doi: 10.1007/s12559-018-9591-8 – ident: ref157 doi: 10.1109/lcsys.2023.3340619 – ident: ref160 doi: 10.1109/iros55552.2023.10341922 – volume: 32 start-page: 7092 volume-title: Proc. 33rd Int. Conf. Adv. Neural Inf. Process. Syst. year: 2019 ident: ref111 article-title: Universal invariant and equivariant graph neural networks – ident: ref87 doi: 10.1109/ICRA48506.2021.9561230 – ident: ref177 doi: 10.1109/IROS45743.2020.9341801 – ident: ref84 doi: 10.1109/ACCESS.2019.2904512 – ident: ref151 doi: 10.48550/ARXIV.1807.06521 – ident: ref153 doi: 10.1109/CVPR42600.2020.00917 – ident: ref133 doi: 10.1109/IROS40897.2019.8967919 – ident: ref170 doi: 10.1109/IROS40897.2019.8967590 – ident: ref10 doi: 10.1007/978-3-030-30683-0_11 – ident: ref63 doi: 10.1109/TRO.2021.3075644 – ident: ref83 doi: 10.1109/CVPR.2019.01238 – ident: ref20 doi: 10.1109/CVPR.2004.1315094 – ident: ref129 doi: 10.1109/ICRA.2017.7989236 – volume-title: Proc. J. Int. Conf. Learn. Representations year: 2016 ident: ref115 article-title: Semi-supervised classification with graph convolutional networks – ident: ref30 doi: 10.1016/j.neucom.2021.05.027 – ident: ref11 doi: 10.1109/MRA.2011.943233 – ident: ref27 doi: 10.1109/CVPR.2019.00987 – ident: ref132 doi: 10.1109/ICCV.2015.316 – ident: ref136 doi: 10.1609/aaai.v34i06.6608 – ident: ref53 doi: 10.1109/ACCESS.2021.3050617 – ident: ref43 doi: 10.1145/358669.358692 – ident: ref165 doi: 10.1109/icra40945.2020.9197519 – ident: ref134 doi: 10.1109/CVPR.2018.00931 – year: 2020 ident: ref130 article-title: TartanVO: A generalizable learning-based VO – ident: ref103 doi: 10.1007/s41651-020-00048-5 – year: 2014 ident: ref119 article-title: Very deep convolutional networks for large-scale image recognition – ident: ref150 doi: 10.1109/LRA.2022.3150854 – ident: ref95 doi: 10.1109/ICCV.2019.00393 – ident: ref123 doi: 10.1109/LRA.2018.2859916 – ident: ref173 doi: 10.1177/0278364916679498 – ident: ref22 doi: 10.1109/ICCV.2011.6126544 – start-page: 2990 volume-title: Proc. Int. Conf. Mach. Learn. year: 2016 ident: ref105 article-title: Group equivariant convolutional networks – ident: ref37 doi: 10.1109/IROS40897.2019.8968008 – ident: ref73 doi: 10.1109/ICRA.2018.8460816 – ident: ref9 doi: 10.1145/3177853 – volume: 28 start-page: 2017 volume-title: Proc. Neural Inf. Process. Syst. year: 2015 ident: ref163 article-title: Spatial transformer networks – ident: ref3 doi: 10.1109/9.855552 – ident: ref1 doi: 10.1109/MAJICC53071.2021.9526266 – ident: ref60 doi: 10.1007/s11263-008-0152-6 – ident: ref68 doi: 10.1109/LRA.2018.2849609 – ident: ref90 doi: 10.1109/icra46639.2022.9812162 – volume: 184 start-page: 363 volume-title: Proc. Conf. Artif. Intell. Res. Develop. ident: ref4 article-title: The SLAM problem: A survey – ident: ref45 doi: 10.1109/ICAIBD51990.2021.9459086 – ident: ref50 doi: 10.1109/TPAMI.2016.2644615 – ident: ref176 doi: 10.1177/02783649221078612 – ident: ref5 doi: 10.1016/j.robot.2017.09.010 – ident: ref126 doi: 10.1007/978-3-031-20080-9_14 – ident: ref28 doi: 10.1109/TRO.2015.2463671 – ident: ref18 doi: 10.1177/1729881420919185 – ident: ref24 doi: 10.1109/TRO.2018.2853729 – ident: ref112 doi: 10.1109/TAI.2022.3194869 – ident: ref13 doi: 10.1109/TITS.2022.3175656 – year: 2019 ident: ref32 article-title: Unsuperpoint: End-to-end unsupervised interest point detector and descriptor – ident: ref75 doi: 10.1109/IROS.2018.8593376 – ident: ref180 doi: 10.1007/s10851-009-0161-2 – start-page: 674 year: 1981 ident: ref41 article-title: An iterative image registration technique with an application to stereo vision – ident: ref147 doi: 10.1109/ROBIO55434.2022.10011660 – volume: 32 start-page: 35 volume-title: Proc. Neural Inf. Process. Syst. year: 2019 ident: ref94 article-title: Unsupervised scale-consistent depth and ego-motion learning from monocular video – volume-title: Proc. Int. Conf. Learn. Representations year: 2018 ident: ref106 article-title: Spherical CNNs – ident: ref142 doi: 10.1109/CVPR52688.2022.00675 – ident: ref12 doi: 10.1109/TCDS.2020.3038898 – volume: 25 start-page: 1 volume-title: Proc. Neural Inf. Process. Syst. year: 2012 ident: ref118 article-title: Imagenet classification with deep convolutional neural networks – ident: ref59 doi: 10.1109/TPAMI.2003.1217599 – ident: ref166 doi: 10.1177/0278364915620033 – ident: ref168 doi: 10.1109/ICCV.2019.00775 – ident: ref55 doi: 10.1109/TPAMI.2004.17 – ident: ref76 doi: 10.1109/ROBOT.2010.5509636 – ident: ref88 doi: 10.1016/j.patcog.2019.107193 – year: 2021 ident: ref171 article-title: The ETH-Microsoft localization dataset – ident: ref145 doi: 10.1109/CVPR.2019.00589 – ident: ref140 doi: 10.1016/j.neucom.2022.06.118 – start-page: 4533 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref109 article-title: LieTransformer: Equivariant self-attention for lie groups – ident: ref137 doi: 10.1007/978-3-030-20876-9_19 – ident: ref117 doi: 10.1109/CVPR.2016.572 – ident: ref16 doi: 10.1007/978-981-10-6370-1_41 – ident: ref64 doi: 10.1109/TRO.2012.2197158 – year: 2017 ident: ref179 article-title: EVO: Python package for the evaluation of odometry and SLAM – ident: ref154 doi: 10.1109/ICCV48922.2021.00619 – ident: ref52 doi: 10.1109/ICCV.2017.322 – ident: ref2 doi: 10.1007/978-3-030-27532-7_14 – ident: ref99 doi: 10.1109/CVPR.2018.00021 – ident: ref86 doi: 10.1109/ICRA.2019.8793836 – ident: ref33 doi: 10.1109/ICCV.2011.6126513 – ident: ref164 doi: 10.1109/CVPR.2018.00884 – ident: ref91 doi: 10.1109/ICRA.2018.8461251 – ident: ref15 doi: 10.1109/MRA.2014.2322282 – ident: ref172 doi: 10.1109/CVPR.2012.6248074 – ident: ref54 doi: 10.1109/ICCV.2017.447 – ident: ref98 doi: 10.1109/ICRA.2019.8793749 – ident: ref19 doi: 10.1109/ISMAR.2007.4538852 – ident: ref44 doi: 10.1109/TRO.2019.2909168 – ident: ref6 doi: 10.1186/s41074-017-0027-2 – ident: ref7 doi: 10.1109/TRO.2016.2624754 – ident: ref156 doi: 10.1109/ICCV48922.2021.00584 – ident: ref26 doi: 10.1109/LRA.2021.3058069 – ident: ref69 doi: 10.1109/TITS.2021.3074520 – ident: ref131 doi: 10.1109/LRA.2018.2803211 – year: 2018 ident: ref107 article-title: Can recurrent neural networks warp time? – ident: ref31 doi: 10.1109/CVPRW.2018.00060 – ident: ref51 doi: 10.1109/LRA.2018.2860039 – ident: ref178 doi: 10.1109/iros55552.2023.10341436 – ident: ref8 doi: 10.1016/j.vrih.2019.09.001 – ident: ref79 doi: 10.1109/LRA.2018.2793349 – ident: ref66 doi: 10.1109/IROS45743.2020.9340907 – ident: ref14 doi: 10.1109/ICRA.2015.7139836 – ident: ref78 doi: 10.1109/IROS.2015.7353389 – ident: ref149 doi: 10.1109/CVPR42600.2020.00136 – volume: 3385 year: 2015 ident: ref135 article-title: Deep residual learning for image recognition publication-title: CoRR – ident: ref80 doi: 10.5244/C.19.50 – volume: 3 start-page: 45 year: 2005 ident: ref57 article-title: Multiple view geometry publication-title: Emerg. Topics Comput. Vis. – ident: ref152 doi: 10.1109/CVPR.2017.700 – ident: ref89 doi: 10.1109/LRA.2020.2965415 – ident: ref101 doi: 10.1109/LRA.2020.2965893 – year: 2020 ident: ref70 article-title: VDO-SLAM: A visual dynamic object-aware SLAM system – ident: ref121 doi: 10.1109/ICIP.2019.8802931
SSID	ssj0002512227
Score	2.275674
Snippet	With the rise of deep learning, there is a fundamental change in visual simultaneous localization and mapping (SLAM) algorithms toward developing different...
SourceID	crossref ieee
SourceType	Enrichment Source Index Database Publisher
StartPage	1990
SubjectTerms	Cameras Deep learning Feature extraction Optimization Pipelines robot vision systems Simultaneous localization and mapping Surveys visual odometry Visualization
Title	Monocular Visual Simultaneous Localization and Mapping: (R)Evolution From Geometry to Deep Learning-Based Pipelines
URI	https://ieeexplore.ieee.org/document/10268057
Volume	5
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE/IET Electronic Library customDbUrl: eissn: 2691-4581 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002512227 issn: 2691-4581 databaseCode: RIE dateStart: 20200101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2691-4581 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002512227 issn: 2691-4581 databaseCode: M~E dateStart: 20200101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEF6sePBifVSsL_bgwR5S0zx2s958tCpUKVrEW9hkJyVgk9Kmghd_u7PJttSDgpcQwgyEfDuZmd35Zgg5w8xf-oxzy5MOXpjvWkJ4rpWASHzJdBVP2cS1z5-egrc3MTBk9ZILAwBl8Rm09W15lq_yeK63ytDCHRZggFEjNc5ZRdZabqhoR-04fHEUaYuL4dVDW08Hb7uaqOI6P1zPyiyV0pX06v98iW2yZWJGelWBvEPWINsl9cU8BmrMc4_M0EDzsq6UvqazOaq8pLpgUGaA-T3ta7dlaJdUZoo-St2cYXRJz59b3Q-zBmlvmo_pHeRjKKaftMjpLcCEmj6sI-sa3Z6ig3Siiewwa5Bhrzu8ubfMUAUrRtsrLPBd33ZE7EQxA1eKuJMIm6koSpwOoP12oshmied7ccSDSKlEYIwmmVQ-x0wwcPfJepZncEBo1NHiCDSDxJNCBZwDcMUwRcLfQCKb5GLxucPYNBzXcy_ewzLxsEWIAIUaoNAA1CStpcakarbxh2xDY7MiV8Fy-MvzI7KJ6l5Vq3hM1ovpHE7IRvxRpLPpKak9fnVPywX1DdhpyLQ
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDI54SXDhjRjPHDjAoaNL26ThxmtsYkwIJsStSht3msTaaeuQ-Pc4bYbgABKXqqqcqsoX13bizybkBCN_FXAhHF8xvPDAc6T0PScFmQaKmyyesohrR3S74eurfLRk9ZILAwBl8hnUzW15lq_zZGq2ylDDGQ_RwZgni4HvM7eia31tqRhTzZiYHUa68rx32a6b_uB1z1BVPPbD-HzrplIak-baPz9jnaxar5FeVjBvkDnINsnarCMDtQq6RSaoonmZWUpfBpMpDnkemJRBlQFG-LRjDJclXlKVafqgTHmG_gU9fTq7fberkDbH-ZDeQT6EYvxBi5zeAIyorcTad67Q8Gn6OBgZKjtMtkmvedu7bjm2rYKToPYVDgRe4DKZsDjh4CmZNFLpch3HKWsAanAjjl2e-oGfxCKMtU4lemmKKx0IjAVDb4csZHkGu4TGDSOOUHNIfSV1KASA0ByDJPwRpKpGzmfTHSW25LjpfPEWlaGHKyMEKDIARRagGjn7GjGqym38IbttsPkmV8Gy98vzY7Lc6j10ok67e79PVvBVfpW5eEAWivEUDslS8l4MJuOjcll9Aq9uyso
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=Monocular+Visual+Simultaneous+Localization+and+Mapping%3A+%28R%29Evolution+From+Geometry+to+Deep+Learning-Based+Pipelines&rft.jtitle=IEEE+transactions+on+artificial+intelligence&rft.au=%C3%81lvarez-Tu%C3%B1%C3%B3n%2C+Olaya&rft.au=Brodskiy%2C+Yury&rft.au=Kayacan%2C+Erdal&rft.date=2024-05-01&rft.issn=2691-4581&rft.eissn=2691-4581&rft.volume=5&rft.issue=5&rft.spage=1990&rft.epage=2010&rft_id=info:doi/10.1109%2FTAI.2023.3321032&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TAI_2023_3321032
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2691-4581&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2691-4581&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2691-4581&client=summon