Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313431522> ?p ?o ?g. }
- W4313431522 endingPage "4368" @default.
- W4313431522 startingPage "4349" @default.
- W4313431522 abstract "Abstract Monocular 3D vehicle localization is an important task for vehicle behaviour analysis, traffic flow parameter estimation and autonomous driving in Intelligent Transportation System (ITS) and Cooperative Vehicle Infrastructure System (CVIS), which is usually achieved by monocular 3D vehicle detection. However, monocular cameras cannot obtain depth information directly due to the inherent imaging mechanism, resulting in more challenging monocular 3D tasks. Currently, most of the monocular 3D vehicle detection methods still rely on 2D detectors and additional geometric constraint modules to recover 3D vehicle information, which reduces the efficiency. At the same time, most of the research is based on datasets of onboard scenes, instead of roadside perspective, which is limited in large-scale 3D perception. Therefore, we focus on 3D vehicle detection without 2D detectors in roadside scenes. We propose a 3D vehicle localization network CenterLoc3D for roadside monocular cameras, which directly predicts centroid and eight vertexes in image space, and the dimension of 3D bounding boxes without 2D detectors. To improve the precision of 3D vehicle localization, we propose a multi-scale weighted-fusion module and a loss with spatial constraints embedded in CenterLoc3D. Firstly, the transformation matrix between 2D image space and 3D world space is solved by camera calibration. Secondly, vehicle type, centroid, eight vertexes, and the dimension of 3D vehicle bounding boxes are obtained by CenterLoc3D. Finally, centroid in 3D world space can be obtained by camera calibration and CenterLoc3D for 3D vehicle localization. To the best of our knowledge, this is the first application of 3D vehicle localization for roadside monocular cameras. Hence, we also propose a benchmark for this application including a dataset (SVLD-3D), an annotation tool (LabelImg-3D), and evaluation metrics. Through experimental validation, the proposed method achieves high accuracy with $$A{P_{3D}}$$ <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML> <mml:mrow> <mml:mi>A</mml:mi> <mml:msub> <mml:mi>P</mml:mi> <mml:mrow> <mml:mn>3</mml:mn> <mml:mi>D</mml:mi> </mml:mrow> </mml:msub> </mml:mrow> </mml:math> of 51.30%, average 3D localization precision of 98%, average 3D dimension precision of 85% and real-time performance with FPS of 41.18." @default.
- W4313431522 created "2023-01-06" @default.
- W4313431522 creator A5002446079 @default.
- W4313431522 creator A5008672520 @default.
- W4313431522 creator A5032539074 @default.
- W4313431522 creator A5088793655 @default.
- W4313431522 date "2023-01-03" @default.
- W4313431522 modified "2023-09-25" @default.
- W4313431522 title "CenterLoc3D: monocular 3D vehicle localization network for roadside surveillance cameras" @default.
- W4313431522 cites W2031489346 @default.
- W4313431522 cites W2144995066 @default.
- W4313431522 cites W2150066425 @default.
- W4313431522 cites W2194775991 @default.
- W4313431522 cites W2468368736 @default.
- W4313431522 cites W2560544142 @default.
- W4313431522 cites W2565639579 @default.
- W4313431522 cites W2590234360 @default.
- W4313431522 cites W2605189827 @default.
- W4313431522 cites W2752782242 @default.
- W4313431522 cites W2914308938 @default.
- W4313431522 cites W2949708697 @default.
- W4313431522 cites W2949777529 @default.
- W4313431522 cites W2950347718 @default.
- W4313431522 cites W2953941229 @default.
- W4313431522 cites W2962807143 @default.
- W4313431522 cites W2963323244 @default.
- W4313431522 cites W2963351448 @default.
- W4313431522 cites W2963727135 @default.
- W4313431522 cites W2963794551 @default.
- W4313431522 cites W2963809933 @default.
- W4313431522 cites W2964062501 @default.
- W4313431522 cites W2964166085 @default.
- W4313431522 cites W2968296999 @default.
- W4313431522 cites W2969050719 @default.
- W4313431522 cites W2997747012 @default.
- W4313431522 cites W3011371059 @default.
- W4313431522 cites W3012466933 @default.
- W4313431522 cites W3013747287 @default.
- W4313431522 cites W3030121836 @default.
- W4313431522 cites W3034314779 @default.
- W4313431522 cites W3035172746 @default.
- W4313431522 cites W3035180028 @default.
- W4313431522 cites W3035254347 @default.
- W4313431522 cites W3035574168 @default.
- W4313431522 cites W3037450713 @default.
- W4313431522 cites W3098467253 @default.
- W4313431522 cites W3106250896 @default.
- W4313431522 cites W3114509423 @default.
- W4313431522 cites W3129282545 @default.
- W4313431522 cites W3176319743 @default.
- W4313431522 cites W3183713609 @default.
- W4313431522 cites W3215100485 @default.
- W4313431522 cites W639708223 @default.
- W4313431522 doi "https://doi.org/10.1007/s40747-022-00962-9" @default.
- W4313431522 hasPublicationYear "2023" @default.
- W4313431522 type Work @default.
- W4313431522 citedByCount "2" @default.
- W4313431522 countsByYear W43134315222023 @default.
- W4313431522 crossrefType "journal-article" @default.
- W4313431522 hasAuthorship W4313431522A5002446079 @default.
- W4313431522 hasAuthorship W4313431522A5008672520 @default.
- W4313431522 hasAuthorship W4313431522A5032539074 @default.
- W4313431522 hasAuthorship W4313431522A5088793655 @default.
- W4313431522 hasBestOaLocation W43134315221 @default.
- W4313431522 hasConcept C146599234 @default.
- W4313431522 hasConcept C154945302 @default.
- W4313431522 hasConcept C158829959 @default.
- W4313431522 hasConcept C31972630 @default.
- W4313431522 hasConcept C41008148 @default.
- W4313431522 hasConcept C63584917 @default.
- W4313431522 hasConcept C65909025 @default.
- W4313431522 hasConceptScore W4313431522C146599234 @default.
- W4313431522 hasConceptScore W4313431522C154945302 @default.
- W4313431522 hasConceptScore W4313431522C158829959 @default.
- W4313431522 hasConceptScore W4313431522C31972630 @default.
- W4313431522 hasConceptScore W4313431522C41008148 @default.
- W4313431522 hasConceptScore W4313431522C63584917 @default.
- W4313431522 hasConceptScore W4313431522C65909025 @default.
- W4313431522 hasFunder F4320321001 @default.
- W4313431522 hasFunder F4320336350 @default.
- W4313431522 hasIssue "4" @default.
- W4313431522 hasLocation W43134315221 @default.
- W4313431522 hasLocation W43134315222 @default.
- W4313431522 hasOpenAccess W4313431522 @default.
- W4313431522 hasPrimaryLocation W43134315221 @default.
- W4313431522 hasRelatedWork W141379373 @default.
- W4313431522 hasRelatedWork W1614704886 @default.
- W4313431522 hasRelatedWork W2078598182 @default.
- W4313431522 hasRelatedWork W2092543616 @default.
- W4313431522 hasRelatedWork W2113039159 @default.
- W4313431522 hasRelatedWork W2787139137 @default.
- W4313431522 hasRelatedWork W4224011692 @default.
- W4313431522 hasRelatedWork W4285813118 @default.
- W4313431522 hasRelatedWork W4312559648 @default.
- W4313431522 hasRelatedWork W4312581048 @default.
- W4313431522 hasVolume "9" @default.
- W4313431522 isParatext "false" @default.
- W4313431522 isRetracted "false" @default.