Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387614384> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4387614384 endingPage "4277" @default.
- W4387614384 startingPage "4277" @default.
- W4387614384 abstract "In driverless systems (scenarios such as subways, buses, trucks, etc.), multi-modal data fusion, such as light detection and ranging (LiDAR) points and camera images, is essential for accurate 3D object detection. In the fusion process, the information interaction between the modes is challenging due to the different coordinate systems of various sensors and the significant difference in the density of the collected data. It is necessary to fully consider the consistency and complementarity of multi-modal information, make up for the gap between multi-source data density, and achieve the joint interactive processing of multi-source information. Therefore, this paper is based on Transformer to improve a new multi-modal fusion model called PIDFusion for 3D object detection. Firstly, the method uses the results of 2D instance segmentation to generate dense 3D virtual points to enhance the original sparse 3D point clouds. This optimizes the issue that the nearest Euclidean distance in the 2D image space cannot ensure the nearest in the 3D space. Secondly, a new cross-modal fusion architecture is designed to maintain individual per-modality features to take advantage of their unique characteristics during 3D object detection. Finally, an instance-level fusion module is proposed to enhance semantic consistency through cross-modal feature interaction. Experiments show that PIDFusion is far ahead of existing 3D object detection methods, especially for small and long-range objects, with 70.8 mAP and 73.5 NDS on the nuScenes test set." @default.
- W4387614384 created "2023-10-14" @default.
- W4387614384 creator A5014154811 @default.
- W4387614384 creator A5027377167 @default.
- W4387614384 creator A5088888083 @default.
- W4387614384 date "2023-10-13" @default.
- W4387614384 modified "2023-10-15" @default.
- W4387614384 title "PIDFusion: Fusing Dense LiDAR Points and Camera Images at Pixel-Instance Level for 3D Object Detection" @default.
- W4387614384 cites W2194775991 @default.
- W4387614384 cites W2468368736 @default.
- W4387614384 cites W2555618208 @default.
- W4387614384 cites W2897529137 @default.
- W4387614384 cites W2954174912 @default.
- W4387614384 cites W2963182550 @default.
- W4387614384 cites W2963727135 @default.
- W4387614384 cites W2968296999 @default.
- W4387614384 cites W3035461736 @default.
- W4387614384 cites W3035574168 @default.
- W4387614384 cites W3107819843 @default.
- W4387614384 cites W3109395584 @default.
- W4387614384 cites W3128555787 @default.
- W4387614384 cites W3167095230 @default.
- W4387614384 cites W3170030651 @default.
- W4387614384 cites W3173668541 @default.
- W4387614384 cites W3209639308 @default.
- W4387614384 cites W3215100485 @default.
- W4387614384 cites W4214763741 @default.
- W4387614384 cites W4214777292 @default.
- W4387614384 cites W4225986494 @default.
- W4387614384 cites W4285606661 @default.
- W4387614384 cites W4312307873 @default.
- W4387614384 cites W4312707458 @default.
- W4387614384 cites W4312954223 @default.
- W4387614384 cites W4313142137 @default.
- W4387614384 cites W4383066393 @default.
- W4387614384 cites W4385804883 @default.
- W4387614384 cites W4385804922 @default.
- W4387614384 cites W4386075854 @default.
- W4387614384 doi "https://doi.org/10.3390/math11204277" @default.
- W4387614384 hasPublicationYear "2023" @default.
- W4387614384 type Work @default.
- W4387614384 citedByCount "0" @default.
- W4387614384 crossrefType "journal-article" @default.
- W4387614384 hasAuthorship W4387614384A5014154811 @default.
- W4387614384 hasAuthorship W4387614384A5027377167 @default.
- W4387614384 hasAuthorship W4387614384A5088888083 @default.
- W4387614384 hasBestOaLocation W43876143841 @default.
- W4387614384 hasConcept C131979681 @default.
- W4387614384 hasConcept C154945302 @default.
- W4387614384 hasConcept C160633673 @default.
- W4387614384 hasConcept C205649164 @default.
- W4387614384 hasConcept C2776151529 @default.
- W4387614384 hasConcept C31972630 @default.
- W4387614384 hasConcept C33954974 @default.
- W4387614384 hasConcept C41008148 @default.
- W4387614384 hasConcept C51399673 @default.
- W4387614384 hasConcept C62649853 @default.
- W4387614384 hasConcept C89600930 @default.
- W4387614384 hasConceptScore W4387614384C131979681 @default.
- W4387614384 hasConceptScore W4387614384C154945302 @default.
- W4387614384 hasConceptScore W4387614384C160633673 @default.
- W4387614384 hasConceptScore W4387614384C205649164 @default.
- W4387614384 hasConceptScore W4387614384C2776151529 @default.
- W4387614384 hasConceptScore W4387614384C31972630 @default.
- W4387614384 hasConceptScore W4387614384C33954974 @default.
- W4387614384 hasConceptScore W4387614384C41008148 @default.
- W4387614384 hasConceptScore W4387614384C51399673 @default.
- W4387614384 hasConceptScore W4387614384C62649853 @default.
- W4387614384 hasConceptScore W4387614384C89600930 @default.
- W4387614384 hasIssue "20" @default.
- W4387614384 hasLocation W43876143841 @default.
- W4387614384 hasOpenAccess W4387614384 @default.
- W4387614384 hasPrimaryLocation W43876143841 @default.
- W4387614384 hasRelatedWork W1964041166 @default.
- W4387614384 hasRelatedWork W2739701376 @default.
- W4387614384 hasRelatedWork W2901265155 @default.
- W4387614384 hasRelatedWork W2956374172 @default.
- W4387614384 hasRelatedWork W3188333020 @default.
- W4387614384 hasRelatedWork W4210818033 @default.
- W4387614384 hasRelatedWork W4293094720 @default.
- W4387614384 hasRelatedWork W4308071650 @default.
- W4387614384 hasRelatedWork W4319317934 @default.
- W4387614384 hasRelatedWork W4319837668 @default.
- W4387614384 hasVolume "11" @default.
- W4387614384 isParatext "false" @default.
- W4387614384 isRetracted "false" @default.
- W4387614384 workType "article" @default.