Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315777727> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4315777727 abstract "3D object detection is an important task in autonomous driving scenario, which is the basis of perception and understanding of 3D scenes. LiDAR and camera are two commonly used sensors in 3D object detection tasks. However, using a single sensor to collect data will make some objects difficult to detect because both sensors have insurmountable shortcomings. Unexpectedly, LiDAR-only detection methods tend to show better performance than the multi-sensor methods in public benchmarks. This shows that people need to further explore the methods of combining the data of the two sensors. Recently, PointPainting has been presented to combine the data of LiDAR and camera more efficiently by attaching the result of image semantic segmentation to point cloud data as new channels. In this paper, we propose an error anchor punishment mechanism based on image semantic segmentation results. After the semantic augmentation of the point cloud data, we judge whether the semantic result of each point is correct by traversing the groundtruth boxes. Further, we assign different weights to each anchor according to the error points contained in each anchor. Experimental results on the KITTI valid set show that SemanticAnchors achieves better performance in both 3D and birds eyes view benchmarks. In particular, our method adds little extra computation and achieves performance improvement in all categories." @default.
- W4315777727 created "2023-01-13" @default.
- W4315777727 creator A5004277281 @default.
- W4315777727 creator A5014703686 @default.
- W4315777727 creator A5030697054 @default.
- W4315777727 creator A5032116461 @default.
- W4315777727 creator A5041053876 @default.
- W4315777727 creator A5060335470 @default.
- W4315777727 date "2022-12-16" @default.
- W4315777727 modified "2023-10-12" @default.
- W4315777727 title "SemanticAnchors: Sequential Fusion using Lidar Point Cloud and Anchors with Semantic Annotations for 3D Object Detection" @default.
- W4315777727 cites W1903029394 @default.
- W4315777727 cites W2150066425 @default.
- W4315777727 cites W2340897893 @default.
- W4315777727 cites W2555618208 @default.
- W4315777727 cites W2897529137 @default.
- W4315777727 cites W2963300546 @default.
- W4315777727 cites W2963351448 @default.
- W4315777727 cites W2963400571 @default.
- W4315777727 cites W2968296999 @default.
- W4315777727 cites W2998254148 @default.
- W4315777727 cites W3034314779 @default.
- W4315777727 cites W3035461736 @default.
- W4315777727 cites W3107819843 @default.
- W4315777727 cites W3108426750 @default.
- W4315777727 cites W3130463448 @default.
- W4315777727 doi "https://doi.org/10.1109/iciea54703.2022.10006149" @default.
- W4315777727 hasPublicationYear "2022" @default.
- W4315777727 type Work @default.
- W4315777727 citedByCount "0" @default.
- W4315777727 crossrefType "proceedings-article" @default.
- W4315777727 hasAuthorship W4315777727A5004277281 @default.
- W4315777727 hasAuthorship W4315777727A5014703686 @default.
- W4315777727 hasAuthorship W4315777727A5030697054 @default.
- W4315777727 hasAuthorship W4315777727A5032116461 @default.
- W4315777727 hasAuthorship W4315777727A5041053876 @default.
- W4315777727 hasAuthorship W4315777727A5060335470 @default.
- W4315777727 hasConcept C124504099 @default.
- W4315777727 hasConcept C127313418 @default.
- W4315777727 hasConcept C131979681 @default.
- W4315777727 hasConcept C154945302 @default.
- W4315777727 hasConcept C177264268 @default.
- W4315777727 hasConcept C199360897 @default.
- W4315777727 hasConcept C2524010 @default.
- W4315777727 hasConcept C2776151529 @default.
- W4315777727 hasConcept C2781238097 @default.
- W4315777727 hasConcept C28719098 @default.
- W4315777727 hasConcept C31972630 @default.
- W4315777727 hasConcept C33923547 @default.
- W4315777727 hasConcept C33954974 @default.
- W4315777727 hasConcept C41008148 @default.
- W4315777727 hasConcept C51399673 @default.
- W4315777727 hasConcept C62649853 @default.
- W4315777727 hasConcept C89600930 @default.
- W4315777727 hasConceptScore W4315777727C124504099 @default.
- W4315777727 hasConceptScore W4315777727C127313418 @default.
- W4315777727 hasConceptScore W4315777727C131979681 @default.
- W4315777727 hasConceptScore W4315777727C154945302 @default.
- W4315777727 hasConceptScore W4315777727C177264268 @default.
- W4315777727 hasConceptScore W4315777727C199360897 @default.
- W4315777727 hasConceptScore W4315777727C2524010 @default.
- W4315777727 hasConceptScore W4315777727C2776151529 @default.
- W4315777727 hasConceptScore W4315777727C2781238097 @default.
- W4315777727 hasConceptScore W4315777727C28719098 @default.
- W4315777727 hasConceptScore W4315777727C31972630 @default.
- W4315777727 hasConceptScore W4315777727C33923547 @default.
- W4315777727 hasConceptScore W4315777727C33954974 @default.
- W4315777727 hasConceptScore W4315777727C41008148 @default.
- W4315777727 hasConceptScore W4315777727C51399673 @default.
- W4315777727 hasConceptScore W4315777727C62649853 @default.
- W4315777727 hasConceptScore W4315777727C89600930 @default.
- W4315777727 hasLocation W43157777271 @default.
- W4315777727 hasOpenAccess W4315777727 @default.
- W4315777727 hasPrimaryLocation W43157777271 @default.
- W4315777727 hasRelatedWork W1721780360 @default.
- W4315777727 hasRelatedWork W1963494852 @default.
- W4315777727 hasRelatedWork W2004370856 @default.
- W4315777727 hasRelatedWork W2019566805 @default.
- W4315777727 hasRelatedWork W2021186063 @default.
- W4315777727 hasRelatedWork W2095705906 @default.
- W4315777727 hasRelatedWork W2383464976 @default.
- W4315777727 hasRelatedWork W2739874619 @default.
- W4315777727 hasRelatedWork W4312981603 @default.
- W4315777727 hasRelatedWork W1967061043 @default.
- W4315777727 isParatext "false" @default.
- W4315777727 isRetracted "false" @default.
- W4315777727 workType "article" @default.