Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386780265> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4386780265 endingPage "103488" @default.
- W4386780265 startingPage "103488" @default.
- W4386780265 abstract "For intelligent transportation systems, moving object segmentation (MOS) provides valuable information for robots and intelligent vehicles, such as collision avoidance, path planning, and static map construction. However, all existing 3D point cloud MOS methods are based on LiDAR-only, which limits the ability to fuse supplementary information from different sensors. In this article, we solve the robust and accurate 3D MOS problem by designing a dual-stream network that integrates point clouds and images. We propose a perspective residual mechanism to mine the spatio-temporal motion information of point clouds, and design a fusion module based on Transformer Attention to extract multi-scale feature information from point clouds and images, improving the segmentation integrity of moving objects. Many experiments on the benchmark dataset show the superiority of our method. On the Semantic-KITTI, we outperform the advanced method by 6.5% mIoU. And we further apply our proposed model to the Semantic-KITTI: Moving Object Segmentation competition and achieve an advanced ranking on the leaderboard." @default.
- W4386780265 created "2023-09-16" @default.
- W4386780265 creator A5066333395 @default.
- W4386780265 creator A5080730492 @default.
- W4386780265 date "2023-09-01" @default.
- W4386780265 modified "2023-09-26" @default.
- W4386780265 title "An efficient image-guided-based 3D point cloud moving object segmentation with transformer-attention in autonomous driving" @default.
- W4386780265 cites W2342662179 @default.
- W4386780265 cites W2555618208 @default.
- W4386780265 cites W2795587607 @default.
- W4386780265 cites W2804870843 @default.
- W4386780265 cites W2962771259 @default.
- W4386780265 cites W2963281829 @default.
- W4386780265 cites W2963351448 @default.
- W4386780265 cites W2964062501 @default.
- W4386780265 cites W2990613095 @default.
- W4386780265 cites W2991216808 @default.
- W4386780265 cites W3033114334 @default.
- W4386780265 cites W3035461736 @default.
- W4386780265 cites W3130044230 @default.
- W4386780265 cites W3173732446 @default.
- W4386780265 cites W3177330511 @default.
- W4386780265 cites W4221141829 @default.
- W4386780265 cites W4221156536 @default.
- W4386780265 cites W4225986494 @default.
- W4386780265 cites W4312707458 @default.
- W4386780265 doi "https://doi.org/10.1016/j.jag.2023.103488" @default.
- W4386780265 hasPublicationYear "2023" @default.
- W4386780265 type Work @default.
- W4386780265 citedByCount "0" @default.
- W4386780265 crossrefType "journal-article" @default.
- W4386780265 hasAuthorship W4386780265A5066333395 @default.
- W4386780265 hasAuthorship W4386780265A5080730492 @default.
- W4386780265 hasBestOaLocation W43867802651 @default.
- W4386780265 hasConcept C131979681 @default.
- W4386780265 hasConcept C154945302 @default.
- W4386780265 hasConcept C2776151529 @default.
- W4386780265 hasConcept C31972630 @default.
- W4386780265 hasConcept C41008148 @default.
- W4386780265 hasConcept C81074085 @default.
- W4386780265 hasConcept C89600930 @default.
- W4386780265 hasConcept C90509273 @default.
- W4386780265 hasConceptScore W4386780265C131979681 @default.
- W4386780265 hasConceptScore W4386780265C154945302 @default.
- W4386780265 hasConceptScore W4386780265C2776151529 @default.
- W4386780265 hasConceptScore W4386780265C31972630 @default.
- W4386780265 hasConceptScore W4386780265C41008148 @default.
- W4386780265 hasConceptScore W4386780265C81074085 @default.
- W4386780265 hasConceptScore W4386780265C89600930 @default.
- W4386780265 hasConceptScore W4386780265C90509273 @default.
- W4386780265 hasLocation W43867802651 @default.
- W4386780265 hasOpenAccess W4386780265 @default.
- W4386780265 hasPrimaryLocation W43867802651 @default.
- W4386780265 hasRelatedWork W1669643531 @default.
- W4386780265 hasRelatedWork W2005437358 @default.
- W4386780265 hasRelatedWork W2008656436 @default.
- W4386780265 hasRelatedWork W2023558673 @default.
- W4386780265 hasRelatedWork W2134924024 @default.
- W4386780265 hasRelatedWork W2517104666 @default.
- W4386780265 hasRelatedWork W2613186388 @default.
- W4386780265 hasRelatedWork W2979718872 @default.
- W4386780265 hasRelatedWork W3158534694 @default.
- W4386780265 hasRelatedWork W2187221949 @default.
- W4386780265 hasVolume "123" @default.
- W4386780265 isParatext "false" @default.
- W4386780265 isRetracted "false" @default.
- W4386780265 workType "article" @default.