DC Field | Value | Language |
---|---|---|
dc.contributor.author | He, Dong | ko |
dc.contributor.author | Abid, Furqan | ko |
dc.contributor.author | Kim, Jong-Hwan | ko |
dc.date.accessioned | 2023-02-10T01:00:16Z | - |
dc.date.available | 2023-02-10T01:00:16Z | - |
dc.date.created | 2023-02-09 | - |
dc.date.created | 2023-02-09 | - |
dc.date.issued | 2022-11 | - |
dc.identifier.citation | 22nd International Conference on Control, Automation and Systems, ICCAS 2022, pp.1143 - 1148 | - |
dc.identifier.issn | 1598-7833 | - |
dc.identifier.uri | http://hdl.handle.net/10203/305120 | - |
dc.description.abstract | Since modern autonomous driving (AD) platforms offer a variety of sensors, it is intuitive to leverage complementary data from multimodal sensors to produce reliable 3D semantic segmentation. However, due to the information loss and the sub-optimized fusion in multimodal fusion methods, LiDAR-only methods currently occupy the top positions in the leaderboard of datasets. In this paper, we focus on two aspects to improve the LiDAR-camera fusion semantic segmentation performance, namely data augmentation and fusion strategy. First, we propose an novel data augmentation by refining point-image patches. Second, we design an attention fusion block for the dual-branch segmentation network by considering the modality gap between LiDAR and RGB camera. Experiments on nuScences indicate that our proposed method outperforms the baseline methods on key classes. | - |
dc.language | English | - |
dc.publisher | IEEE Computer Society | - |
dc.title | Multimodal Fusion and Data Augmentation for 3D Semantic Segmentation | - |
dc.type | Conference | - |
dc.identifier.wosid | 000927498500181 | - |
dc.identifier.scopusid | 2-s2.0-85146556163 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 1143 | - |
dc.citation.endingpage | 1148 | - |
dc.citation.publicationname | 22nd International Conference on Control, Automation and Systems, ICCAS 2022 | - |
dc.identifier.conferencecountry | KO | - |
dc.identifier.conferencelocation | BEXCO, Busan | - |
dc.identifier.doi | 10.23919/ICCAS55662.2022.10003729 | - |
dc.contributor.localauthor | Kim, Jong-Hwan | - |
dc.contributor.nonIdAuthor | He, Dong | - |
dc.contributor.nonIdAuthor | Abid, Furqan | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.