SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloud
4D LiDAR semantic segmentation classifies the semantic category of each LiDAR point and detects whether it is dynamic, a critical ability for tasks like obstacle avoidance and autonomous navigation. Existing approaches often rely on computationally heavy 4D convolutions or recursive networks, which...
Uloženo v:
| Vydáno v: | IEEE transactions on automation science and engineering Ročník 22; s. 15339 - 15350 |
|---|---|
| Hlavní autoři: | , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
2025
|
| Témata: | |
| ISSN: | 1545-5955, 1558-3783 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | 4D LiDAR semantic segmentation classifies the semantic category of each LiDAR point and detects whether it is dynamic, a critical ability for tasks like obstacle avoidance and autonomous navigation. Existing approaches often rely on computationally heavy 4D convolutions or recursive networks, which result in poor real-time performance. In this paper, we introduce SegNet4D, a novel real-time 4D semantic segmentation network, offering both efficiency and strong semantic understanding. SegNet4D addresses 4D segmentation as two tasks: single-scan semantic segmentation and moving object segmentation, each tackled by a separate network head. Both results are combined in a motion-semantic fusion module to achieve comprehensive 4D segmentation. Additionally, instance information is extracted from the current scan and exploited for instance-wise segmentation consistency. Extensive experiments on the SemanticKITTI and nuScenes datasets demonstrate that our method outperforms the state-of-the-art in both 4D semantic segmentation and moving object segmentation. Through detailed runtime analysis, our method shows greater efficiency, enabling real-time operation. Besides, its effectiveness and efficiency have also been validated on a real-world robotic platform. The implementation of our method has been released at https://github.com/nubot-nudt/SegNet4D Note to Practitioners-This paper focuses on enhancing the efficiency of 4D semantic segmentation for applications in autonomous driving or navigation. Existing LiDAR-based 4D semantic segmentation methods fall short of real-time processing capabilities, thereby severely limiting their practicality for autonomous vehicles and robotic systems. To tackle these issues, we design a high-efficiency 4D semantic segmentation network that not only performs real-time operations on real-world robotic systems but also delivers superior performance, validating its practical utility. Future work can further leverage the instance information we introduced to improve the network's functionality by achieving panoptic segmentation or 4D panoptic segmentation. Furthermore, some studies may use the 4D semantic labels predicted by our approach to reinforce tasks associated with robotic autonomy. |
|---|---|
| AbstractList | 4D LiDAR semantic segmentation classifies the semantic category of each LiDAR point and detects whether it is dynamic, a critical ability for tasks like obstacle avoidance and autonomous navigation. Existing approaches often rely on computationally heavy 4D convolutions or recursive networks, which result in poor real-time performance. In this paper, we introduce SegNet4D, a novel real-time 4D semantic segmentation network, offering both efficiency and strong semantic understanding. SegNet4D addresses 4D segmentation as two tasks: single-scan semantic segmentation and moving object segmentation, each tackled by a separate network head. Both results are combined in a motion-semantic fusion module to achieve comprehensive 4D segmentation. Additionally, instance information is extracted from the current scan and exploited for instance-wise segmentation consistency. Extensive experiments on the SemanticKITTI and nuScenes datasets demonstrate that our method outperforms the state-of-the-art in both 4D semantic segmentation and moving object segmentation. Through detailed runtime analysis, our method shows greater efficiency, enabling real-time operation. Besides, its effectiveness and efficiency have also been validated on a real-world robotic platform. The implementation of our method has been released at https://github.com/nubot-nudt/SegNet4D Note to Practitioners-This paper focuses on enhancing the efficiency of 4D semantic segmentation for applications in autonomous driving or navigation. Existing LiDAR-based 4D semantic segmentation methods fall short of real-time processing capabilities, thereby severely limiting their practicality for autonomous vehicles and robotic systems. To tackle these issues, we design a high-efficiency 4D semantic segmentation network that not only performs real-time operations on real-world robotic systems but also delivers superior performance, validating its practical utility. Future work can further leverage the instance information we introduced to improve the network's functionality by achieving panoptic segmentation or 4D panoptic segmentation. Furthermore, some studies may use the 4D semantic labels predicted by our approach to reinforce tasks associated with robotic autonomy. |
| Author | Zhang, Hui Guo, Ruibin Chen, Xieyuanli Wang, Ziyue Wang, Neng Zheng, Zhiqiang Shi, Chenghao Lu, Huimin |
| Author_xml | – sequence: 1 givenname: Neng orcidid: 0009-0005-3620-347X surname: Wang fullname: Wang, Neng organization: College of Intelligence Science and Technology and the National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, Changsha, China – sequence: 2 givenname: Ruibin orcidid: 0000-0001-9935-6792 surname: Guo fullname: Guo, Ruibin organization: College of Intelligence Science and Technology and the National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, Changsha, China – sequence: 3 givenname: Chenghao orcidid: 0000-0002-1462-2367 surname: Shi fullname: Shi, Chenghao organization: College of Intelligence Science and Technology and the National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, Changsha, China – sequence: 4 givenname: Ziyue surname: Wang fullname: Wang, Ziyue organization: College of Intelligence Science and Technology and the National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, Changsha, China – sequence: 5 givenname: Hui surname: Zhang fullname: Zhang, Hui organization: College of Intelligence Science and Technology and the National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, Changsha, China – sequence: 6 givenname: Huimin orcidid: 0000-0002-6375-581X surname: Lu fullname: Lu, Huimin organization: College of Intelligence Science and Technology and the National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, Changsha, China – sequence: 7 givenname: Zhiqiang surname: Zheng fullname: Zheng, Zhiqiang organization: College of Intelligence Science and Technology and the National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, Changsha, China – sequence: 8 givenname: Xieyuanli orcidid: 0000-0003-0955-6681 surname: Chen fullname: Chen, Xieyuanli email: xieyuanli.chen@nudt.edu.cn organization: College of Intelligence Science and Technology and the National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, Changsha, China |
| BookMark | eNp9kMtOwzAQRS1UJNrCByCx8A-k2LEd2-yiPqBSxatlHdmOXRmlDnKMEH9PonaBWLCau5hzR3MmYBTaYAG4xmiGMZK3u3K7nOUoZzPCCoEQPgNjzJjICBdkNGTKMiYZuwCTrntHKKdCojF42dr9o010cQeXznnjbUhwHbqkgrFZ-aWihXQBt_agQvKmD_tDv6KSbwN0bYQbvyhf4XPre27etJ_1JTh3quns1WlOwdtquZs_ZJun-_W83GQmL0TKNFVOGMR1bTThSOVGUE0ZJjUiknGZO-pqJ42jkhRCKlFrQpXiUtccCanJFOBjr4lt10Xrqo_oDyp-VxhVg5NqcFINTqqTk57hfxjjj7-kqHzzL3lzJL219tclKQnlkvwAkg1wXw |
| CODEN | ITASC7 |
| CitedBy_id | crossref_primary_10_3390_app15158162 |
| Cites_doi | 10.1109/CASE59546.2024.10711541 10.1109/IVS.2017.7995698 10.1109/TIM.2023.3292948 10.1109/LRA.2023.3325687 10.1109/TASE.2024.3394519 10.1109/ICRA.2011.5980567 10.1109/WACV56688.2023.00169 10.1007/s11263-024-02149-w 10.1109/ICRA57147.2024.10610262 10.1109/ICRA46639.2022.9811818 10.1109/TITS.2023.3286464 10.1109/LRA.2022.3166544 10.1109/TPAMI.2021.3098789 10.1109/LRA.2022.3186080 10.1109/IROS47612.2022.9981210 10.1109/TPAMI.2023.3349304 10.1109/ICCV.2019.00737 10.48550/ARXIV.1807.06521 10.1109/TASE.2024.3429280 10.1109/CVPR52729.2023.01683 10.1109/IROS55552.2023.10342277 10.1109/LRA.2022.3183245 10.1109/TRO.2022.3141876 10.1109/LRA.2021.3132059 10.1109/CVPR.2019.00319 10.1109/ICCV.2019.00939 10.1007/s11263-009-0275-4 10.1109/LRA.2024.3371873 10.1037/h0070888 10.1109/LRA.2021.3093567 10.1109/TPAMI.2020.3042093 10.1109/CVPR46437.2021.00548 10.1109/ICCV.2019.00651 10.1109/LRA.2023.3236568 10.1109/CVPR46437.2021.01161 |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION |
| DOI | 10.1109/TASE.2025.3568001 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-3783 |
| EndPage | 15350 |
| ExternalDocumentID | 10_1109_TASE_2025_3568001 10993479 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Young Elite Scientists Sponsorship Program by China Association for Science and Technology (CAST) grantid: 2023QNRC001 funderid: 10.13039/501100019005 – fundername: National Science Foundation of China grantid: 62403478; U22A2059; 62203460 funderid: 10.13039/501100001809 |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IFIPE IPLJI JAVBF LAI M43 O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION |
| ID | FETCH-LOGICAL-c268t-b4af8c07bdcb370a2c84b4513d0395792f4fdf9cf493689a8db34aa79bd7089b3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 3 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001494111500013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1545-5955 |
| IngestDate | Sat Nov 29 07:54:51 EST 2025 Tue Nov 18 22:27:43 EST 2025 Wed Aug 27 01:37:50 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c268t-b4af8c07bdcb370a2c84b4513d0395792f4fdf9cf493689a8db34aa79bd7089b3 |
| ORCID | 0000-0003-0955-6681 0000-0001-9935-6792 0000-0002-1462-2367 0009-0005-3620-347X 0000-0002-6375-581X |
| PageCount | 12 |
| ParticipantIDs | crossref_primary_10_1109_TASE_2025_3568001 ieee_primary_10993479 crossref_citationtrail_10_1109_TASE_2025_3568001 |
| PublicationCentury | 2000 |
| PublicationDate | 20250000 2025-00-00 |
| PublicationDateYYYYMMDD | 2025-01-01 |
| PublicationDate_xml | – year: 2025 text: 20250000 |
| PublicationDecade | 2020 |
| PublicationTitle | IEEE transactions on automation science and engineering |
| PublicationTitleAbbrev | TASE |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref15 ref14 Shi (ref29) 2024; 132 ref17 Caesar (ref45) ref16 ref18 Li (ref28) ref51 ref50 Duerr (ref12) Chen (ref7) Mohapatra (ref24) 2021 ref42 ref41 ref43 Geiger (ref46) ref8 ref9 ref4 ref3 Fradlin (ref33) ref6 ref5 Patil (ref19) ref40 ref35 Shi (ref11) Chen (ref30) ref37 ref36 ref31 ref32 Everingham (ref49) 2010; 88 ref2 ref1 Li (ref10) 2022; 7 Chen (ref21) 2021; 6 ref38 ref26 ref25 Liu (ref13) ref20 ref22 Graham (ref34) Kingma (ref48) ref27 Liebel (ref44) 2018 Cheng (ref23) Paszke (ref47) Hotelling (ref39) 1933; 24 |
| References_xml | – year: 2021 ident: ref24 article-title: LiMoSeg: Real-time bird’s eye view based LiDAR motion segmentation publication-title: arXiv:2111.04875 – ident: ref3 doi: 10.1109/CASE59546.2024.10711541 – ident: ref40 doi: 10.1109/IVS.2017.7995698 – ident: ref8 doi: 10.1109/TIM.2023.3292948 – ident: ref25 doi: 10.1109/LRA.2023.3325687 – ident: ref5 doi: 10.1109/TASE.2024.3394519 – start-page: 781 volume-title: Proc. Int. Conf. 3D Vis. (3DV) ident: ref12 article-title: LiDAR-based recurrent 3D semantic segmentation with temporal memory alignment – start-page: 745 volume-title: Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV) ident: ref28 article-title: MemorySeg: Online LiDAR semantic segmentation with a latent memory – ident: ref38 doi: 10.1109/ICRA.2011.5980567 – ident: ref27 doi: 10.1109/WACV56688.2023.00169 – start-page: 12499 volume-title: Proc. IEEE Int. Conf. Robot. Autom. (ICRA) ident: ref23 article-title: MF-MOS: A motion-focused model for moving object segmentation – start-page: 1 volume-title: Proc. IEEE Int. Conf. Robot. Autom. (ICRA) ident: ref33 article-title: Interactive4D: Interactive 4D LiDAR segmentation – volume: 132 start-page: 5603 issue: 12 year: 2024 ident: ref29 article-title: Learning temporal variations for 4D point cloud segmentation publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-024-02149-w – start-page: 3354 volume-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. ident: ref46 article-title: Are we ready for autonomous driving? The KITTI vision benchmark suite – start-page: 11618 volume-title: Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) ident: ref45 article-title: NuScenes: A multimodal dataset for autonomous driving – ident: ref31 doi: 10.1109/ICRA57147.2024.10610262 – ident: ref16 doi: 10.1109/ICRA46639.2022.9811818 – ident: ref4 doi: 10.1109/TITS.2023.3286464 – start-page: 9372 volume-title: Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) ident: ref13 article-title: MarS3D: A plug-and-play motion-aware model for semantic segmentation on multi-scan 3D point clouds – ident: ref18 doi: 10.1109/LRA.2022.3166544 – ident: ref1 doi: 10.1109/TPAMI.2021.3098789 – ident: ref2 doi: 10.1109/LRA.2022.3186080 – ident: ref22 doi: 10.1109/IROS47612.2022.9981210 – ident: ref32 doi: 10.1109/TPAMI.2023.3349304 – ident: ref42 doi: 10.1109/ICCV.2019.00737 – ident: ref43 doi: 10.48550/ARXIV.1807.06521 – start-page: 4573 volume-title: Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) ident: ref11 article-title: SpSequenceNet: Semantic segmentation network on 4D point clouds – ident: ref6 doi: 10.1109/TASE.2024.3429280 – start-page: 9224 volume-title: Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. ident: ref34 article-title: 3D semantic segmentation with submanifold sparse convolutional networks – ident: ref35 doi: 10.1109/CVPR52729.2023.01683 – ident: ref17 doi: 10.1109/IROS55552.2023.10342277 – ident: ref26 doi: 10.1109/LRA.2022.3183245 – ident: ref50 doi: 10.1109/TRO.2022.3141876 – volume: 7 start-page: 738 issue: 2 year: 2022 ident: ref10 article-title: Multi-scale interaction for real-time LiDAR data segmentation on an embedded platform publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/LRA.2021.3132059 – ident: ref15 doi: 10.1109/CVPR.2019.00319 – start-page: 4530 volume-title: Proc. IEEE/RSJ Intl. Conf. Intell. Robots Syst. (IROS) ident: ref7 article-title: SuMa++: Efficient LiDAR-based semantic SLAM – ident: ref14 doi: 10.1109/ICCV.2019.00939 – volume: 88 start-page: 303 issue: 2 year: 2010 ident: ref49 article-title: The Pascal visual object classes (VOC) challenge publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-009-0275-4 – year: 2018 ident: ref44 article-title: Auxiliary tasks in multi-task learning publication-title: arXiv:1805.06334 – volume-title: arXiv:1412.6980 ident: ref48 article-title: Adam: A method for stochastic optimization – start-page: 8146 volume-title: Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) ident: ref19 article-title: An end-to-end edge aggregation network for moving object segmentation – ident: ref51 doi: 10.1109/LRA.2024.3371873 – volume: 24 start-page: 498 issue: 7 year: 1933 ident: ref39 article-title: Analysis of a complex of statistical variables into principal components publication-title: J. Educ. Psychol. doi: 10.1037/h0070888 – volume: 6 start-page: 6529 issue: 4 year: 2021 ident: ref21 article-title: Moving object segmentation in 3D LiDAR data: A learning-based approach exploiting sequential data publication-title: IEEE Robot. Autom. Lett. doi: 10.1109/LRA.2021.3093567 – ident: ref20 doi: 10.1109/TPAMI.2020.3042093 – start-page: 8535 volume-title: Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV) ident: ref30 article-title: SVQNet: Sparse voxel-adjacent query network for 4D spatio-temporal LiDAR semantic segmentation – ident: ref36 doi: 10.1109/CVPR46437.2021.00548 – ident: ref9 doi: 10.1109/ICCV.2019.00651 – ident: ref37 doi: 10.1109/LRA.2023.3236568 – start-page: 8026 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref47 article-title: Pytorch: An imperative style, high-performance deep learning library – ident: ref41 doi: 10.1109/CVPR46437.2021.01161 |
| SSID | ssj0024890 |
| Score | 2.4192836 |
| Snippet | 4D LiDAR semantic segmentation classifies the semantic category of each LiDAR point and detects whether it is dynamic, a critical ability for tasks like... |
| SourceID | crossref ieee |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 15339 |
| SubjectTerms | 4D semantic segmentation deep learning Feature extraction Laser radar LiDAR point cloud Motion segmentation moving object segmentation Object segmentation Point cloud compression Real-time systems Robots Semantic segmentation Semantics Three-dimensional displays |
| Title | SegNet4D: Efficient Instance-Aware 4D Semantic Segmentation for LiDAR Point Cloud |
| URI | https://ieeexplore.ieee.org/document/10993479 |
| Volume | 22 |
| WOSCitedRecordID | wos001494111500013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-3783 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0024890 issn: 1545-5955 databaseCode: RIE dateStart: 20040101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFA5u-KAPXifOG3nwScjWtUmT-FZ2QUHGdBP2VppLR2FbZXb6903SqvNBwbdQckr5Wjhfzun3HQCuuSEZAaYYaUIIwlxqxHxMkEcSloZUdYSSbtgEHQ7ZdMpHlVjdaWG01u7nM92yS9fLV7lc21JZ23ZxrPKxBmqUhqVY69tYj7mCiqUEiHBCqhamiWlPonHfHAV90gpIaBhS50cS2piq4pLKYP-fj3MA9ir2CKPydR-CLb08ArsbnoLH4HGsZ0Nd4N4t7Dt7CHMPeO9IoEEoek9WGuIeHOuFwTSTZjFbVPqjJTQMFj5kvegJjvLMxHXn-Vo1wPOgP-neoWpuApJ-yAokcJIy6VEDswiol_iSYYFJJ1Ce68r5KU5VymWKeRAynjAlApwklAtFPcZFcALqy3ypTwH0tEiJTzlhVGNDBoQ0yQ1TKXwmdaj8JvA-gYxlZSpuZ1vMY3e48HhssY8t9nGFfRPcfIW8lI4af21uWNw3NpaQn_1y_Rzs2PCyRnIB6sVqrS_BtnwrstfVlftgPgBHarth |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aBfXgs-LbHDwJq2k22STelrZisRa1Fbwtm8fKgt1KbfXvm2RXrQcFb2HJhPBlYb7MZL4B4ERYkhESRgJDKQ2IUCbgmNAA0ZRnEdMNqZVvNsF6Pf74KG6rYnVfC2OM8Y_PzJkb-ly-HqmpC5WduyyOq3ycBwuUEIzKcq1vaT3uQyqOFARUUFolMa3V-SDut-1lENOzkEaWIzV-uKGZvirerVyu_XND62C14o8wLg98A8yZYhOszKgKboG7vnnqmQlpXcC2F4iwa8COp4EWo_g9HRtIWrBvhhbVXNnB07CqQCqg5bCwm7fie3g7yq1d83k01XXwcNkeNK-CqnNCoHDEJ4EkacYVYhZoGTKUYsWJJLQRauTzcjgjmc6EyogIIy5SrmVI0pQJqRniQobboFaMCrMDIDIyo5gJypkhlg5IZd0bYUpirkyk8S5An0AmqpIVd90tnhN_vUAicdgnDvukwn4XnH6ZvJSaGn9NrjvcZyaWkO_98v0YLF0NbrpJt9O73gfLbqkyYnIAapPx1ByCRfU2yV_HR_7n-QA2Hb6o |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=SegNet4D%3A+Efficient+Instance-Aware+4D+Semantic+Segmentation+for+LiDAR+Point+Cloud&rft.jtitle=IEEE+transactions+on+automation+science+and+engineering&rft.au=Wang%2C+Neng&rft.au=Guo%2C+Ruibin&rft.au=Shi%2C+Chenghao&rft.au=Wang%2C+Ziyue&rft.date=2025&rft.issn=1545-5955&rft.eissn=1558-3783&rft.volume=22&rft.spage=15339&rft.epage=15350&rft_id=info:doi/10.1109%2FTASE.2025.3568001&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TASE_2025_3568001 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1545-5955&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1545-5955&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1545-5955&client=summon |