{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T18:52:02Z","timestamp":1778784722051,"version":"3.51.4"},"reference-count":21,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T00:00:00Z","timestamp":1699920000000},"content-version":"vor","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003695","name":"Korea Institute of Industrial Technology","doi-asserted-by":"publisher","award":["KITECH JA-23\u20130011"],"award-info":[{"award-number":["KITECH JA-23\u20130011"]}],"id":[{"id":"10.13039\/501100003695","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>As Light Detection and Ranging (LiDAR) sensors become increasingly prevalent in the field of autonomous driving, the need for accurate semantic segmentation of three-dimensional points grows accordingly. To address this challenge, we propose a novel network model that enhances segmentation performance by utilizing normal vector information. Firstly, we present a method to improve the accuracy of normal estimation by using the intensity and reflection angles of the light emitted from the LiDAR sensor. Secondly, we introduce a novel local feature aggregation module that integrates normal vector information into the network to improve the performance of local feature extraction. The normal information is closely related to the local structure of the shape of an object, which helps the network to associate unique features with corresponding objects. We propose four different structures for local feature aggregation, evaluate them, and choose the one that shows the best performance. Experiments using the SemanticKITTI dataset demonstrate that the proposed architecture outperforms both the baseline models, RandLA-Net, and other existing methods, achieving mean intersection over union of 57.9%. Furthermore, it shows highly competitive performance compared with RandLA-Net for small and dynamic objects in a real road environment. For example, it yielded 95.2% for cars, 47.4% for bicycles, 41.0% for motorcycles, 57.4% for bicycles, and 53.2% for pedestrians.<\/jats:p>","DOI":"10.1093\/jcde\/qwad102","type":"journal-article","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T07:40:01Z","timestamp":1699947601000},"page":"2332-2344","source":"Crossref","is-referenced-by-count":7,"title":["Improved semantic segmentation network using normal vector guidance for LiDAR point clouds"],"prefix":"10.1093","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9515-7544","authenticated-orcid":false,"given":"Minsung","family":"Kim","sequence":"first","affiliation":[{"name":"The School of Mechanical Engineering, Gwangju Institute of Science and Technology , 123 Cheomdangwagiro, Gwangju 61005 , Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Inyoung","family":"Oh","sequence":"additional","affiliation":[{"name":"The School of Mechanical Engineering, Gwangju Institute of Science and Technology , 123 Cheomdangwagiro, Gwangju 61005 , Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongho","family":"Yun","sequence":"additional","affiliation":[{"name":"Automotive Mobility Materials and Components R&D Group, Korea Institute of Industrial Technology , Gwangju 61012 , Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7668-5796","authenticated-orcid":false,"given":"Kwanghee","family":"Ko","sequence":"additional","affiliation":[{"name":"The School of Mechanical Engineering, Gwangju Institute of Science and Technology , 123 Cheomdangwagiro, Gwangju 61005 , Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,11,13]]},"reference":[{"key":"2024011907224989700_bib22_1700577860534","first-page":"9297","article-title":"SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Behley","year":"(2019)"},{"key":"2024011907224989700_bib1","first-page":"424","article-title":"3D U-Net: Learning dense volumetric segmentation from sparse annotation","volume-title":"Proceedings of the 19th International Conference on Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2016 Part II","author":"\u00c7i\u00e7ek","year":"2016"},{"issue":"5","key":"2024011907224989700_bib2","doi-asserted-by":"crossref","first-page":"1995","DOI":"10.1093\/jcde\/qwac088","article-title":"Mode confusion of human\u2013machine interfaces for automated vehicles","volume":"9","author":"Eom","year":"2022","journal-title":"Journal of Computational Design and Engineering"},{"key":"2024011907224989700_bib20_1700575012079","first-page":"98","article-title":"The PASCAL Visual Object Classes Challenge: A Retrospective","volume-title":"International Journal of Computer Vision","author":"Everingham","year":"(2015)"},{"key":"2024011907224989700_bib3","first-page":"14504","article-title":"SCF-Net: Learning spatial contextual features for large-scale point cloud segmentation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Fan","year":"2021"},{"issue":"3","key":"2024011907224989700_bib4","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1093\/jcde\/qwad027","article-title":"Enhancing three-dimensional convolutional neural network-based geometric feature recognition for adaptive additive manufacturing: A signed distance field data approach","volume":"10","author":"Hilbig","year":"2023","journal-title":"Journal of Computational Design and Engineering"},{"key":"2024011907224989700_bib5","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1145\/133994.134011","article-title":"Surface reconstruction from unorganized points","volume-title":"Proceedings of the 19th Annual Conference on Computer Graphics and Interactive Techniques","author":"Hoppe","year":"1992"},{"key":"2024011907224989700_bib6","first-page":"11108","article-title":"RandLA-Net: Efficient semantic segmentation of large-scale point clouds","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2020"},{"key":"2024011907224989700_bib21_1700576986400","volume-title":"Robust statistics","author":"Huber","year":"(2004)"},{"key":"2024011907224989700_bib7","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1016\/j.patrec.2021.10.023","article-title":"kNN-based feature learning network for semantic segmentation of point cloud data","volume":"152","author":"Luo","year":"2021","journal-title":"Pattern Recognition Letters"},{"key":"2024011907224989700_bib8","first-page":"4213","article-title":"RangeNet++: Fast and accurate LiDAR semantic segmentation","volume-title":"Proceedings of the 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Milioto","year":"2019"},{"issue":"5","key":"2024011907224989700_bib9","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.1093\/jcde\/qwac079","article-title":"Reliable, robust, and comprehensive risk assessment framework for urban autonomous driving","volume":"9","author":"Noh","year":"2022","journal-title":"Journal of Computational Design and Engineering"},{"key":"2024011907224989700_bib18_1700573707705","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1109\/UR49135.2020.9144987","article-title":"I-LOAM: Intensity Enhanced LiDAR Odometry and Mapping","volume-title":"17th International Conference on Ubiquitous Robots (UR)","author":"Park","year":"(2020)"},{"key":"2024011907224989700_bib10","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Qi","year":"2017"},{"key":"2024011907224989700_bib11","first-page":"5099","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Advances in neural information processing systems","author":"Qi","year":"2017"},{"key":"2024011907224989700_bib12","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"2024011907224989700_bib13","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.1109\/ICRA.2018.8462926","article-title":"SqueezeSeg: Convolutional neural nets with recurrent CRF for real-time road-object segmentation from 3D LiDAR point cloud","volume-title":"2018 IEEE International Conference on Robotics and Automation (ICRA)","author":"Wu","year":"2018"},{"key":"2024011907224989700_bib14","doi-asserted-by":"crossref","first-page":"4376","DOI":"10.1109\/ICRA.2019.8793495","article-title":"SqueezeSegV2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a LiDAR point cloud","volume-title":"Proceedings of the 2019 International Conference on Robotics and Automation (ICRA)","author":"Wu","year":"2019"},{"key":"2024011907224989700_bib15","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1007\/978-3-030-58586-0_38","article-title":"Deep FusionNet for point cloud semantic segmentation","volume-title":"Proceedings of the 16th European Conference on Computer Vision\u2013ECCV 2020, Part XXIV","author":"Zhang","year":"2020"},{"key":"2024011907224989700_bib16","first-page":"9601","article-title":"PolarNet: An improved grid representation for online LiDAR point clouds semantic segmentation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhang","year":"2020"},{"key":"2024011907224989700_bib17","first-page":"4490","article-title":"VoxelNet: End-to-end learning for point cloud based 3D object detection","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhou","year":"2018"}],"container-title":["Journal of Computational Design and Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcde\/advance-article-pdf\/doi\/10.1093\/jcde\/qwad102\/53381445\/qwad102.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/10\/6\/2332\/56245568\/qwad102.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcde\/article-pdf\/10\/6\/2332\/56245568\/qwad102.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T07:23:09Z","timestamp":1705648989000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcde\/article\/10\/6\/2332\/7419878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,3]]},"references-count":21,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,11,3]]}},"URL":"https:\/\/doi.org\/10.1093\/jcde\/qwad102","relation":{},"ISSN":["2288-5048"],"issn-type":[{"value":"2288-5048","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,12]]},"published":{"date-parts":[[2023,11,3]]}}}