{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T04:39:26Z","timestamp":1780979966749,"version":"3.54.1"},"reference-count":28,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T00:00:00Z","timestamp":1742169600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>3D LiDAR point clouds, obtained through scanning by LiDAR devices, contain rich information such as 3D coordinates (X, Y, Z), color, classification values, intensity values, and time. However, the original collected 3D LiDAR point clouds often exhibit significant disparities in instance counts, which can hinder the effectiveness of point cloud segmentation. PolarMix, a data augmentation algorithm for 3D LiDAR point cloud datasets, addresses this issue by rotating and pasting selected class instances around the Z axis multiple times to enrich the distribution of the point cloud. However, PolarMix does not adequately consider the substantial variations in instance counts within the original point clouds, leading to an imbalance in the dataset. To address this limitation, we propose a modified version of PolarMix\u2019s instance-level rotation and pasting method that dynamically adjusts the number of rotations and pastes based on the proportion of each instance\u2019s point cloud count relative to the total. This adaptive class-balancing approach ensures a more balanced distribution of instances across the entire dataset. We term our new algorithm Dynamic Adaptive Class-Balanced PolarMix (DACB-PolarMix). Experimental results demonstrate the effectiveness of DACB-PolarMix in balancing class distribution and enhancing model performance. The results on the SemanticKitti dataset are particularly significant. Under the MinkNet model, our method improved the mIoU from 65% to 67.9%, and under the SPVCNN model, our method increased the mIoU from 66.2% to 67.5%.<\/jats:p>","DOI":"10.1371\/journal.pone.0318888","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T17:42:37Z","timestamp":1742233357000},"page":"e0318888","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["A dynamic and adaptive class-balanced data augmentation approach for 3D LiDAR point clouds"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3948-2839","authenticated-orcid":true,"given":"Bo","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6613-7347","authenticated-orcid":true,"given":"Xiao","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,3,17]]},"reference":[{"key":"pone.0318888.ref001"},{"key":"pone.0318888.ref002"},{"key":"pone.0318888.ref003"},{"key":"pone.0318888.ref004"},{"key":"pone.0318888.ref005"},{"key":"pone.0318888.ref006"},{"key":"pone.0318888.ref007"},{"issue":"19","key":"pone.0318888.ref008","doi-asserted-by":"crossref","first-page":"4685","DOI":"10.3390\/rs14194685","article-title":"Review of automatic processing of topography and surface feature identification LiDAR data using machine learning techniques","volume":"14","author":"Z Gharineiat","year":"2022","journal-title":"Remote Sens"},{"key":"pone.0318888.ref009"},{"key":"pone.0318888.ref010"},{"key":"pone.0318888.ref011"},{"key":"pone.0318888.ref012"},{"issue":"17","key":"pone.0318888.ref013","doi-asserted-by":"crossref","first-page":"7360","DOI":"10.3390\/s23177360","article-title":"Contribution of geometric feature analysis for deep learning classification algorithms of urban LiDAR data","volume":"23","author":"F Tarsha Kurdi","year":"2023","journal-title":"Sensors (Basel)"},{"key":"pone.0318888.ref014","article-title":"Quantifying data augmentation for LiDAR based 3d object detection","author":"M Hahner","year":"2020","journal-title":"arXiv preprint"},{"key":"pone.0318888.ref015"},{"key":"pone.0318888.ref016"},{"key":"pone.0318888.ref017"},{"key":"pone.0318888.ref018"},{"key":"pone.0318888.ref019"},{"key":"pone.0318888.ref020"},{"key":"pone.0318888.ref021"},{"key":"pone.0318888.ref022"},{"key":"pone.0318888.ref023"},{"key":"pone.0318888.ref024"},{"key":"pone.0318888.ref025"},{"key":"pone.0318888.ref026"},{"key":"pone.0318888.ref027"},{"issue":"2","key":"pone.0318888.ref028","doi-asserted-by":"crossref","first-page":"04022056","DOI":"10.1061\/JCCEE5.CPENG-5009","article-title":"Point cloud\u2013based concrete surface defect semantic segmentation","volume":"37","author":"N Bolourian","year":"2023","journal-title":"J Comput Civ Eng"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0318888","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T17:42:44Z","timestamp":1742233364000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0318888"}},"subtitle":[],"editor":[{"given":"Yawen","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,3,17]]},"references-count":28,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3,17]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0318888","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,17]]}}}