{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T08:26:48Z","timestamp":1791361608304,"version":"4.3.1"},"reference-count":23,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T00:00:00Z","timestamp":1766620800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Point cloud data, with its rich information and high-precision geometric details, holds significant value for urban road infrastructure surveying and management. To overcome the limitations of manual classification, this study employs deep learning techniques for automated point cloud feature extraction and classification, achieving high-precision object recognition in road scenes. By integrating the Princeton ModelNet40, ShapeNet, and Sydney Urban Objects datasets, we extracted 3D spatial coordinates from the Sydney Urban Objects Dataset and organized labeled point cloud files to build a comprehensive dataset reflecting real-world road scenarios. To address noise and occlusion-induced data gaps, three augmentation strategies were implemented: (1) Farthest Point Sampling (FPS): Preserves critical features while mitigating overfitting. (2) Random Z-axis rotation, translation, and scaling: Enhances model generalization. (3) Gaussian noise injection: Improves training sample realism. The PointNet++ framework was enhanced by integrating a point-filling method into the preprocessing module. Model training and prediction were conducted using its Multi-Scale Grouping (MSG) and Single-Scale Grouping (SSG) schemes. The model achieved an average training accuracy of 86.26% (peak single-instance accuracy: 98.54%; best category accuracy: 93.15%) and a test set accuracy of 97.41% (category accuracy: 84.50%). This study demonstrates successful road scene point cloud classification, providing valuable insights for point cloud data processing and related research.<\/jats:p>","DOI":"10.3390\/s26010153","type":"journal-article","created":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T23:52:27Z","timestamp":1766706747000},"page":"153","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Classification of Point Cloud Data in Road Scenes Based on PointNet++"],"prefix":"10.3390","volume":"26","author":[{"given":"Jingfeng","family":"Xue","sequence":"first","affiliation":[{"name":"Qingdao Huanghai University, Qingdao 266555, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2659-5053","authenticated-orcid":false,"given":"Bin","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Geology and Geomatics, Tianjin Chengjian University, Tianjin 300384, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunhong","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Geology and Geomatics, Tianjin Chengjian University, Tianjin 300384, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueru","family":"Li","sequence":"additional","affiliation":[{"name":"Lerner College of Business and Economics, University of Delaware, Newark, DE 19716, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3759-5028","authenticated-orcid":false,"given":"Yihao","family":"Cao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Geographical Process and Ecological Security of Changbai Mountain, Ministry of Education, School of Geographical Sciences, Northeast Normal University, Changchun 130024, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"4338","DOI":"10.1109\/TPAMI.2020.3005434","article-title":"Deep Learning for 3d Point Clouds: A Survey","volume":"43","author":"Guo","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_2","first-page":"1226","article-title":"Object Classification and Recognition from Mobile Laser Scanning Point Clouds in a Road Environment","volume":"54","author":"Jaakkola","year":"2015","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"100936","DOI":"10.1016\/j.aei.2019.100936","article-title":"Road Pothole Extraction and Safety Evaluation by Integration of Point Cloud and Images Derived from Mobile Mapping Sensors","volume":"42","author":"Wu","year":"2019","journal-title":"Adv. Eng. Inf."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1109\/TITS.2020.3023541","article-title":"Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review","volume":"23","author":"Cui","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.isprsjprs.2021.01.007","article-title":"Airborne LiDAR Point Cloud Classification with Global-Local Graph Attention Convolution Neural Network","volume":"173","author":"Wen","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"5412","DOI":"10.1109\/TGRS.2016.2564501","article-title":"A Three-Step Approach for TLS Point Cloud Classification","volume":"54","author":"Li","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhang, H., Ernst, I., Zuev, S., B\u00f6rner, A., Knoche, M., and Klette, R. (2018, January 19\u201321). Visual Odometry and 3D Point Clouds under Low-Light Conditions. Proceedings of the 2018 International Conference on Image and Vision Computing New Zealand (IVCNZ), Auckland, New Zealand.","DOI":"10.1109\/IVCNZ.2018.8634769"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"104555","DOI":"10.1016\/j.trc.2024.104555","article-title":"Geometric Information Constraint 3D Object Detection from LiDAR Point Cloud for Autonomous Vehicles under Adverse Weather","volume":"161","author":"Qi","year":"2024","journal-title":"Transp. Res. Part C Emerging Technol."},{"key":"ref_9","first-page":"263","article-title":"Conditional Random Fields for Lidar Point Cloud Classification in Complex Urban Areas","volume":"1","author":"Niemeyer","year":"2012","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.isprsjprs.2017.04.022","article-title":"Robust Point Cloud Classification Based on Multi-Level Semantic Relationships for Urban Scenes","volume":"129","author":"Zhu","year":"2017","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"8052","DOI":"10.1109\/TMM.2024.3374580","article-title":"Pointgt: A Method for Point-Cloud Classification and Segmentation Based on Local Geometric Transformation","volume":"26","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Multimedia"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"111622","DOI":"10.1016\/j.asoc.2024.111622","article-title":"Multi-Scale Learnable Key-Channel Attention Network for Point Cloud Classification and Segmentation","volume":"159","author":"Zhao","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref_13","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017, January 21\u201326). Pointnet: Deep Learning on Point Sets for 3d Classification and Segmentation. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA."},{"key":"ref_14","unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017, January 4\u20139). Pointnet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. Advances in Neural Information Processing Systems 30, Proceedings of the 31st Annual Conference on Neural Information Processing Systems (NeurIPS 2017), Long Beach, California, USA."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.isprsjprs.2017.03.012","article-title":"SigVox\u2013A 3D Feature Matching Algorithm for Automatic Street Object Recognition in Mobile Laser Scanning Point Clouds","volume":"128","author":"Wang","year":"2017","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.cag.2010.03.002","article-title":"Visibility of Noisy Point Cloud Data","volume":"34","author":"Mehra","year":"2010","journal-title":"Comput. Graphics"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2364","DOI":"10.1109\/TITS.2016.2639582","article-title":"Traffic Sign Occlusion Detection Using Mobile Laser Scanning Point Clouds","volume":"18","author":"Huang","year":"2017","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Cheng, L., Chen, S., Liu, X., Xu, H., Wu, Y., Li, M., and Chen, Y. (2018). Registration of Laser Scanning Point Clouds: A Review. Sensors, 18.","DOI":"10.3390\/s18051641"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Mekuria, R., Laserre, S., and Tulvan, C. (2017, January 10\u201313). Performance Assessment of Point Cloud Compression. Proceedings of the 2017 IEEE Visual Communications and Image Processing (VCIP), St. Petersburg, FL, USA.","DOI":"10.1109\/VCIP.2017.8305132"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1109\/TVCG.2012.310","article-title":"Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid","volume":"19","author":"Tam","year":"2012","journal-title":"IEEE Trans. Vis. Comput. Graphics"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"388","DOI":"10.9734\/jerr\/2024\/v26i61188","article-title":"Hyperparameter Tuning in Machine Learning: A Comprehensive Review","volume":"26","author":"Durodola","year":"2024","journal-title":"J. Eng. Res. Rep."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/0893-6080(88)90003-2","article-title":"Increased Rates of Convergence through Learning Rate Adaptation","volume":"1","author":"Jacobs","year":"1988","journal-title":"Neural Networks"},{"key":"ref_23","unstructured":"Kinga, D., and Adam, J.B. (2015, January 7\u20139). Others A Method for Stochastic Optimization. Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, USA."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/153\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T23:56:19Z","timestamp":1766706979000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/153"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,25]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26010153"],"URL":"https:\/\/doi.org\/10.3390\/s26010153","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,25]]}}}