{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T00:14:03Z","timestamp":1776557643819,"version":"3.51.2"},"reference-count":38,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,2,10]],"date-time":"2023-02-10T00:00:00Z","timestamp":1675987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council (NSERC) of Canada","doi-asserted-by":"publisher","award":["RGPIN-2018-04046"],"award-info":[{"award-number":["RGPIN-2018-04046"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Currently, 3D point clouds are being used widely due to their reliability in presenting 3D objects and accurately localizing them. However, raw point clouds are unstructured and do not contain semantic information about the objects. Recently, dedicated deep neural networks have been proposed for the semantic segmentation of 3D point clouds. The focus has been put on the architecture of the network, while the performance of some networks, such as Kernel Point Convolution (KPConv), shows that the way data are presented at the input of the network is also important. Few prior works have studied the impact of using data preparation on the performance of deep neural networks. Therefore, our goal was to address this issue. We propose two novel data preparation methods that are compatible with typical density variations in outdoor 3D LiDAR point clouds. We also investigated two already existing data preparation methods to show their impact on deep neural networks. We compared the four methods with a baseline method based on point cloud partitioning in PointNet++. We experimented with two deep neural networks: PointNet++ and KPConv. The results showed that using any of the proposed data preparation methods improved the performance of both networks by a tangible margin compared to the baseline. The two proposed novel data preparation methods achieved the best results among the investigated methods for both networks. We noticed that, for datasets containing many classes with widely varying sizes, the KNN-based data preparation offered superior performance compared to the Fixed Radius (FR) method. Moreover, this research allowed identifying guidelines to select meaningful downsampling and partitioning of large-scale outdoor 3D LiDAR point clouds at the input of deep neural networks.<\/jats:p>","DOI":"10.3390\/rs15040982","type":"journal-article","created":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T06:09:21Z","timestamp":1676268561000},"page":"982","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Data Preparation Impact on Semantic Segmentation of 3D Mobile LiDAR Point Clouds Using Deep Neural Networks"],"prefix":"10.3390","volume":"15","author":[{"given":"Reza","family":"Mahmoudi Kouhi","sequence":"first","affiliation":[{"name":"Department of Geomatics Sciences, Universit\u00e9 Laval, Qu\u00e9bec City, QC G1V 0A6, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2383-9442","authenticated-orcid":false,"given":"Sylvie","family":"Daniel","sequence":"additional","affiliation":[{"name":"Department of Geomatics Sciences, Universit\u00e9 Laval, Qu\u00e9bec City, QC G1V 0A6, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7520-8290","authenticated-orcid":false,"given":"Philippe","family":"Gigu\u00e8re","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, Universit\u00e9 Laval, Qu\u00e9bec City, QC G1V 0A6, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.3390\/ijgi2041038","article-title":"Georeferenced Point Clouds: A Survey of Features and Point Cloud Management","volume":"2","author":"Otepka","year":"2013","journal-title":"ISPRS Int. J. -Geo-Inf."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zhou, Y., and Tuzel, O. (2018, January 18\u201322). VoxelNet: End-to-end learning for point cloud based 3d object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.isprsjprs.2018.03.018","article-title":"A multi-scale fully convolutional network for semantic labeling of 3D point clouds","volume":"143","author":"Yousefhussien","year":"2018","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yu, T., Meng, J., and Yuan, J. (2018, January 18\u201322). Multi-view Harmonized Bilinear Network for 3D Object Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00027"},{"key":"ref_5","unstructured":"Yang, Z., and Wang, L. (November, January 27). Learning Relationships for Multi-View 3D Object Recognition. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Korea."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.cag.2017.11.010","article-title":"SnapNet: 3D point cloud semantic labeling with 2D deep segmentation networks","volume":"71","author":"Boulch","year":"2018","journal-title":"Comput. Graph."},{"key":"ref_7","unstructured":"Hackel, T., Savinov, N., Ladicky, L., Wegner, J.D., Schindler, K., and Pollefeys, M. (2017). ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Copernicus GmbH."},{"key":"ref_8","unstructured":"Huang, J., and You, S. (2016, January 4\u20138). Point cloud labeling using 3d convolutional neural network. Proceedings of the IEEE International Conference on Pattern Recognition (ICPR), Cancun, Mexico."},{"key":"ref_9","unstructured":"Riegler, G., Ulusoy, A.O., and Geiger, A. (July, January 21). OctNet: Learning Deep 3D Representations at High Resolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA."},{"key":"ref_10","first-page":"1","article-title":"O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis","volume":"36","author":"Wang","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref_11","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (July, January 21). PointNet: Deep learning on point sets for 3d classification and segmentation. Proceedings of the IEEE Conference on Computer VISION and Pattern recognition, Honolulu, HI, USA."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Engelmann, F., Kontogianni, T., Hermans, A., and Leibe, B. (2017, January 22\u201329). Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds. Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW), Venice, Italy.","DOI":"10.1109\/ICCVW.2017.90"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Griffiths, D., and Boehm, J. (2019). A Review on Deep Learning Techniques for 3D Sensed Data Classification. Remote. Sens., 11.","DOI":"10.3390\/rs11121499"},{"key":"ref_14","unstructured":"Behley, J., Garbade, M., Milioto, A., Quenzel, J., Behnke, S., Stachniss, C., and Gall, J. (November, January 27). SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Seoul, Korea."},{"key":"ref_15","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., and Guibas, L.J. (November, January 27). KPConv: Flexible and Deformable Convolution for Point Clouds. Proceedings of the IEEE International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_16","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. Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA."},{"key":"ref_17","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_18","first-page":"1","article-title":"Dynamic Graph CNN for Learning on Point Clouds","volume":"38","author":"Wang","year":"2019","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Komarichev, A., Zhong, Z., and Hua, J. (2019, January 15\u201320). A-CNN: Annularly Convolutional Neural Networks on Point Clouds. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00760"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Su, H., Jampani, V., Sun, D., Maji, S., Kalogerakis, E., Yang, M.H., and Kautz, J. (2018, January 18\u201322). SPLATNet: Sparse Lattice Networks for Point Cloud Processing. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00268"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, Y., Hou, Y., Zhang, S., and Shan, J. (2019, January 15\u201320). Graph Attention Convolution for Point Cloud Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.01054"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Engelmann, F., Kontogianni, T., Schult, J., and Leibe, B. (2019, January 16\u201321). Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds. Proceedings of the IEEE European Conference on Computer Vision\u2014ECCV Workshops, Long Beach, CA, USA.","DOI":"10.1007\/978-3-030-11015-4_29"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Xu, Y., Fan, T., Xu, M., Zeng, L., and Qiao, Y. (2018, January 18\u201322). SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters. Proceedings of the IEEE European Conference on Computer Vision, Salt Lake City, UT, USA.","DOI":"10.1007\/978-3-030-01237-3_6"},{"key":"ref_24","unstructured":"Li, Y., Bu, R., Sun, M., Wu, W., Di, X., and Chen, B. (2018). PointCNN: Convolution On X-Transformed Points. In Proceedings of the Neural Inf. Process. Syst. (NIPS). arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Groh, F., Wieschollek, P., and Lensch, H.P.A. (2018, January 2\u20136). Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds). Proceedings of the IEEE Asian Conference on Computer Vision (ACCV), Perth, Australia.","DOI":"10.1007\/978-3-030-20887-5_7"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, S., Suo, S., Ma, W.C., Pokrovsky, A., and Urtasun, R. (2018, January 18\u201322). Deep Parametric Continuous Convolutional Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00274"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Thomas, H., Deschaud, J.E., Marcotegui, B., Goulette, F., and Gall, Y.L. (2018, January 5\u20138). Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods. Proceedings of the IEEE International Conference on 3D Vision, Verona, Italy.","DOI":"10.1109\/3DV.2018.00052"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3272127.3275110","article-title":"Monte Carlo convolution for learning on non-uniformly sampled point clouds","volume":"37","author":"Hermosilla","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Hu, Q., Yang, B., Xie, L., Rosa, S., Guo, Y., Wang, Z., Trigoni, N., and Markham, A. (2020, January 13\u201319). RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Scott, D.W. (2015). Multivariate Density Estimation: Theory, Practice, and Visualization, John Wiley & Sons.","DOI":"10.1002\/9781118575574"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1177\/0278364918767506","article-title":"Paris-Lille-3D: A large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification","volume":"37","author":"Roynard","year":"2018","journal-title":"Int. J. Robot. Res."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Armeni, I., Sener, O., Zamir, A., Jiang, H., Brilakis, I., Fischer, M., and Savarese, S. (2016, January 27\u201330). 3D semantic parsing of large-scale indoor spaces. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Hackel, T., Savinov, N., Ladicky, L., Wegner, J., Schindler, K., and Pollefeys, M. (2017). SEMANTIC3D.NET: A new large-scale point cloud classification benchmark. arXiv.","DOI":"10.5194\/isprs-annals-IV-1-W1-91-2017"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.5194\/isprs-archives-XLIII-B2-2020-1419-2020","article-title":"A Benchmark For Large-Scale Heritage Point Cloud Semantic Segmentation","volume":"43","author":"Matrone","year":"2020","journal-title":"Int. Arch.Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"ref_36","unstructured":"Boulch, A., Puy, G., and Marlet, R. (December, January 30). FKAConv: Feature-Kernel Alignment for Point Cloud Convolution. Proceedings of the IEEE Asian Conference on Computer Vision, Kyoto, Japan."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Choy, C., and JunYoung Gwak, S.S. (2019, January 15\u201320). 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Tor, P., and Koltu, V. (2021, January 11\u201317). Point Transformer. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.01595"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/4\/982\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:30:16Z","timestamp":1760121016000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/4\/982"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,10]]},"references-count":38,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["rs15040982"],"URL":"https:\/\/doi.org\/10.3390\/rs15040982","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,10]]}}}