{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:27:54Z","timestamp":1785421674684,"version":"3.56.0"},"reference-count":30,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100004415","name":"North Atlantic Treaty Organization","doi-asserted-by":"crossref","award":["G-5888"],"award-info":[{"award-number":["G-5888"]}],"id":[{"id":"10.13039\/100004415","id-type":"DOI","asserted-by":"crossref"}]},{"award":["G-5888"],"award-info":[{"award-number":["G-5888"]}],"id":[{"id":"https:\/\/ror.org\/05xagc088","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/100019347","name":"Universidad Pedag\u00f3gica y Tecnol\u00f3gica de Colombia","doi-asserted-by":"crossref","award":["SGI-3139"],"award-info":[{"award-number":["SGI-3139"]}],"id":[{"id":"10.13039\/100019347","id-type":"DOI","asserted-by":"crossref"}]},{"award":["SGI-3139"],"award-info":[{"award-number":["SGI-3139"]}],"id":[{"id":"https:\/\/ror.org\/04vdmbk59","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Reliable person segmentation with sparse 3D sensors degrades significantly under adverse atmospheric conditions. This work presents a controlled comparative evaluation of four segmentation architectures\u2014U-Net, Mask R-CNN, DeepLabV3+, and FCN-ResNet\u2014on a fused Radar\u2013LiDAR dataset for binary person\u2013background segmentation and applies a dual-domain evaluation procedure that formally links 2D pixel-level overlap (IoU, Dice) to 3D geometric fidelity (Chamfer distance, Completeness) through mask back-projection onto fused point clouds. Raw point clouds are rasterized into range\u2013intensity grids enriched with Radar reflectivity; the predicted masks are then reprojected into 3D space and evaluated using Chamfer distance and Completeness under three controlled visibility conditions. U-Net achieves the highest 2D overlap (IoU = 0.82, Dice = 0.89), while DeepLabV3+ delivers the best 3D reconstruction fidelity (Chamfer = 0.021 m, Completeness = 93.4%) and the highest overall accuracy (97.9%). This dissociation between 2D overlap and 3D fidelity is explained by DeepLabV3+\u2019s multi-scale Atrous Spatial Pyramid Pooling (ASPP), which reduces boundary fragmentation during back-projection; more than 70% of the Chamfer deviation across competing architectures originates at object contours. Mask R-CNN performs well when instances are clearly separated, and FCN-ResNet offers the lowest computational cost at reduced boundary precision. Radar\u2013LiDAR fusion sustains an IoU within 3% of clear-weather performance under dense fog, whereas LiDAR-only inputs degrade by more than 12%. Due to the 12:1 background-to-person class imbalance, overlap-based metrics (IoU, Dice) are prioritized over raw accuracy in all reported comparisons. These results provide actionable deployment guidance and constitute a reproducible evaluation procedure for future sparse-sensor fusion studies, independently of the architectures evaluated.<\/jats:p>","DOI":"10.3390\/s26092900","type":"journal-article","created":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T09:03:37Z","timestamp":1778144617000},"page":"2900","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fusion-Based Semantic Segmentation and 3D Reconstruction Using Radar\u2013LiDAR Point Clouds: A Comparative Evaluation of DeepLabv3 and FCN-ResNet Against Traditional Architectures"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5389-1479","authenticated-orcid":false,"given":"John","family":"Paipa","sequence":"first","affiliation":[{"name":"Escuela de Ingenier\u00eda de Sistemas y Computaci\u00f3n, UPTC, Sogamoso 152210, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8420-3445","authenticated-orcid":false,"given":"Cristian","family":"Suancha","sequence":"additional","affiliation":[{"name":"Escuela de Ingenier\u00eda de Sistemas y Computaci\u00f3n, UPTC, Sogamoso 152210, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0910-8539","authenticated-orcid":false,"given":"Eduardo A.","family":"Fern\u00e1ndez","sequence":"additional","affiliation":[{"name":"Escuela de Ingenier\u00eda Electr\u00f3nica, UPTC, Sogamoso 152210, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"key":"ref_1","first-page":"4515","article-title":"Atmospheric Scattering Model Combined with Image Segmentation in Foggy Image Enhancement","volume":"15","author":"Zhao","year":"2011","journal-title":"Procedia Eng."},{"key":"ref_2","first-page":"1510","article-title":"Radar\u2013LiDAR Fusion for Robust Object Detection in Autonomous Driving","volume":"26","author":"Park","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A.H., Vora, S., Liong, V.E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., and Beijbom, O. (2020). nuScenes: A Multimodal Dataset for Autonomous Driving. arXiv.","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015). Fully Convolutional Networks for Semantic Segmentation. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","article-title":"Fully Convolutional Networks for Semantic Segmentation","volume":"39","author":"Shelhamer","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017). Mask R-CNN. 2017 IEEE International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_8","first-page":"833","article-title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","volume":"Volume 11211","author":"Chen","year":"2018","journal-title":"Proceedings of the European Conference Computer Vision (ECCV)"},{"key":"ref_9","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., and Luo, P. (2021, January 6\u201314). SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. Proceedings of the 35th International Conference on Neural Information Processing Systems, Virtual."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"10138","DOI":"10.1109\/TPAMI.2024.3434373","article-title":"Transformer-Based Visual Segmentation: A Survey","volume":"46","author":"Li","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Urrea, C., and V\u00e9lez, M. (2025). Advances in Deep Learning for Semantic Segmentation of Low-Contrast Images: A Systematic Review of Methods, Challenges, and Future Directions. Sensors, 25.","DOI":"10.3390\/s25072043"},{"key":"ref_12","unstructured":"Ma, Z., and Tang, H. (2025). Multimodal Alignment and Fusion: A Survey. arXiv."},{"key":"ref_13","first-page":"1","article-title":"A Comprehensive Survey on Deep Learning Multi-Modal Fusion","volume":"96","author":"Cheng","year":"2024","journal-title":"J. Signal Process. Syst."},{"key":"ref_14","first-page":"14200","article-title":"Attention Bottlenecks for Multimodal Fusion","volume":"34","author":"Nagrani","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref_15","first-page":"1","article-title":"ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection","volume":"146","author":"Zhao","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tao, Y., Liu, W., Chen, J., Gao, J., Li, R., Wang, X., Zhang, Y., Ren, J., Yin, S., and Zhu, X. (2025). A Graph-Based Multimodal Data Fusion Framework for Identifying Urban Functional Zone. Int. J. Appl. Earth Obs. Geoinf., 136.","DOI":"10.1016\/j.jag.2024.104353"},{"key":"ref_17","first-page":"2300","article-title":"Gated Graph Fusion for Robust 3D Perception","volume":"9","author":"Huang","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Riegler, G., Ulusoy, A.O., and Geiger, A. (2017). OctNet: Learning Deep 3D Representations at High Resolutions. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2017.701"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, A., Tsui, P., Guo, J., Zhou, Y., Chai, Y., and Caine, B. (2020). Scalability in Perception for Autonomous Driving: Waymo Open Dataset. arXiv.","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1177\/0278364913491297","article-title":"Vision Meets Robotics: The KITTI Dataset","volume":"32","author":"Geiger","year":"2013","journal-title":"Int. J. Robot. Res."},{"key":"ref_21","unstructured":"Chen, Z., Zhao, M., and Tang, X. (2024). Multi-Dataset Training for LiDAR 3D Object Detection Generalization. arXiv."},{"key":"ref_22","first-page":"15112","article-title":"Limitations of Open Multimodal Datasets for Adverse Weather Perception","volume":"13","author":"Alvarez","year":"2025","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"108825","DOI":"10.1109\/ACCESS.2024.3435993","article-title":"Semantic Segmentation and Construction of a Dataset from a 3D Point Cloud Obtained by LiDAR Sensor","volume":"12","author":"Mesa","year":"2024","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Safarov, F., Khojamuratova, U., Komoliddin, M., Kurbanov, Z., Tamara, A., Nizamjon, I., Muksimova, S., and Cho, Y.I. (2025). Lightweight Evolving U-Net for Next-Generation Biomedical Imaging. Diagnostics, 15.","DOI":"10.3390\/diagnostics15091120"},{"key":"ref_25","first-page":"740","article-title":"Microsoft COCO: Common Objects in Context","volume":"8693","author":"Lin","year":"2014","journal-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. Feature Pyramid Networks for Object Detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017). Focal Loss for Dense Object Detection. 2017 IEEE International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_28","unstructured":"Tan, M., and Le, Q. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.neunet.2018.07.011","article-title":"A Systematic Study of the Class Imbalance Problem in Convolutional Neural Networks","volume":"106","author":"Buda","year":"2018","journal-title":"Neural Netw."},{"key":"ref_30","unstructured":"Banbury, C., Reddi, V.J., Torelli, P., Krishnan, R., Wan, B., Criado, G., Warden, P., Kanter, D., Jeyakumar, C., and Pau, D. (2021). MLPerf Tiny Benchmark. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/9\/2900\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T04:29:50Z","timestamp":1778214590000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/9\/2900"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":30,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["s26092900"],"URL":"https:\/\/doi.org\/10.3390\/s26092900","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]}}}