{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T17:59:09Z","timestamp":1793123949351,"version":"4.5.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T00:00:00Z","timestamp":1767744000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T00:00:00Z","timestamp":1767830400000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100009367","name":"Mansoura University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100009367","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This paper presents a modular late-fusion framework that integrates Camera, LiDAR, and Radar modalities for object classification in autonomous driving. Rather than relying on complex end-to-end fusion architectures, we train two lightweight yet complementary neural networks independently: a CNN for Camera\u2009+\u2009LiDAR using KITTI, and a GRU-based radar classifier trained on RadarScenes. A unified 5-class label space is constructed to align the heterogeneous datasets, and we verify its validity through class-distribution analysis. The fusion rule is formally defined using a confidence-weighted decision mechanism. To ensure statistical rigor, we conduct 3-fold cross-validation with three random seeds, reporting mean and standard deviation of mAP and per-class AP. Results show that the Camera\u2009+\u2009LiDAR model achieves a strong average mAP of 95.34%, while Radar achieves 33.89%, reflecting its robustness but lower granularity. Using the proposed late-fusion rule, performance increases to 94.97% mAP versus KITTI ground truth and 33.74% versus RadarScenes. Cross-validated per-class trends confirm complementary sensing: Camera\u2009+\u2009LiDAR excels at Cars, Bicycles, and Pedestrians, while Radar contributes stability under adverse conditions. The paper also provides a complexity and latency analysis, discusses dataset limitations, clarifies temporal handling for radar, and includes updated literature up to 2025. Findings show that lightweight late fusion can achieve high reliability while remaining computationally efficient, making it suitable for real-time embedded autonomous driving systems.<\/jats:p>","DOI":"10.1038\/s41598-025-32588-5","type":"journal-article","created":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T12:36:39Z","timestamp":1767789399000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Cross-dataset late fusion of Camera\u2013LiDAR and radar models for object detection"],"prefix":"10.1038","volume":"16","author":[{"given":"Assem","family":"Ali","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed M.","family":"Tawfik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahmoud M.","family":"Saafan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,7]]},"reference":[{"issue":"6","key":"32588_CR1","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.3390\/s21062140","volume":"21","author":"DJ Yeong","year":"2021","unstructured":"Yeong, D. J. et al. Sensor and sensor fusion technology in autonomous vehicles: A review. Sensors 21 (6), 2140. https:\/\/doi.org\/10.3390\/s21062140 (2021).","journal-title":"Sensors"},{"issue":"15","key":"32588_CR2","doi-asserted-by":"publisher","first-page":"4220","DOI":"10.3390\/s20154220","volume":"20","author":"J Fayyad","year":"2020","unstructured":"Fayyad, J. et al. Deep learning sensor fusion for autonomous vehicle perception and localization: A review. Sensors 20 (15), 4220. https:\/\/doi.org\/10.3390\/s20154220 (2020).","journal-title":"Sensors"},{"key":"32588_CR3","doi-asserted-by":"publisher","unstructured":"Man, Y., Gui, L. Y. & Wang, Y. X. Bev-guided multi-modality fusion for driving perception.\u00a0\u00a0IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21960\u201321969. (2023). https:\/\/doi.org\/10.1109\/cvpr52729.2023.02103","DOI":"10.1109\/cvpr52729.2023.02103"},{"key":"32588_CR4","doi-asserted-by":"publisher","unstructured":"Liu, Z. et al. Bevfusion: Multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. 2023 IEEE Int. Conf. Rob. Autom. (ICRA) 2774\u20132781. https:\/\/doi.org\/10.1109\/icra48891.2023.10160968 (2023).","DOI":"10.1109\/icra48891.2023.10160968"},{"key":"32588_CR5","doi-asserted-by":"publisher","unstructured":"Drews, F. et al. DeepFusion: A robust and modular 3D object detector for lidars, cameras and radars. 2022 IEEE\/RSJ Int. Conf. Intell. Robots Syst. (IROS) 560\u2013567. https:\/\/doi.org\/10.1109\/iros47612.2022.9981778 (2022).","DOI":"10.1109\/iros47612.2022.9981778"},{"issue":"11","key":"32588_CR6","doi-asserted-by":"publisher","first-page":"12878","DOI":"10.1109\/tpami.2022.3200245","volume":"45","author":"K Chitta","year":"2023","unstructured":"Chitta, K. et al. Transfuser: imitation with transformer-based sensor fusion for autonomous driving. IEEE Trans. Pattern Anal. Mach. Intell. 45 (11), 12878\u201312895. https:\/\/doi.org\/10.1109\/tpami.2022.3200245 (2023).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32588_CR7","doi-asserted-by":"publisher","unstructured":"Qin, Z. et al. Unifusion: Unified multi-view fusion transformer for spatial-temporal representation in bird\u2019s-eye-view.\u00a0IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8656\u20138665. (2023). https:\/\/doi.org\/10.1109\/iccv51070.2023.00798","DOI":"10.1109\/iccv51070.2023.00798"},{"key":"32588_CR8","doi-asserted-by":"publisher","first-page":"97147","DOI":"10.1109\/access.2023.3312382","volume":"11","author":"A Srivastav","year":"2023","unstructured":"Srivastav, A. & Mandal, S. Radars for autonomous driving: A review of deep learning methods and challenges. IEEE Access. 11, 97147\u201397168. https:\/\/doi.org\/10.1109\/access.2023.3312382 (2023).","journal-title":"IEEE Access."},{"key":"32588_CR9","doi-asserted-by":"publisher","unstructured":"Lang, A. H. et al. Pointpillars: Fast encoders for object detection from point clouds.\u00a0IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) [Preprint]. (2019). https:\/\/doi.org\/10.1109\/cvpr.2019.01298","DOI":"10.1109\/cvpr.2019.01298"},{"issue":"10","key":"32588_CR10","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y. & Li, B. Second: sparsely embedded convolutional detection. Sensors 18 (10), 3337. https:\/\/doi.org\/10.3390\/s18103337 (2018).","journal-title":"Sensors"},{"key":"32588_CR11","doi-asserted-by":"publisher","unstructured":"Yin, T., Zhou, X. & Krahenbuhl, P. Center-based 3D object detection and tracking.\u00a0IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11779\u201311788. (2021). https:\/\/doi.org\/10.1109\/cvpr46437.2021.01161","DOI":"10.1109\/cvpr46437.2021.01161"},{"key":"32588_CR12","doi-asserted-by":"publisher","unstructured":"Zhou, Y. & Tuzel, O. VoxelNet: End-to-end learning for point cloud based 3D object detection.\u00a0IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4490\u20134499. (2018). https:\/\/doi.org\/10.1109\/cvpr.2018.00472","DOI":"10.1109\/cvpr.2018.00472"},{"issue":"6","key":"32588_CR13","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/tpami.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S. et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39 (6), 1137\u20131149. https:\/\/doi.org\/10.1109\/tpami.2016.2577031 (2017).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32588_CR14","unstructured":"Redmon, J. & Farhadi, A. Yolov3: An incremental improvement, arXiv.org. (2018). Available at: https:\/\/arxiv.org\/abs\/1804.02767 (Accessed: 22 June 2025)."},{"key":"32588_CR15","unstructured":"Wu, D. et al. A survey of deep learning based radar and vision fusion for 3D object detection in autonomous driving, arXiv.org. (2024). Available at: https:\/\/arxiv.org\/abs\/2406.00714 (Accessed: 02 December 2025)."},{"key":"32588_CR16","doi-asserted-by":"publisher","unstructured":"Wu, Z. et al. MVFusion: Multi-view 3D object detection with Semantic-aligned radar and camera fusion. IEEE Int. Conf. Rob. Autom. (ICRA). 2766\u20132773. https:\/\/doi.org\/10.1109\/icra48891.2023.10161329 (2023).","DOI":"10.1109\/icra48891.2023.10161329"},{"issue":"12","key":"32588_CR17","doi-asserted-by":"publisher","first-page":"5598","DOI":"10.3390\/app11125598","volume":"11","author":"F Nobis","year":"2021","unstructured":"Nobis, F. et al. Radar voxel fusion for 3D object detection. Appl. Sci. 11 (12), 5598. https:\/\/doi.org\/10.3390\/app11125598 (2021).","journal-title":"Appl. Sci."},{"key":"32588_CR18","doi-asserted-by":"publisher","unstructured":"Yang, B. et al. RadarNet: Exploiting radar for robust perception of dynamic objects.\u00a0Lecture Notes in Computer Science, pp. 496\u2013512. (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_29","DOI":"10.1007\/978-3-030-58523-5_29"},{"key":"32588_CR19","doi-asserted-by":"publisher","unstructured":"Wang, Y. et al. Bi-lrfusion: Bi-directional LIDAR-radar fusion for 3D dynamic object detection. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR). 13394\u201313403. https:\/\/doi.org\/10.1109\/cvpr52729.2023.01287 (2023).","DOI":"10.1109\/cvpr52729.2023.01287"},{"key":"32588_CR20","doi-asserted-by":"publisher","unstructured":"Chae, Y., Kim, H. & Yoon, K. J. Towards robust 3D object detection with LIDAR and 4D radar fusion in various weather conditions.\u00a0IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15162\u201315172. (2024). https:\/\/doi.org\/10.1109\/cvpr52733.2024.01436","DOI":"10.1109\/cvpr52733.2024.01436"},{"key":"32588_CR21","doi-asserted-by":"publisher","unstructured":"Le, D. T. et al. Diffusion model for robust multi-sensor fusion in 3D object detection and bev segmentation. Lecture Notes in Computer Science 232\u2013249. https:\/\/doi.org\/10.1007\/978-3-031-73113-6_14 (2024).","DOI":"10.1007\/978-3-031-73113-6_14"},{"key":"32588_CR22","doi-asserted-by":"publisher","unstructured":"Geiger, A., Lenz, P. & Urtasun, R. Are we ready for autonomous driving? The Kitti Vision Benchmark Suite.\u00a0IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. (2012). https:\/\/doi.org\/10.1109\/cvpr.2012.6248074","DOI":"10.1109\/cvpr.2012.6248074"},{"key":"32588_CR23","unstructured":"Schumann, O. et al. RadarScenes: A real-world radar point cloud data set for automotive applications. zenodo.org. (2021). Available at: https:\/\/arxiv.org\/html\/2104.02493v2 (Accessed: 22 June 2025)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-32588-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-32588-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-32588-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T16:15:27Z","timestamp":1781626527000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-32588-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,7]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["32588"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-32588-5","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,7]]},"assertion":[{"value":"1 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"879"}}