{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T10:03:07Z","timestamp":1784714587237,"version":"3.55.0"},"reference-count":48,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Characteristic Innovation Project of Colleges and Universities in Guangdong Province","award":["2025KTSCX349"],"award-info":[{"award-number":["2025KTSCX349"]}]},{"name":"Department of Education of Guangdong Province Young Innovative Talents Program Project","award":["2025KQNCX237"],"award-info":[{"award-number":["2025KQNCX237"]}]},{"name":"Doctoral Research Startup Fund Project","award":["BS22024009"],"award-info":[{"award-number":["BS22024009"]}]},{"name":"Guangdong Province Ordinary University Machine Vision and Inspection Technology Innovation Team","award":["2024KCXTD065"],"award-info":[{"award-number":["2024KCXTD065"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Modern autonomous systems rely on heterogeneous sensing modalities\u2014including vision sensors, millimeter-wave radar, and LiDAR\u2014yet each individual sensor exhibits characteristic failure modes in challenging real-world conditions. While LiDAR-vision co-processing has received extensive attention, the synergistic potential of 4D radar paired with monocular optics remains comparatively unexplored. To fill this gap, we develop a graph-enhanced multi-modal architecture that jointly leverages sparse 4D radar returns and high-resolution camera imagery for scene-level 3D perception. The proposed system is organized around four tightly coupled processing stages: (i) an image-guided point densification scheme (SAA) that augments sparse radar clouds with camera-derived pseudo measurements; (ii) a pose-invariant cross-modal fusion layer that harmonizes enriched radar features with image descriptors and object saliency maps; (iii) a dynamic hypergraph assembly stage that captures higher-order inter-object and cross-sensor dependencies; and (iv) a HyperGCN inference module that regresses 3D bounding parameters and class labels on the resulting relational graph. Integrating the temporal velocity cues native to radar with the rich appearance information from cameras, the system delivers reliable perception under diverse environmental conditions. On the View-of-Delft (VOD) evaluation suite, the proposed model records an mAP of 69.3 and mAOS of 59.8. A systematic ablation further quantifies how geometric invariance\u2014across translation, rotation, and scale transformations\u2014individually affects end-to-end detection fidelity.<\/jats:p>","DOI":"10.3390\/s26144635","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T09:20:39Z","timestamp":1784712039000},"page":"4635","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Graph Enhanced Multi-Modal Network of 4-D Radar-Camera Fusion for Perception in Autonomous Systems"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5465-5043","authenticated-orcid":false,"given":"Yuanzhi","family":"Deng","sequence":"first","affiliation":[{"name":"School of Sino-German Intelligent Manufacturing, Shenzhen City Polytechnic, Shenzhen 518116, China"},{"name":"Guangdong Engineering Center for Intelligent Sensing and Flexible Manufacturing, Shenzhen City Polytechnic, Shenzhen 518116, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Chi","sequence":"additional","affiliation":[{"name":"College of Urban Transportation and Logistics, Shenzhen Technology University, Shenzhen 518118, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhao","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Urban Transportation and Logistics, Shenzhen Technology University, Shenzhen 518118, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Han","sequence":"additional","affiliation":[{"name":"School of Sino-German Intelligent Manufacturing, Shenzhen City Polytechnic, Shenzhen 518116, China"},{"name":"Guangdong Engineering Center for Intelligent Sensing and Flexible Manufacturing, Shenzhen City Polytechnic, Shenzhen 518116, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanyin","family":"He","sequence":"additional","affiliation":[{"name":"School of Sino-German Intelligent Manufacturing, Shenzhen City Polytechnic, Shenzhen 518116, China"},{"name":"Guangdong Engineering Center for Intelligent Sensing and Flexible Manufacturing, Shenzhen City Polytechnic, Shenzhen 518116, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaolong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Sino-German Intelligent Manufacturing, Shenzhen City Polytechnic, Shenzhen 518116, China"},{"name":"Guangdong Engineering Center for Intelligent Sensing and Flexible Manufacturing, Shenzhen City Polytechnic, Shenzhen 518116, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1842","DOI":"10.1007\/s10489-022-03468-6","article-title":"Improving environmental awareness for autonomous vehicles","volume":"53","author":"Peixoto","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1909","DOI":"10.1007\/s11263-023-01790-1","article-title":"3D object detection for autonomous driving: A comprehensive survey","volume":"131","author":"Mao","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"22753","DOI":"10.1007\/s10489-023-04630-4","article-title":"3D object detection algorithm based on multi-sensor segmental fusion of frustum association for autonomous driving","volume":"53","author":"Tao","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Nabati, R., and Qi, H. (2020). CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection. 2021 IEEE Winter Conference on Applications of Computer Vision, IEEE.","DOI":"10.1109\/WACV48630.2021.00157"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Li, Y., Yu, A.W., Meng, T., Caine, B., Ngiam, J., Peng, D., Shen, J., Wu, B.X., Lu, Y., and Zhou, D. (2022). DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection. 2022 IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"St\u00e4cker, L., Mishra, S., Heidenreich, P., Rambach, J., and Stricker, D. (2023, January 19\u201322). RC-BEVFusion: A plug-in module for radar-camera bird\u2019s eye view feature fusion. Proceedings of the DAGM German Conference on Pattern Recognition, Munich, Germany.","DOI":"10.1007\/978-3-031-54605-1_12"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Vora, S., Lang, A.H., Helou, B., and Beijbom, O. (2020). Pointpainting: Sequential fusion for 3d object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Fent, F., Bauerschmidt, P., and Lienkamp, M. (2023). RadarGNN: Transformation Invariant Graph Neural Network for Radar-based Perception. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPRW59228.2023.00023"},{"key":"ref_9","unstructured":"Yadati, N., Nimishakavi, M., Yadav, P., Nitin, V., Louis, A., and Talukdar, P. (2019). Hypergcn: A new method for training graph convolutional networks on hypergraphs. Adv. Neural Inf. Process. Syst., 32\u201345."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wu, X., Chen, Q., Li, W., Xiao, Y., and Hu, B. (2020). AdaHGNN: Adaptive hypergraph neural networks for multi-label image classification. Proceedings of the 28th ACM International Conference on Multimedia, ACM.","DOI":"10.1145\/3394171.3414046"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ali, W., Abdelkarim, S., Zidan, M., Zahran, M., and El Sallab, A. (2018, January 8\u201314). Yolo3d: End-to-end real-time 3d oriented object bounding box detection from lidar point cloud. Proceedings of the European Conference on Computer Vision Workshops, Munich, Germany.","DOI":"10.1007\/978-3-030-11015-4_54"},{"key":"ref_12","unstructured":"Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv."},{"key":"ref_13","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017). Pointnet: Deep learning on point sets for 3d classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., and Xia, T. (2017). Multi-view 3d object detection network for autonomous driving. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., and Waslander, S.L. (2018). Joint 3d proposal generation and object detection from view aggregation. Proceedings of the IEEE International Conference on Intelligent Robots and Systems, IEEE.","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bulo, S.R., Porzi, L., L\u00f3pez-Antequera, M., and Kontschieder, P. (2019). Disentangling monocular 3d object detection. Proceedings of the IEEE International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV.2019.00208"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.neucom.2021.01.110","article-title":"Monocular 3D object detection using dual quadric for autonomous driving","volume":"441","author":"Li","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., and Krahenbuhl, P. (2021). Center-based 3d object detection and tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., and Beijbom, O. (2019). Pointpillars: Fast encoders for object detection from point clouds. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., and Li, H. (2019). Pointrcnn: 3d object proposal generation and detection from point cloud. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref_21","unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inf. Process. Syst., 30\u201345."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., and Jia, J. (2020). 3dssd: Point-based 3d single stage object detector. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., and Li, H. (2020). Pv-rcnn: Point-voxel feature set abstraction for 3d object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zheng, W., Tang, W., Chen, S., Jiang, L., and Fu, C.W. (2021, January 2\u20139). Cia-ssd: Confident iou-aware single-stage object detector from point cloud. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i4.16470"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yan, Y., Mao, Y., and Li, B. (2018). Second: Sparsely embedded convolutional detection. Sensors, 18.","DOI":"10.3390\/s18103337"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhou, Y., and Tuzel, O. (2018). Voxelnet: End-to-end learning for point cloud based 3d object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wang, Z., and Jia, K. (2019). Frustum convnet: Sliding frustums to aggregate local point-wise features for amodal 3d object detection. Proceedings of the 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems, IEEE.","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1523","DOI":"10.1109\/TIV.2023.3240287","article-title":"Bridging the view disparity between radar and camera features for multi-modal fusion 3d object detection","volume":"8","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"4961","DOI":"10.1109\/LRA.2022.3147324","article-title":"Multi-class road user detection with 3+ 1D radar in the View-of-Delft dataset","volume":"7","author":"Palffy","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_31","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. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Yu, F., Wang, D., Shelhamer, E., and Darrell, T. (2018). Deep layer aggregation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., and Tian, Q. (2019). Centernet: Keypoint triplets for object detection. Proceedings of the IEEE International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Drost, B., Ulrich, M., Navab, N., and Ilic, S. (2010). Model globally, match locally: Efficient and robust 3D object recognition. Proceedings of the 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2010.5540108"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Law, H., and Deng, J. (2018). Cornernet: Detecting objects as paired keypoints. Proceedings of the European Conference on Computer Vision, IEEE.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref_36","first-page":"3781","article-title":"Multi-modal 3d object detection in autonomous driving: A survey","volume":"8","author":"Wang","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"ref_37","first-page":"7016","article-title":"Hypergraph Representation for Detecting 3D Objects from Noisy Point Clouds","volume":"35","author":"Jiang","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: A review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Chiang, W.L., Liu, X., Si, S., Li, Y., Bengio, S., and Hsieh, C.J. (2019). Cluster-gcn: An efficient algorithm for training deep and large graph convolutional networks. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, IEEE.","DOI":"10.1145\/3292500.3330925"},{"key":"ref_40","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_41","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014, January 6\u201312). Microsoft coco: Common objects in context. Proceedings of the Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Shi, W., and Rajkumar, R. (2020). Point-gnn: Graph neural network for 3d object detection in a point cloud. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"ref_44","unstructured":"Cortes, C., Mohri, M., and Rostamizadeh, A. (2009, January 18\u201321). L2 regularization for learning kernels. Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, UAI 2009, Montreal, QC, Canada."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Shi, X., Chen, Z., and Kim, T.K. (2023). Multivariate Probabilistic Monocular 3D Object Detection. Proceedings of the IEEE Winter Conference on Applications of Computer Vision, IEEE.","DOI":"10.1109\/WACV56688.2023.00426"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hu, Q., Xu, G., Ma, Y., Wan, J., and Guo, Y. (2022). Not all points are equal: Learning highly efficient point-based detectors for 3d lidar point clouds. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Svenningsson, P., Fioranelli, F., and Yarovoy, A. (2021). Radar-pointgnn: Graph based object recognition for unstructured radar point-cloud data. Proceedings of the 2021 IEEE Radar Conference, IEEE.","DOI":"10.1109\/RadarConf2147009.2021.9455172"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Luo, Z., Zhang, G., Zhou, C., Liu, T., Lu, S., and Pan, L. (2023). TransPillars: Coarse-to-fine aggregation for multi-frame 3D object detection. Proceedings of the IEEE Winter Conference on Applications of Computer Vision, IEEE.","DOI":"10.1109\/WACV56688.2023.00421"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4635\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T09:24:01Z","timestamp":1784712241000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4635"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":48,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144635"],"URL":"https:\/\/doi.org\/10.3390\/s26144635","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,22]]}}}