{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T04:15:19Z","timestamp":1790223319881,"version":"4.1.0"},"reference-count":32,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China\n\t\t\t\t\t\t\t\t              https:\/\/ror.org\/01h0zpd94","doi-asserted-by":"publisher","award":["62003362"],"award-info":[{"award-number":["62003362"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>4D millimeter-wave radar provides high-precision ranging capability and exhibits strong robustness under adverse weather and low-visibility conditions, but its point clouds are relatively sparse and suffer from severe elevation-angle measurement noise. Monocular cameras, by contrast, provide rich semantic information and high recall, yet are fundamentally limited by scale ambiguity. To exploit the complementary characteristics of these two sensors, this paper proposes a radar-camera fusion 3D multi-object tracking framework that does not rely on complex 3D annotated data. First, on the radar signal-processing side, a Gaussian distribution-based adaptive angle compression method and IMU-based velocity compensation are introduced to effectively suppress measurement noise, and an improved DBSCAN clustering scheme with recursive cluster splitting and historical static-box guidance is employed to generate high-quality radar detections. Second, a disparity-domain metric depth recovery method is proposed. This method uses filtered radar points as sparse metric anchors, performs robust fitting with RANSAC, and applies Kalman filtering for temporal smoothing, thereby converting the relative depth output of the visual foundation model Depth Anything V2 into metric depth. Finally, a hierarchical fusion strategy is designed at both the detection and tracking levels to achieve stable cross-modal state association. Experimental results on a self-collected dataset show that the proposed method achieves an overall MOTA of 77.93%, outperforming single-modality baselines and other comparison methods by 11 to 31 percentage points. This study provides an effective solution for low-cost and robust environment perception in complex dynamic scenarios.<\/jats:p>","DOI":"10.3390\/s26072096","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T14:33:33Z","timestamp":1774622013000},"page":"2096","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Robust 3D Multi-Object Tracking via 4D mmWave Radar-Camera Fusion and Disparity-Domain Depth Recovery"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9435-5712","authenticated-orcid":false,"given":"Yunfei","family":"Xie","sequence":"first","affiliation":[{"name":"Northwest Institute of Mechanical and Electrical Engineering, Xianyang 712099, China"},{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0678-987X","authenticated-orcid":false,"given":"Xiaohui","family":"Li","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3414-6529","authenticated-orcid":false,"given":"Dingheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwest Institute of Mechanical and Electrical Engineering, Xianyang 712099, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwest Institute of Mechanical and Electrical Engineering, Xianyang 712099, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiliang","family":"Li","sequence":"additional","affiliation":[{"name":"Northwest Institute of Mechanical and Electrical Engineering, Xianyang 712099, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwest Institute of Mechanical and Electrical Engineering, Xianyang 712099, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenping","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1109\/MVT.2019.2892497","article-title":"The impact of adverse weather conditions on autonomous vehicles: How rain, snow, fog, and hail affect the performance of a self-driving car","volume":"14","author":"Zang","year":"2019","journal-title":"IEEE Veh. Technol. Mag."},{"key":"ref_2","unstructured":"Eigen, D., Puhrsch, C., and Fergus, R. (2014, January 8\u201313). Depth map prediction from a single image using a multi-scale deep network. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1109\/MSP.2020.2978507","article-title":"MIMO radar for advanced driver-assistance systems and autonomous driving: Advantages and challenges","volume":"37","author":"Sun","year":"2020","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_4","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_5","doi-asserted-by":"crossref","first-page":"5628","DOI":"10.1109\/TVT.2022.3230265","article-title":"Multi-modal and multi-scale fusion 3D object detection of 4D radar and LiDAR for autonomous driving","volume":"72","author":"Wang","year":"2022","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","article-title":"Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer","volume":"44","author":"Ranftl","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., and Koltun, V. (2021, January 10\u201317). Vision transformers for dense prediction. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., and Zhao, H. (2024, January 17\u201321). Depth anything: Unleashing the power of large-scale unlabeled data. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref_9","unstructured":"Yang, L., Kang, B., Huang, Z., Zhao, Z., Xu, X., Feng, J., and Zhao, H. (2024). Depth anything v2. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ma, F., and Karaman, S. (2018). Sparse-to-dense: Depth prediction from sparse depth samples and a single image. Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), IEEE.","DOI":"10.1109\/ICRA.2018.8460184"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Park, J., Joo, K., Hu, Z., Liu, C.K., and So Kweon, I. (2020). Non-local spatial propagation network for depth completion. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-030-58601-0_8"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Long, Y., Morris, D., Liu, X., Castro, M., Chakravarty, P., and Narayanan, P. (2021, January 19\u201325). Radar-camera pixel depth association for depth completion. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Online.","DOI":"10.1109\/CVPR46437.2021.01232"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lin, J.T., Dai, D., and Van Gool, L. (2020). Depth estimation from monocular images and sparse radar data. Proceedings of the 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE.","DOI":"10.1109\/IROS45743.2020.9340998"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Nabati, R., and Qi, H. (2021, January 5\u20139). Centerfusion: Center-based radar and camera fusion for 3d object detection. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Online.","DOI":"10.1109\/WACV48630.2021.00157"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"8503814","DOI":"10.1109\/TIM.2023.3280525","article-title":"Rcfusion: Fusing 4-D radar and camera with bird\u2019s-eye view features for 3-D object detection","volume":"72","author":"Zheng","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1109\/LRA.2024.3513041","article-title":"Sgdet3D: Semantics and geometry fusion for 3D object detection using 4d radar and camera","volume":"10","author":"Bai","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Pan, Z., Ding, F., Zhong, H., and Lu, C.X. (2024). Ratrack: Moving object detection and tracking with 4D radar point cloud. Proceedings of the 2024 IEEE International Conference on Robotics and Automation (ICRA), IEEE.","DOI":"10.1109\/ICRA57147.2024.10610368"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"37764","DOI":"10.1109\/JSEN.2024.3465019","article-title":"A robust multi-object tracking method based on 4D millimeter wave radar and monocular vision fusion","volume":"24","author":"Tang","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kuan, S.Y., Cheng, J.H., Huang, H.W., Chai, W., Yang, C.Y., Latapie, H., Liu, G., Wu, B.F., and Hwang, J.N. (2024). Boosting online 3D multi-object tracking through camera-radar cross check. Proceedings of the 2024 IEEE Intelligent Vehicles Symposium (IV), IEEE.","DOI":"10.1109\/IV55156.2024.10588514"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Tan, B., Ma, Z., Zhu, X., Li, S., Zheng, L., Huang, L., and Bai, J. (2023). Tracking of multiple static and dynamic targets for 4d automotive millimeter-wave radar point cloud in urban environments. Remote Sens., 15.","DOI":"10.3390\/rs15112923"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Liu, J., Ding, G., Xia, Y., Sun, J., Huang, T., Xie, L., and Zhu, B. (2024). Which framework is suitable for online 3D multi-object tracking for autonomous driving with automotive 4d imaging radar?. Proceedings of the 2024 IEEE Intelligent Vehicles Symposium (IV), IEEE.","DOI":"10.1109\/IV55156.2024.10588837"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"17218","DOI":"10.1109\/TITS.2024.3421339","article-title":"Deep learning-based robust multi-object tracking via fusion of mmWave radar and camera sensors","volume":"25","author":"Cheng","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"11125","DOI":"10.1109\/JSEN.2022.3219643","article-title":"3-D object detection for multiframe 4-D automotive millimeter-wave radar point cloud","volume":"23","author":"Tan","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1465","DOI":"10.3390\/rs17081465","article-title":"Moving-Least-Squares-Enhanced 3D Object Detection for 4D Millimeter-Wave Radar","volume":"17","author":"Shi","year":"2025","journal-title":"Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Cheng, L., Sengupta, A., and Cao, S. (2023). 3D radar and camera co-calibration: A flexible and accurate method for target-based extrinsic calibration. Proceedings of the 2023 IEEE Radar Conference (RadarConf23), IEEE.","DOI":"10.1109\/RadarConf2351548.2023.10149669"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Cheng, L., and Cao, S. (2023). Online targetless radar-camera extrinsic calibration based on the common features of radar and camera. Proceedings of the NAECON 2023-IEEE National Aerospace and Electronics Conference, IEEE.","DOI":"10.1109\/NAECON58068.2023.10366051"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1109\/TITS.2025.3624716","article-title":"Radar-Camera Fused Multi-Object Tracking: Online Calibration and Common Feature","volume":"27","author":"Cheng","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kramer, A., Stahoviak, C., Santamaria-Navarro, A., Agha-Mohammadi, A.A., and Heckman, C. (2020). Radar-inertial ego-velocity estimation for visually degraded environments. Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA), IEEE.","DOI":"10.1109\/ICRA40945.2020.9196666"},{"key":"ref_29","unstructured":"Ester, M., Kriegel, H.P., Sander, J., and Xu, X. (1996, January 2\u20134). A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD-96), Portland, OR, USA."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., and Wang, X. (2022). Bytetrack: Multi-object tracking by associating every detection box. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Casiez, G., Roussel, N., and Vogel, D. (2012, January 5\u201310). 1\u20ac filter: A simple speed-based low-pass filter for noisy input in interactive systems. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Austin, TX, USA.","DOI":"10.1145\/2207676.2208639"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"5501304","DOI":"10.1109\/LSENS.2022.3213529","article-title":"Robust multiobject tracking using mmwave radar-camera sensor fusion","volume":"6","author":"Sengupta","year":"2022","journal-title":"IEEE Sens. Lett."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/7\/2096\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T14:35:34Z","timestamp":1774622134000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/7\/2096"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":32,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["s26072096"],"URL":"https:\/\/doi.org\/10.3390\/s26072096","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,27]]}}}