{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T05:16:53Z","timestamp":1788239813366,"version":"build-2803163510"},"reference-count":43,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,8,30]],"date-time":"2026-08-30T00:00:00Z","timestamp":1788048000000},"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","doi-asserted-by":"crossref","award":["62367005"],"award-info":[{"award-number":["62367005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"award":["62367005"],"award-info":[{"award-number":["62367005"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"publisher"}]},{"name":"China Railway Society","award":["7th edition"],"award-info":[{"award-number":["7th edition"]}]},{"DOI":"10.13039\/501100004775","name":"Natural Science Foundation of Gansu Province","doi-asserted-by":"crossref","award":["25JRRA847"],"award-info":[{"award-number":["25JRRA847"]}],"id":[{"id":"10.13039\/501100004775","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100009014","name":"Lanzhou Jiaotong University","doi-asserted-by":"crossref","award":["JGZ202503"],"award-info":[{"award-number":["JGZ202503"]}],"id":[{"id":"10.13039\/501100009014","id-type":"DOI","asserted-by":"crossref"}]},{"award":["JGZ202503"],"award-info":[{"award-number":["JGZ202503"]}],"id":[{"id":"https:\/\/ror.org\/03144pv92","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Lanzhou Jiaotong University Experimental Teaching Reform Project","award":["2026042"],"award-info":[{"award-number":["2026042"]}]},{"award":["2026042"],"award-info":[{"award-number":["2026042"]}],"id":[{"id":"https:\/\/ror.org\/03144pv92","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Augmented reality (AR) enhances the real world scene by overlaying virtual information onto it. Vision-based 3D tracking and registration is the key technology for ensuring the fusion of virtual and real content in monocular AR systems. Existing mainstream visual tracking and registration methods are susceptible to illumination variations, motion blur, target occlusion, and dynamic background interference in complex scenarios. They also suffer from low computational efficiency, cumulative pose errors, and insufficient stability, making them difficult to deploy on low power edge devices such as embedded systems and mobile terminals. To address these issues, this paper proposes a lightweight monocular AR 3D tracking and registration method that integrates ORB-FREAK features, mismatching outlier filtering, background weighted mean shift, and template-based relocalization. The method does not rely on depth sensors or neural network inference, enabling efficient and accurate lightweight pose estimation. Specifically, we first combine the ORB (Oriented FAST and Rotated BRIEF) descriptor with the FREAK (Fast Retina Keypoint) algorithm for feature detection and initial matching. Hamming distance is used for coarse filtering of mismatched point pairs, and an ascending sort combined with an iterative sequential sampling strategy is applied to solve the optimal homography matrix, significantly improving the accuracy and efficiency of matrix estimation. Then, distance constraints among feature points are imposed on the target registration region to optimize the selection, and camera pose is computed based on the matching between 2D feature points and their corresponding 3D spatial coordinates, eliminating the error accumulation problem of conventional algorithms. Real-time feature matching is further used to correct the optical flow tracking sequence and camera pose, ensuring the continuity of the AR tracking process. Finally, a background weighted mean shift algorithm is introduced to narrow the feature detection range and suppress background interference, complemented by a template-matching relocalization module and a dynamic model update strategy, which effectively enhance the robustness of continuous tracking and registration under complex conditions. Experimental results demonstrate that, in extreme scenarios such as low light conditions, high speed motion, and occlusion, the proposed method achieves AR 3D tracking and registration success rates of 86.7%, 82.3%, and 78.5%, respectively. It exhibits superior performance in pose estimation accuracy and anti-interference capability in complex environments, with significantly reduced computational overhead. Moreover, it can achieve robust and continuous AR 3D tracking and registration on low power edge devices, effectively adapting to demanding AR application scenarios and providing reliable technical support for lightweight AR applications.<\/jats:p>","DOI":"10.3390\/s26175509","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T05:55:56Z","timestamp":1788155756000},"page":"5509","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An AR 3D Tracking and Registration Method That Integrates Optical Flow Tracking and Mean Shift"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7244-8934","authenticated-orcid":false,"given":"Jiu","family":"Yong","sequence":"first","affiliation":[{"name":"The School of Electronic and Information Engineering, Lanzhou Jiaotong Univeristy, Lanzhou 730070, China"},{"name":"School of Computer Science, Peking University, Beijing 100871, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8837-1815","authenticated-orcid":false,"given":"Xiaomei","family":"Lei","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin 300072, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[{"name":"The School of Electronic and Information Engineering, Lanzhou Jiaotong Univeristy, Lanzhou 730070, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1109\/TMRB.2024.3503999","article-title":"AR and MR in dentistry: Developments, applications, and prospects","volume":"7","author":"Ahmad","year":"2025","journal-title":"IEEE Trans. Med. Robot. Bionics"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1018","DOI":"10.1016\/j.jmapro.2025.07.063","article-title":"Review of augmented reality maintenance and registration in aerospace industry","volume":"151","author":"Zhao","year":"2025","journal-title":"J. Manuf. Process."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"4417","DOI":"10.1109\/TMI.2025.3577759","article-title":"Toward reliable AR-guided surgical navigation: Interactive deformation modeling with data-driven biomechanics and prompts","volume":"44","author":"Han","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"6497","DOI":"10.1109\/TVCG.2024.3518258","article-title":"EVD surgical guidance with retro-reflective tool tracking and spatial reconstruction using head-mounted augmented reality device","volume":"31","author":"Li","year":"2025","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.jmsy.2025.08.019","article-title":"AI-aided automated AR-assisted assembly instruction authoring and generation method","volume":"83","author":"Lin","year":"2025","journal-title":"J. Manuf. Syst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"122331","DOI":"10.1016\/j.eswa.2023.122331","article-title":"Self-training based augmented reality for robust 3D object registration and task assistance","volume":"238","author":"Park","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"132978","DOI":"10.1016\/j.eswa.2026.132978","article-title":"Scene-level markerless registration for industrial augmented assembly system: Leveraging multi-object joint pose optimization","volume":"329","author":"Sun","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2900","DOI":"10.1109\/TMC.2024.3504960","article-title":"Visualizing the smart environment in AR: An approach based on visual geometry matching","volume":"24","author":"Xia","year":"2025","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1016\/j.jmsy.2025.04.013","article-title":"Automatic 3D inspection method for AR-assisted assembly based on virtual-to-real registration","volume":"80","author":"Zhang","year":"2025","journal-title":"J. Manuf. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"103168","DOI":"10.1016\/j.aei.2025.103168","article-title":"Integrated registration and utility of mobile AR human-machine collaborative assembly in rail transit","volume":"65","author":"Yong","year":"2025","journal-title":"Adv. Eng. Inform."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"4647","DOI":"10.1109\/TVCG.2026.3680634","article-title":"EasyREG: Easy depth-based markerless registration and tracking using augmented reality device for surgical guidance","volume":"32","author":"Yang","year":"2026","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"101957","DOI":"10.1016\/j.rcim.2020.101957","article-title":"Markerless cooperative augmented reality-based smart manufacturing double-check system: Case of safe PCBA inspection following automatic optical inspection","volume":"64","author":"Runji","year":"2020","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101950","DOI":"10.1016\/j.aei.2023.101950","article-title":"A marker-less assembly stage recognition method based on corner feature","volume":"56","author":"Hong","year":"2023","journal-title":"Adv. Eng. Inform."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1007\/s11340-026-01276-4","article-title":"A DMD-based adaptive modulation method for high dynamic range imaging in high-glare environments","volume":"66","author":"Guan","year":"2026","journal-title":"Exp. Mech."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1007\/s11340-026-01286-2","article-title":"Event-based method for high speed 3D deformation measurement under extreme illumination conditions","volume":"66","author":"Bian","year":"2026","journal-title":"Exp. Mech."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wu, X., Yu, Y., and Lyu, X. (2025). EAG3R: Event-augmented 3D geometry estimation for dynamic and extreme-lighting scenes. Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS 2025), Neural Information Processing Systems Foundation, Inc. (NeurIPS).","DOI":"10.52202\/085713-2457"},{"key":"ref_17","unstructured":"Shen, W. (2026). E-TraMamba: A new paradigm for efficient long-term 3D feature tracking with event cameras. IEEE Robot. Autom. Lett., Available online: https:\/\/arxiv.org\/pdf\/2607.02866."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"106195","DOI":"10.1016\/j.cie.2019.106195","article-title":"Augmented reality in support of intelligent manufacturing: A systematic literature review","volume":"140","author":"Egger","year":"2020","journal-title":"Comput. Ind. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"106585","DOI":"10.1016\/j.cie.2020.106585","article-title":"Deep learning-based mobile augmented reality for task assistance using 3D spatial mapping and snapshot-based RGB-D data","volume":"146","author":"Park","year":"2020","journal-title":"Comput. Ind. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1016\/j.jmsy.2020.12.017","article-title":"Fully convolutional network-based registration for augmented assembly systems","volume":"61","author":"Li","year":"2021","journal-title":"J. Manuf. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2516110","DOI":"10.1109\/TIM.2021.3120377","article-title":"Reliable hybrid mixture model for generalized point set registration","volume":"70","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"6825","DOI":"10.1109\/TII.2022.3189428","article-title":"Integrated registration and occlusion handling based on deep learning for augmented-reality-assisted assembly instruction","volume":"19","author":"Li","year":"2023","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"119098","DOI":"10.1016\/j.eswa.2022.119098","article-title":"CMDGAT: Knowledge extraction and retention based continual graph attention network for point cloud registration","volume":"214","author":"Zaman","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1504\/IJWGS.2022.121960","article-title":"Survey on tracking and registration technology for mobile augmented reality","volume":"18","author":"Yang","year":"2022","journal-title":"Int. J. Wirel. Grid Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"15281","DOI":"10.1038\/s41598-024-65204-z","article-title":"Augmented reality navigation method based on image segmentation and sensor tracking registration technology","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"04TR02","DOI":"10.1088\/1361-6560\/acaf23","article-title":"Visualization, Registration and Tracking Techniques for Augmented Reality Guided Surgery: A Review","volume":"68","author":"Ma","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","article-title":"ORB-SLAM3: An accurate open-source library for visual, visual-inertial, and multimap SLAM","volume":"37","author":"Campos","year":"2021","journal-title":"IEEE Trans. Robot."},{"key":"ref_28","first-page":"2054005:1","article-title":"A SLAM-based mobile augmented reality tracking registration algorithm","volume":"34","author":"Liu","year":"2020","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1016\/j.vrih.2020.01.004","article-title":"Object registration using an RGB-D camera for complex product augmented assembly guidance","volume":"2","author":"Yang","year":"2020","journal-title":"Virtual Real. Intell. Hardw."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Tareen, S.A.K., and Saleem, Z. (2018, January 3\u20134). A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK. Proceedings of the 2018 International Conference on Computing, Mathematics and Engineering Technologies (iCoMET), Sukkur, Pakistan.","DOI":"10.1109\/ICOMET.2018.8346440"},{"key":"ref_31","unstructured":"Ma, S.D., and Zhang, Z.Y. (1998). Computer Vision: Computational Theory and Algorithm Foundation, Science Press."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Lindenberger, P., Sarlin, P.E., and Pollefeys, M. (2023, January 1\u20136). LightGlue: Local feature matching at light speed. Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., Detone, D., and Malisiewicz, T. (2020, January 13\u201319). SuperGlue: Learning feature matching with graph neural networks. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Sun, J., Shen, Z., and Wang, Y. (2021, January 19\u201325). LoFTR: Detector-free local feature matching with transformers. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Online.","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Wen, B., Yang, W., and Kautz, J. (2024, January 17\u201321). FoundationPose: Unified 6D pose estimation and tracking of novel objects. Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"ref_36","unstructured":"Lin, Y.C., Florence, P., and Barron, J.T. (October, January 27). iNeRF: Inverting neural radiance fields for pose estimation. Proceedings of the 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1109\/TPAMI.2018.2884990","article-title":"A region-based gauss-newton approach to real-time monocular multiple object tracking","volume":"41","author":"Tjaden","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"89431","DOI":"10.1109\/ACCESS.2022.3199350","article-title":"Real-time dynamic SLAM algorithm based on deep learning","volume":"10","author":"Su","year":"2022","journal-title":"IEEE Access"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2692","DOI":"10.1109\/LRA.2022.3144795","article-title":"ART-SLAM: Accurate real-time 6DoF LiDAR SLAM","volume":"7","author":"Frosi","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zhang, A., Wang, Y., Peng, H., Zhang, Q., Sun, M., Yao, P., and Xu, R.X. (2026). A smart projective imaging and navigation system for oral and maxillofacial surgery. IEEE Trans. Biomed. Eng., Early Access.","DOI":"10.1109\/TBME.2026.3687733"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"104178","DOI":"10.1016\/j.cag.2025.104178","article-title":"3D medical model registration using scale-invariant coherent point drift algorithm for AR","volume":"127","author":"Zhang","year":"2025","journal-title":"Comput. Graph."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"105561","DOI":"10.1016\/j.robot.2026.105561","article-title":"Uncertainty-aware monocular 6DoF pose tracking system of small objects for AR-assisted industrial assembly","volume":"204","author":"Zhao","year":"2026","journal-title":"Robot. Auton. Syst."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"10014","DOI":"10.1109\/TASE.2026.3695137","article-title":"LA-SLAM for laparoscopic navigation with pose estimation and 3D surface reconstruction","volume":"23","author":"Zhang","year":"2026","journal-title":"IEEE Trans. Autom. Sci. Eng."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/17\/5509\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T04:26:33Z","timestamp":1788236793000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/17\/5509"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,30]]},"references-count":43,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26175509"],"URL":"https:\/\/doi.org\/10.3390\/s26175509","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,30]]}}}