{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T17:09:00Z","timestamp":1785431340586,"version":"3.56.0"},"reference-count":34,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","award":["24-SF-AI-01"],"award-info":[{"award-number":["24-SF-AI-01"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"award":["24-SF-AI-01"],"award-info":[{"award-number":["24-SF-AI-01"]}],"id":[{"id":"https:\/\/ror.org\/008nkqk13","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Gait analysis is an essential tool in clinical domains for diagnosing musculoskeletal disorders and evaluating rehabilitation, yet traditional marker-based systems are limited by high costs and spatial constraints. To overcome these challenges, this study proposes and evaluates a joint-level hybrid framework that integrates a single RGB camera with two shoe-mounted inertial measurement units (IMUs) to leverage their complementary strengths. The camera-based module estimates hip and knee sagittal joint angles using 3D pose estimation, where the DEAS optimization algorithm aligns estimated coordinates with a humanoid model, and an LSTM-based refinement network corrects hip angles by referencing more accurately estimated knee data. Simultaneously, the IMU-based module estimates sagittal ankle angles through kinematic chain relationships that combine camera-derived proximal joint information with IMU-measured foot orientation. Experimental validation with 11 healthy participants in a controlled laboratory environment demonstrates promising estimation performance, achieving an average mean absolute error (MAE) of 7.89\u00b0 and RMSE of 10.09\u00b0 on the held-out test set across sagittal hip, knee, and ankle angles. Leave-one-subject-out (LOSO) cross-validation of the LSTM correction model further confirmed its generalizability, yielding an average MAE of 6.40\u00b0 across bilateral hip angles. By accurately mitigating the trunk-inclination-induced overestimation of hip angles with a minimal sensor configuration (one camera and two IMUs), the proposed framework provides a practical and interpretable approach for portable lower limb gait analysis.<\/jats:p>","DOI":"10.3390\/s26123828","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T03:27:21Z","timestamp":1781666841000},"page":"3828","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Joint-Level Hybrid Framework for Gait Analysis Using Camera\u2013IMU Fusion and LSTM-Based Temporal Correction"],"prefix":"10.3390","volume":"26","author":[{"given":"Eunju","family":"Ha","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Seunghak Campus, Dong-A University, Busan 49315, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1343-5404","authenticated-orcid":false,"given":"Jong-Wook","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Seunghak Campus, Dong-A University, Busan 49315, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,16]]},"reference":[{"key":"ref_1","unstructured":"Whittle, M.W. (2014). Gait Analysis: An Introduction, Butterworth-Heinemann. [5th ed.]."},{"key":"ref_2","unstructured":"Baker, R. (2013). Measuring Walking: A Handbook of Clinical Gait Analysis, Mac Keith Press."},{"key":"ref_3","unstructured":"Perry, J., and Burnfield, J.M. (2010). Gait Analysis: Normal and Pathological Function, SLACK Incorporated. [2nd ed.]."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3362","DOI":"10.3390\/s140203362","article-title":"Gait Analysis Methods: An Overview of Wearable and Non-Wearable Systems, Highlighting Clinical Applications","volume":"14","year":"2014","journal-title":"Sensors"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1869","DOI":"10.1016\/j.jbiomech.2004.02.047","article-title":"Quantification of Human Motion: Gait Analysis\u2014Benefits and Limitations to Its Application to Clinical Problems","volume":"37","author":"Simon","year":"2004","journal-title":"J. Biomech."},{"key":"ref_6","first-page":"186","article-title":"Human movement analysis using stereophotogrammetry: Part 1: Theoretical background","volume":"21","author":"Cappozzo","year":"2005","journal-title":"Gait Posture"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/1743-0003-3-4","article-title":"Gait Analysis Methods in Rehabilitation","volume":"3","author":"Baker","year":"2006","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s40798-018-0139-y","article-title":"A Review of the Evolution of Vision-Based Motion Analysis and the Integration of Advanced Computer Vision Methods Towards Developing a Markerless System","volume":"4","author":"Colyer","year":"2018","journal-title":"Sports Med.-Open"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"110665","DOI":"10.1016\/j.jbiomech.2021.110665","article-title":"Concurrent Assessment of Gait Kinematics Using Marker-Based and Markerless Motion Capture","volume":"127","author":"Kanko","year":"2021","journal-title":"J. Biomech."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"20673","DOI":"10.1038\/s41598-021-00212-x","article-title":"The Accuracy of Several Pose Estimation Methods for 3D Joint Centre Localisation","volume":"11","author":"Needham","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_11","unstructured":"Bazarevsky, V., Grishchenko, I., Raveendran, K., Zhu, T., Zhang, F., and Grundmann, M. (2020). BlazePose: On-Device Real-Time Body Pose Tracking. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, C., Chen, Z., Bian, S., Yang, L., and Lu, C. (2022). HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhang, J., Zhang, Q., and Tao, D. (2022). ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation. Advances in Neural Information Processing Systems 35, Neural Information Processing Systems Foundation.","DOI":"10.52202\/068431-2795"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Viswakumar, A., Rajagopalan, V., Ray, T., and Parimi, C. (2019). Human Gait Analysis Using OpenPose. Proceedings of the 2019 Fifth International Conference on Image Information Processing (ICIIP), IEEE.","DOI":"10.1109\/ICIIP47207.2019.8985781"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Stenum, J., Rossi, C., and Roemmich, R.T. (2021). Two-Dimensional Video-Based Analysis of Human Gait Using Pose Estimation. PLoS Comput. Biol., 17.","DOI":"10.1371\/journal.pcbi.1008935"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"6891","DOI":"10.3390\/s140406891","article-title":"IMU-Based Joint Angle Measurement for Gait Analysis","volume":"14","author":"Seel","year":"2014","journal-title":"Sensors"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1109\/TBME.2012.2227317","article-title":"On-Shoe Wearable Sensors for Gait and Turning Assessment of Patients With Parkinson\u2019s Disease","volume":"60","author":"Mariani","year":"2013","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.gaitpost.2017.04.013","article-title":"Validity and Repeatability of Inertial Measurement Units for Measuring Gait Parameters","volume":"55","author":"Washabaugh","year":"2017","journal-title":"Gait Posture"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/j.gaitpost.2016.11.008","article-title":"25 Years of Lower Limb Joint Kinematics by Using Inertial and Magnetic Sensors: A Review of Methodological Approaches","volume":"51","author":"Picerno","year":"2017","journal-title":"Gait Posture"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1007\/978-3-030-01249-6_37","article-title":"Recovering Accurate 3D Human Pose in the Wild Using IMUs and a Moving Camera","volume":"Volume 11214","author":"Ferrari","year":"2018","journal-title":"Computer Vision\u2014ECCV 2018"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1594","DOI":"10.1007\/s11263-019-01270-5","article-title":"Real-Time Multi-Person Motion Capture from Multi-View Video and IMUs","volume":"128","author":"Malleson","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1007\/s11263-018-1118-y","article-title":"Fusing Visual and Inertial Sensors with Semantics for 3D Human Pose Estimation","volume":"127","author":"Gilbert","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Huang, Y., Kaufmann, M., Aksan, E., Black, M.J., Hilliges, O., and Pons-Moll, G. (2018). Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time. ACM Trans. Graph., 37.","DOI":"10.1145\/3272127.3275108"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kim, J. (2006). On the Global Convergence of Univariate-Dynamic Encoding Algorithm for Searches (uDEAS). Proceedings of the 2006 SICE-ICASE International Joint Conference, IEEE. Busan Exhibition & Convention Center-BEXCO.","DOI":"10.1109\/SICE.2006.314675"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"16","DOI":"10.5302\/J.ICROS.2026.25.0282","article-title":"A Correction Method for Monocular Camera-based Gait Joint Angle Estimation Using LSTM With Knee Joint Time-series Information","volume":"32","author":"Ha","year":"2026","journal-title":"J. Inst. Control Robot. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kim, J.-W., Choi, J.-Y., Ha, E.-J., and Choi, J.-H. (2023). Human Pose Estimation Using MediaPipe Pose and Optimization Method Based on a Humanoid Model. Appl. Sci., 13.","DOI":"10.3390\/app13042700"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wang, F., Liang, W., Afzal, H.M.R., Fan, A., Li, W., Dai, X., Liu, S., Hu, Y., Li, Z., and Yang, P. (2023). Estimation of Lower Limb Joint Angles and Joint Moments during Different Locomotive Activities Using the Inertial Measurement Units and a Hybrid Deep Learning Model. Sensors, 23.","DOI":"10.3390\/s23229039"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.gaitpost.2023.11.002","article-title":"Measuring Highly Accurate Foot Position and Angle Trajectories with Foot-Mounted IMUs in Clinical Practice","volume":"108","author":"Jocham","year":"2024","journal-title":"Gait Posture"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"108016","DOI":"10.1016\/j.compbiomed.2024.108016","article-title":"Integrating an LSTM Framework for Predicting Ankle Joint Biomechanics during Gait Using Inertial Sensors","volume":"170","author":"Xiang","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"17719","DOI":"10.1038\/s41598-022-22246-5","article-title":"Verification of Gait Analysis Method Fusing Camera-Based Pose Estimation and an IMU Sensor in Various Gait Conditions","volume":"12","author":"Yamamoto","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields","volume":"43","author":"Cao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Choi, J.-Y., Ha, E., Son, M., Jeon, J.-H., and Kim, J.-W. (2024). Human Joint Angle Estimation Using Deep Learning-Based Three-Dimensional Human Pose Estimation for Application in a Real Environment. Sensors, 24.","DOI":"10.3390\/s24123823"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Madgwick, S.O.H., Harrison, A.J.L., and Vaidyanathan, R. (2011). Estimation of IMU and MARG Orientation Using a Gradient Descent Algorithm. Proceedings of the 2011 IEEE International Conference on Rehabilitation Robotics, IEEE.","DOI":"10.1109\/ICORR.2011.5975346"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Trabassi, D., Castiglia, S.F., Bini, F., Marinozzi, F., Ajoudani, A., Lorenzini, M., Chini, G., Varrecchia, T., Ranavolo, A., and De Icco, R. (2024). Optimizing Rare Disease Gait Classification through Data Balancing and Generative AI: Insights from Hereditary Cerebellar Ataxia. Sensors, 24.","DOI":"10.3390\/s24113613"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3828\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T04:12:11Z","timestamp":1782187931000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/12\/3828"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,16]]},"references-count":34,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["s26123828"],"URL":"https:\/\/doi.org\/10.3390\/s26123828","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,16]]}}}