{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T14:58:30Z","timestamp":1790866710163,"version":"4.1.0"},"reference-count":55,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Biomechanical feedback can improve sports technique, but the 3D motion capturing gold standards typically used to generate such feedback are rarely available in everyday training. This study evaluates how the choice of pose estimation model affects automated movement analysis of the double side kick in Pointfighting, Kickboxing using ordinary 2D side-view video. In doing so, the study aims to determine whether advances in pose-estimation models translate into meaningful improvements in complete, sport-specific movement-analysis systems under realistic training conditions. The analysis compared MoveNet, YOLO11x-Pose, ViTPose-L, and RTMPose-L on 27 videos recorded under varying lighting conditions. Seventeen movement characteristics extracted from the videos were compared with 3D motion-capture measurements of the same kicks. Friedman tests with Wilcoxon signed-rank post-hoc tests showed that model choice significantly affected phase-duration errors (p&lt;0.01, Kendall\u2019s W=0.150) and femur-angle errors (p&lt;0.01, Kendall\u2019s W=0.174), but not leg-spreading angles or distance- and height-based characteristics. ViTPose-L achieved the lowest median errors for phase durations (0.043 s, IQR 0.035 to 0.062 s), femur angles (6.95\u00b0, IQR 4.35 to 11.65\u00b0), and leg-spreading angles (6.22\u00b0, IQR 5.08 to 10.04\u00b0), while RTMPose-L had the lowest median error for distance- and height-based characteristics (6.09 percentage points, IQR 3.84 to 9.10). Bland\u2013Altman analysis showed generally small systematic biases, but acceptable agreement with the 3D reference system was achieved only for a small subset of the evaluated characteristics. The runtime benchmark, performed on the tested local hardware, further demonstrated substantial differences in computational efficiency, with mean processing speeds ranging from 6.50 \u00b1 0.10 FPS for ViTPose-L to 66.87 \u00b1 0.36 FPS for MoveNet. These findings indicate that, for 2D technique analysis of rapid sports movements from side-view recordings that meet minimum quality requirements, ViTPose-L and RTMPose-L are preferable when accuracy and keypoint completeness are prioritized, whereas MoveNet is preferable when runtime performance on comparable hardware is the main requirement. Therefore, the choice of pose-estimation model is strongly use-case dependent, and automated 2D analysis should be interpreted as approximate feedback for selected characteristics rather than precise individual-level biomechanical measurement.<\/jats:p>","DOI":"10.3390\/s26195997","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T14:23:56Z","timestamp":1790864636000},"page":"5997","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Validation of Pose Estimation Models for Automated Kickboxing Technique Analysis Using 2TRAX3"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7918-0094","authenticated-orcid":false,"given":"Samir","family":"Duvelek","sequence":"first","affiliation":[{"name":"Research Group for Industrial Software (INSO), Vienna University of Technology, 1040 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7099-2576","authenticated-orcid":false,"given":"Dominik Peter","family":"Hoelbling","sequence":"additional","affiliation":[{"name":"Software and Digital Systems Engineering, University of Applied Sciences Wiener Neustadt (FHWN), Biotech Campus Tulln, Konrad Lorenz Stra\u00dfe 10, 3430 Tulln, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roland","family":"Breiteneder","sequence":"additional","affiliation":[{"name":"Institute of Software Engineering and Artificial Intelligence, TU Graz, Inffeldgasse 16b\/II, 8010 Graz, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6056-5853","authenticated-orcid":false,"given":"Benedikt","family":"Mitter","sequence":"additional","affiliation":[{"name":"Research Group for Industrial Software (INSO), Vienna University of Technology, 1040 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0088-9140","authenticated-orcid":false,"given":"Ren\u00e9","family":"Baranyi","sequence":"additional","affiliation":[{"name":"Research Group for Industrial Software (INSO), Vienna University of Technology, 1040 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Grechenig","sequence":"additional","affiliation":[{"name":"Research Group for Industrial Software (INSO), Vienna University of Technology, 1040 Vienna, Austria"},{"name":"RISE Institute of Technology (RIT), SSS District, Ongole 515134, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1080\/026404102320675657","article-title":"Technique Analysis in Sports: A Critical Review","volume":"20","author":"Lees","year":"2002","journal-title":"J. Sports Sci."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ouergui, I., Delleli, S., Bouassida, A., Bouhlel, E., Chaabene, H., Ardig\u00f2, L.P., and Franchini, E. (2021). Technical\u2013Tactical Analysis of Small Combat Games in Male Kickboxers: Effects of Varied Number of Opponents and Area Size. BMC Sports Sci. Med. Rehabil., 13.","DOI":"10.1186\/s13102-021-00391-0"},{"key":"ref_3","first-page":"11","article-title":"The Effectiveness of Kickboxing Techniques and Its Relation to Fights Won by Knockout","volume":"16","author":"Rydzik","year":"2020","journal-title":"Arch. Budo"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1080\/24748668.2021.1920314","article-title":"Exploration of Martial Arts Kick Initiation Actions and Telegraphs","volume":"21","author":"Hoelbling","year":"2021","journal-title":"Int. J. Perform. Anal. Sport"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/S1440-2440(99)80003-6","article-title":"Biomechanics: An Integral Part of Sport Science and Sport Medicine","volume":"2","author":"Elliott","year":"1999","journal-title":"J. Sci. Med. Sport"},{"key":"ref_6","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_7","doi-asserted-by":"crossref","first-page":"241","DOI":"10.47197\/retos.v0i32.56072","article-title":"Application of Motion Capture Technology for Sport Performance Analysis","volume":"32","author":"Pueo","year":"2017","journal-title":"Retos"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Se\u00e7kin, A.\u00c7., Ate\u015f, B., and Se\u00e7kin, M. (2023). Review on Wearable Technology in Sports: Concepts, Challenges and Opportunities. Appl. Sci., 13.","DOI":"10.3390\/app131810399"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Worsey, M.T.O., Espinosa, H.G., Shepherd, J.B., and Thiel, D.V. (2019). Inertial Sensors for Performance Analysis in Combat Sports: A Systematic Review. Sports, 7.","DOI":"10.3390\/sports7010028"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Xue, H., Han, C., and Zhu, D. (2025). Limb Biomechanics in Combat Sports: Insights from Wearable Sensor Technology. Front. Bioeng. Biotechnol., 13.","DOI":"10.3389\/fbioe.2025.1663592"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Pezenka, L., and Wirth, K. (2025). Reliability of a Low-Cost Inertial Measurement Unit (IMU) to Measure Punch and Kick Velocity. Sensors, 25.","DOI":"10.3390\/s25020307"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1080\/02640414.2016.1164333","article-title":"Kinematic Analysis of the Double Side Kick in Pointfighting, Kickboxing","volume":"35","author":"Preuschl","year":"2017","journal-title":"J. Sports Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1186\/s40798-025-00953-3","article-title":"The Application of Deep Learning Human Pose Estimation in Sport: A Systematic Review","volume":"11","author":"Aulton","year":"2025","journal-title":"Sports Med.-Open"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Badiola-Bengoa, A., and Mendez-Zorrilla, A. (2021). A Systematic Review of the Application of Camera-Based Human Pose Estimation in the Field of Sport and Physical Exercise. Sensors, 21.","DOI":"10.3390\/s21185996"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lahkar, B.K., Muller, A., Dumas, R., Reveret, L., and Robert, T. (2022). Accuracy of a Markerless Motion Capture System in Estimating Upper Extremity Kinematics During Boxing. Front. Sports Act. Living, 4.","DOI":"10.3389\/fspor.2022.939980"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1007\/s10439-020-02569-y","article-title":"Validity of Using Automated Two-Dimensional Video Analysis to Measure Continuous Sagittal Plane Running Kinematics","volume":"49","author":"Peebles","year":"2021","journal-title":"Ann. Biomed. Eng."},{"key":"ref_17","first-page":"163","article-title":"Two-Dimensional Video Analysis Is Comparable to 3D Motion Capture in Lower Extremity Movement Assessment","volume":"12","author":"Schurr","year":"2017","journal-title":"Int. J. Sports Phys. Ther."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1007\/s10926-021-10002-x","article-title":"Towards the Use of 2D Video-Based Markerless Motion Capture to Measure and Parameterize Movement during Functional Capacity Evaluation","volume":"31","author":"Remedios","year":"2021","journal-title":"J. Occup. Rehabil."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1080\/14763141.2022.2137425","article-title":"Validation of pitchAITM Markerless Motion Capture Using Marker-Based 3D Motion Capture","volume":"24","author":"Dobos","year":"2025","journal-title":"Sports Biomech."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"119","DOI":"10.18280\/ts.390111","article-title":"Comparative Analysis of OpenPose, PoseNet, and MoveNet Models for Pose Estimation in Mobile Devices","volume":"39","author":"Jo","year":"2022","journal-title":"Trait. Signal"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"38767","DOI":"10.1038\/s41598-025-22626-7","article-title":"Assessment of Monocular Human Pose Estimation Models for Clinical Movement Analysis","volume":"15","author":"Rode","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Moreira, R., Teixeira, S., Fialho, R., Miranda, A., Lima, L.D.B., Carvalho, M.B., Alves, A.B., Bastos, V.H.V., and Teles, A.S. (2024). Validity Analysis of Monocular Human Pose Estimation Models Interfaced with a Mobile Application for Assessing Upper Limb Range of Motion. Sensors, 24.","DOI":"10.3390\/s24247983"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1080\/24748668.2020.1774730","article-title":"Sequential Action, Power Generation and Balance Characteristics of a Martial Arts Kick Combination","volume":"20","author":"Hoelbling","year":"2020","journal-title":"Int. J. Perform. Anal. Sport"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1080\/14763141.2020.1795237","article-title":"A Kinematic Model for Assessment of Hip Joint Range-of-Motion in Fast Sport Movements Using Spreading Angles","volume":"22","author":"Baca","year":"2023","journal-title":"Sports Biomech."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Memmert, D. (2025). Digitaler Plattform- und Systembau: \u00dcber Spezifika, Evolution und IT-Architekturen in Sport und Rehabilitation. Digitalisierung und Innovation im Sport und in der Sportwissenschaft, Springer Spektrum.","DOI":"10.1007\/978-3-662-70475-2"},{"key":"ref_26","unstructured":"Hoelbling, D., Grafinger, M., Baca, A., and Dabnichki, P. (2020, January 5\u20136). The Flexibility Trainer: Feasibility Analysis, Prototype- and Test Station Development for a Sports Device for Hip-Joint Flexibility and Strength Enhancement. Proceedings of the 8th International Conference on Sport Sciences Research and Technology Support, Online."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Baranyi, R., Hirber, C., Roehrling, L., Aigner, C., Hoelbling, D., Hoerner, W., and Grechenig, T. (2024). Virtual Reality-Powered Wrist Therapy: Developing a Therapist-Driven Exit-the-Room Serious Game with Hand Gesture Interactions. Appl. Sci., 14.","DOI":"10.3390\/app14114780"},{"key":"ref_28","unstructured":"Jiang, T., Lu, P., Zhang, L., Ma, N., Han, R., Lyu, C., Li, Y., and Chen, K. (2023). RTMPose: Real-Time Multi-Person Pose Estimation Based on MMPose. arXiv."},{"key":"ref_29","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 European Conference on Computer Vision (ECCV), Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_30","unstructured":"(2018). Ergonomics of Human-System Interaction\u2014Part 11: Usability: Definitions and Concepts (Standard No. ISO 9241-11:2018)."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Duvelek, S., H\u00f6lbling, D., Baranyi, R., Breiteneder, R., Pinter, K., and Grechenig, T. (2023, January 16\u201317). 2Trax3: Raising Accessibility and Everyday Use of Automatic Motion Analysis in (Combat) Sports via ML Enhanced 2D to 3D Estimation Algorithms. Proceedings of the 11th International Conference on Sport Sciences Research and Technology Support (icSPORTS), Rome, Italy.","DOI":"10.5220\/0012165200003587"},{"key":"ref_32","first-page":"1","article-title":"Statistical Comparisons of Classifiers over Multiple Data Sets","volume":"7","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1080\/01621459.1937.10503522","article-title":"The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance","volume":"32","author":"Friedman","year":"1937","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual Comparisons by Ranking Methods","volume":"1","author":"Wilcoxon","year":"1945","journal-title":"Biom. Bull."},{"key":"ref_35","first-page":"65","article-title":"A Simple Sequentially Rejective Multiple Test Procedure","volume":"6","author":"Holm","year":"1979","journal-title":"Scand. J. Stat."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/S0140-6736(86)90837-8","article-title":"Statistical Methods for Assessing Agreement between Two Methods of Clinical Measurement","volume":"1","author":"Bland","year":"1986","journal-title":"Lancet"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Baldinger, M., Reimer, L.M., and Senner, V. (2025). Influence of the Camera Viewing Angle on OpenPose Validity in Motion Analysis. Sensors, 25.","DOI":"10.3390\/s25030799"},{"key":"ref_38","unstructured":"FFmpeg Developers (2026, July 14). FFmpeg, Version 8.0.1; FFmpeg Project. Available online: https:\/\/ffmpeg.org\/."},{"key":"ref_39","unstructured":"Votel, R., and Li, N. (2026, July 09). Next-Generation Pose Detection with MoveNet and TensorFlow.js. TensorFlow Blog, Available online: https:\/\/blog.tensorflow.org\/2021\/05\/next-generation-pose-detection-with-movenet-and-tensorflowjs.html."},{"key":"ref_40","unstructured":"Jocher, G., and Qiu, J. (2026, July 13). Ultralytics YOLO11. Available online: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"38571","DOI":"10.52202\/068431-2795","article-title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","volume":"35","author":"Xu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_42","unstructured":"Hetzner Online GmbH (2026, July 13). Dedicated GPU Server GEX44. Available online: https:\/\/www.hetzner.com\/pressroom\/new-gpu-server\/."},{"key":"ref_43","unstructured":"OpenMMLab (2026, July 29). RTMPose Body8-COCO Model Configurations. MMPose Model Zoo, Available online: https:\/\/github.com\/open-mmlab\/mmpose\/blob\/main\/configs\/body_2d_keypoint\/rtmpose\/body8\/rtmpose_body8-coco.md."},{"key":"ref_44","unstructured":"Lyu, C., Zhang, W., Huang, H., Zhou, Y., Wang, Y., Liu, Y., Zhang, S., and Chen, K. (2022). RTMDet: An Empirical Study of Designing Real-Time Object Detectors. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1177\/096228029900800204","article-title":"Measuring agreement in method comparison studies","volume":"8","author":"Bland","year":"1999","journal-title":"Stat. Methods Med. Res."},{"key":"ref_46","unstructured":"Khanam, R., and Hussain, M. (2024). YOLOv11: An Overview of the Key Architectural Enhancements. arXiv."},{"key":"ref_47","unstructured":"Gozlan, Y., Falisse, A., Uhlrich, S., Gatti, A., Black, M., Hicks, J., Delp, S., and Chaudhari, A. (March, January 28). OpenCapBench: A Benchmark to Bridge Pose Estimation and Biomechanics. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"e12995","DOI":"10.7717\/peerj.12995","article-title":"Applications and Limitations of Current Markerless Motion Capture Methods for Clinical Gait Biomechanics","volume":"10","author":"Wade","year":"2022","journal-title":"PeerJ"},{"key":"ref_49","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_50","doi-asserted-by":"crossref","first-page":"1847","DOI":"10.1080\/02640414.2024.2415233","article-title":"Validity and Reliability of Trunk and Lower-Limb Kinematics during Squatting, Hopping, Jumping and Side-Stepping Using OpenCap Markerless Motion Capture Application","volume":"42","author":"Lima","year":"2024","journal-title":"J. Sports Sci."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"e14693","DOI":"10.1111\/sms.14693","article-title":"Automating Video-Based Two-Dimensional Motion Analysis in Sport? Implications for Gait Event Detection, Pose Estimation, and Performance Parameter Analysis","volume":"34","author":"Mundt","year":"2024","journal-title":"Scand. J. Med. Sci. Sports"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"6849","DOI":"10.21105\/joss.06849","article-title":"Sports2D: Compute 2D Human Pose and Angles from a Video or a Webcam","volume":"9","author":"Pagnon","year":"2024","journal-title":"J. Open Source Softw."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Prusina, T., Beni\u0107, J., \u0160everdija, D., and Matijevi\u0107, D. (2025). Multi-Person 2D Human Pose Estimation: A Benchmark for Real-Time Applications. Res. Sq., Preprint.","DOI":"10.21203\/rs.3.rs-7157503\/v1"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Pagnon, D., Domalain, M., and Reveret, L. (2022). Pose2Sim: An End-to-End Workflow for 3D Markerless Sports Kinematics\u2014Part 2: Accuracy. Sensors, 22.","DOI":"10.3390\/s22072712"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Uhlrich, S.D., Falisse, A., Kidzi\u0144ski, \u0141., Muccini, J., Ko, M., Chaudhari, A.S., Hicks, J.L., and Delp, S.L. (2023). OpenCap: Human Movement Dynamics from Smartphone Videos. PLoS Comput. Biol., 19.","DOI":"10.1371\/journal.pcbi.1011462"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/5997\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T14:33:45Z","timestamp":1790865225000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/5997"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":55,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26195997"],"URL":"https:\/\/doi.org\/10.3390\/s26195997","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]}}}