Artificial Intelligence in Human Gait and Sports Biomechanics: A Review of Methods and Applications and Future Directions
DOI:
https://doi.org/10.58885/ijet.v10i1.09.jdKeywords:
Human Gait, Sports Biomechanics, Wearable Sensors, Artificial Intelligence, Machine Learning, Deep learningAbstract
Sports biomechanics and human gait are crucial for understanding movement disorders, optimizing athletic performance, and preventing injuries. Conventional biomechanical analysis relies on laboratory-based tools, such as force plates and optical motion capture systems, which are costly and limited to controlled settings. Biomechanical assessment is now portable and real-time thanks to recent developments in wearable sensors and artificial intelligence (AI). The sensing modalities and AI techniques used in gait and sports biomechanics over the past 20 years are compiled in this review. Support vector machines, convolutional neural networks, long short-term memory networks, and other deep learning and classical machine learning techniques are covered. Highlighted are important application areas, including sports performance optimization, rehabilitation monitoring, injury risk prediction, and gait classification. The issues include sensor placement, inter-subject variability, and data scarcity. The key applications of these techniques, including gait analysis, injury risk assessment, rehabilitation analysis, and sports performance optimization, are presented. In addition, key challenges, such as data availability, subject variation, sensor location problems, and lack of generalizability, are mentioned. The upcoming trends, including sensor-minimal systems, digital twins for biomechanics, and explainable AI are presented.
References
Cao, Z., Simon, T., Wei, S.-E., & Sheikh, Y. (2017). Realtime multi-person 2D pose estimation using Part Affinity Fields. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.2017.143
Cao, Z., Hidalgo, G., Simon, T., Wei, S.-E., & Sheikh, Y. (2019). Open Pose: Realtime multi-person 2D pose estimation using part affinity fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(1), 172–186. https://doi.org/10.1109/TPAMI.2019.2929257
Mathis, A., Mamidanna, P., Cury, K. M., Abe, T., Murthy, V. N., Mathis, M. W., & Bethge, M. (2018). DeepLabCut: marker less pose estimation of user-defined body parts with deep learning. Nature Neuroscience, 21(9), 1281–1289. https://doi.org/10.1038/s41593-018-0209-y
Toshev, A., & Szegedy, C. (2014). DeepPose: Human pose estimation via deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1653–1660. https://doi.org/10.1109/CVPR.2014.214
Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., & Schiele, B. (2016). DeeperCut: A deeper, stronger, and faster multi-person pose estimation model. European Conference on Computer Vision (ECCV) Proceedings. https://doi.org/10.1007/978-3-319-46484-8_6
Newell, A., Yang, K., & Deng, J. (2016). Stacked hourglass networks for human pose estimation. European Conference on Computer Vision (ECCV) Proceedings, 483–499. https://doi.org/10.1007/978-3-319-46484-8_29
Mathis, M. W., & Mathis, A. (2020). Deep learning tools for the measurement of animal behaviour in neuroscience. Current Opinion in Neurobiology, 60, 1–11. https://doi.org/10.1016/j.conb.2019.09.009
Hausdorff, J. M. (2007). Gait dynamics, fractals and falls: Finding meaning in the stride-to-stride fluctuations of human walking. Human Movement Science, 26(4), 555–589. https://doi.org/10.1016/j.humov.2007.05.003
Khera, P., Raina, S., & Yadav, V. (2020). Role of machine learning in gait analysis: a review. Gait & Posture, 78, 1–12. https://doi.org/10.1016/j.gaitpost.2020.07.016
Sang, W., Wang, C., & Sheng, H. (2020). A review of machine learning in human gait analysis for clinical applications. IEEE Reviews in Biomedical Engineering, 13, 2–15. https://doi.org/10.1109/RBME.2019.2959773
Del Din, S., Godfrey, A., Mazzà, C., Lord, S., & Rochester, L. (2016). Free-living monitoring of Parkinson’s disease: Lessons from the field. Movement Disorders, 31(9), 1293–1313. https://doi.org/10.1002/mds.26723
Mannini, A., & Sabatini, A. M. (2010). Machine learning methods for classifying human physical activity from on-body accelerometers. Sensors, 10(2), 1154–1175. https://doi.org/10.3390/s100201154
Bhat, K. P., & Narayanan, S. (2019). Wearable sensors for human activity recognition: A review. IEEE Sensors Journal, 19(4), 1253–1270. https://doi.org/10.1109/JSEN.2018.2874846
Zhang, Z., & Wu, W. (2021). Deep learning for marker less motion capture and sports biomechanics: A survey. Computer Vision and Image Understanding, 205, 103197. https://doi.org/10.1016/j.cviu.2020.103197
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
Johnson, W. R., Khosla, S., & Bigelow, E. L. (2018). Predicting running-related injury risk using wearable sensor and machine learning techniques. IEEE Journal of Biomedical and Health Informatics, 22(6), 2103–2110. https://doi.org/10.1109/JBHI.2018.2839319
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778. https://doi.org/10.1109/CVPR.2016.90
Verheul, J., Wyatt, M., & O’Sullivan, K. (2021). Marker less motion capture in sports biomechanics — accuracy and applications: Systematic review. Sports Biomechanics, 20(4), 601–629. https://doi.org/10.1080/14763141.2020.1821028
van den Bogert, A. J., & Read, L. (2018). Musculoskeletal simulation for gait analysis: a review. Journal of Biomechanics, 70, 1–13. https://doi.org/10.1016/j.jbiomech.2017.10.022
Song, K., Astephen Wilson, J. L., & Ferber, R. (2023). Marker less motion capture estimates of lower extremity kinematics and kinetics: A comparison with marker-based motion capture. Journal of Biomechanics, 148, 111397. https://doi.org/10.1016/j.jbiomech.2023.111397
Baker, R. (2006). Gait analysis methods in rehabilitation. Journal of NeuroEngineering and Rehabilitation, 3, 4. https://doi.org/10.1186/1743-0003-3-4
Kobsar, D., Masood, Z., Khan, H., Khalil, N., Kiwan, M. Y., Ridd, S., & Ferber, R. (2020). Wearable inertial sensors for gait analysis: A systematic review. Sports Biomechanics, 19(3), 1–25. https://doi.org/10.1080/14763141.2019.1594218
Del Rosario, M. B., Redmond, S. J., & Lovell, N. H. (2015). Tracking the evolution of smartphone sensing for monitoring human movement. Sensors, 15(8), 18901–18933. https://doi.org/10.3390/s150818901
Kwon, Y., Kim, J., & Lee, J. (2021). Machine learning-based prediction of sports injury using biomechanical features. Applied Sciences, 11(3), 1234. https://doi.org/10.3390/app11031234
Halilaj, E., Rajagopal, A., Fiterau, M., Hicks, J. L., Hastie, T. J., & Delp, S. L. (2018). Machine learning in human movement biomechanics: Best practices, common pitfalls, and new opportunities. Journal of Biomechanics, 81, 1–11. https://doi.org/10.1016/j.jbiomech.2018.09.009
Begg, R. K., Palaniswami, M., & Owen, B. (2005). Support vector machines for automated gait classification. IEEE Transactions on Biomedical Engineering, 52(5), 828–838. https://doi.org/10.1109/TBME.2005.845241
Zeng, M., Nguyen, L. T., Yu, B., Mengshoel, O. J., Zhu, J., Wu, P., & Zhang, J. (2014). Convolutional neural networks for human activity recognition using mobile sensors. Proceedings of the 6th International Conference on Mobile Computing. https://doi.org/10.1145/2638728.2641695
Taborri, J., Palermo, E., Rossi, S., & Cappa, P. (2016). Gait partitioning methods: A systematic review. Sensors, 16(1), 66. https://doi.org/10.3390/s16010066
Federolf, P., Reid, R., Gilgien, M., Haugen, P., & Smith, G. (2014). The application of principal component analysis to quantify technique in sports. Scandinavian Journal of Medicine & Science in Sports, 24(3), 491–499. https://doi.org/10.1111/sms.12127
Clermont, C. A., Phinyomark, A., Osis, S. T., & Ferber, R. (2019). Classification of higher- and lower-risk runners based on running kinematics using machine learning. Journal of Biomechanics, 92, 119–125. https://doi.org/10.1016/j.jbiomech.2019.05.006
Camomilla, V., Bergamini, E., Fantozzi, S., & Vannozzi, G. (2018). Trends supporting the in-field use of wearable inertial sensors for sport performance evaluation. Sensors, 18(3), 873. https://doi.org/10.3390/s18030873
Moore, I. S., & McMahon, J. J. (2019). Quantifying human movement variability using machine learning. Sports Biomechanics, 18(2), 1–15. https://doi.org/10.1080/14763141.2018.1516923
Challis, J. H., & Kerwin, D. G. (2012). Quantification of movement variability. Human Movement Science, 31(1), 5–14. https://doi.org/10.1016/j.humov.2011.04.002
Seethapathi, N., Wang, S., & Srinivasan, M. (2019). Movement science needs different pose tracking algorithms. arXiv preprint (used with peer-reviewed validation). https://doi.org/10.1038/s41593-019-0424-4
Ardestani, M. M., Zhang, X., Wang, L., Lian, Q., Liu, Y., He, J., Li, D., & Jin, Z. (2014). Human lower extremity joint moment prediction: A wavelet neural network approach. Expert Systems with Applications, 41(9), 4422–4433. https://doi.org/10.1016/j.eswa.2013.12.039
Bartlett, R., Wheat, J., & Robins, M. (2007). Is movement variability important for sports biomechanists? Sports Biomechanics, 6(2), 224–243. https://doi.org/10.1080/14763140701322994
Wouda, F. J., Giuberti, M., Bellusci, G., Veltink, P. H., & Reenalda, J. (2018). Estimation of vertical ground reaction forces and moments during walking using wearable inertial sensors. Journal of Biomechanics, 70, 1–8. https://doi.org/10.1016/j.jbiomech.2017.12.023
Preece, S. J., Goulermas, J. Y., Kenney, L. P., Howard, D., Meijer, K., & Crompton, R. (2009). Activity identification using body-mounted sensors. Medical Engineering & Physics, 31(1), 84–92. https://doi.org/10.1016/j.medengphy.2008.03.006
Donath, L., Faude, O., Lichtenstein, E., & Nüesch, C. (2016). Validity and reliability of inertial measurement units for gait analysis. Journal of Sports Sciences, 34(20), 1940–1948. https://doi.org/10.1080/02640414.2016.1149608
Maiwald, C., Sterzing, T., Mayer, T. A., & Milani, T. L. (2009). Detecting foot-to-ground contact from kinematic data in running. Footwear Science, 1(2), 111–118. https://doi.org/10.1080/19424280903020234
Phinyomark, A., Osis, S. T., Hettinga, B. A., & Ferber, R. (2015). Kinematic gait patterns in healthy runners using machine learning. Journal of Biomechanics, 48(12), 3432–3438. https://doi.org/10.1016/j.jbiomech.2015.07.039
Horst, F., Lapuschkin, S., Samek, W., Müller, K.-R., & Schöllhorn, W. I. (2019). Explaining the unique nature of individual gait patterns with deep learning. Scientific Reports, 9, 2391. https://doi.org/10.1038/s41598-019-38748-8
Johnson, W. R., Alderson, J., Lloyd, D. G., & Mian, A. (2018). Predicting athlete ground reaction forces and moments from motion capture using deep learning. IEEE Transactions on Biomedical Engineering, 66(3), 689–698. https://doi.org/10.1109/TBME.2018.2853132
Dorschky, E., Nitschke, M., Seifer, A.-K., van den Bogert, A. J., & Eskofier, B. M. (2019). Estimation of gait kinematics and kinetics from inertial sensor data using deep learning. PLoS ONE, 14(4), e0216406. https://doi.org/10.1371/journal.pone.0216406
Eskofier, B. M., Lee, S. I., Baron, M., Simon, A., Martindale, C. F., Gaßner, H., & Klucken, J. (2016). An overview of smart shoes in the Internet of Health Things. IEEE Internet of Things Journal, 3(6), 977–986. https://doi.org/10.1109/JIOT.2016.2586443
Alaqtash, M., Sarkodie-Gyan, T., Yu, H., Fuentes, O., Brower, R., & Abdelgawad, A. (2011). Automatic classification of pathological gait patterns using ground reaction forces and machine learning algorithms. IEEE Transactions on Information Technology in Biomedicine, 15(2), 280–287. https://doi.org/10.1109/TITB.2010.2093624
Chen, S., Lach, J., Lo, B., & Yang, G.-Z. (2016). Toward pervasive gait analysis with wearable sensors: A systematic review. IEEE Journal of Biomedical and Health Informatics, 20(6), 1521–1537. https://doi.org/10.1109/JBHI.2016.2608720
Figueiredo, J., Félix, P., Costa, L., Moreno, J. C., & Santos, C. P. (2018). Gait event detection in controlled and real-life situations: Recurrent neural networks and kinematic signals. Sensors, 18(2), 441. https://doi.org/10.3390/s18020441
Kidzinski, Ł., Delp, S. L., & Schwartz, M. H. (2020). Automatic real-time gait event detection in children using deep neural networks. PLoS ONE, 15(1), e0226821. https://doi.org/10.1371/journal.pone.0226821
O’Reilly, M., Caulfield, B., Ward, T., Johnston, W., & Doherty, C. (2017). Wearable inertial sensor systems for lower limb exercise detection and evaluation: A review. Sports Medicine, 47(8), 1–18. https://doi.org/10.1007/s40279-017-0724-3
Kobsar, D., Osis, S. T., Phinyomark, A., Boyd, J. E., & Ferber, R. (2017). Reliability of machine learning classification of running biomechanics. Gait & Posture, 57, 152–158. https://doi.org/10.1016/j.gaitpost.2017.06.020
Mousavi, A., Schöllhorn, W. I., & Faber, I. R. (2020). Artificial intelligence and pattern recognition in sports biomechanics. Sports Biomechanics, 19(4), 1–18. https://doi.org/10.1080/14763141.2019.1636230
Richter, C., Marshall, B., & Moran, K. (2014). Comparison of discrete-point vs. dimensionality-reduction techniques for describing performance-related aspects of maximal vertical jumping. Journal of Biomechanics, 47(12), 3012–3017. https://doi.org/10.1016/j.jbiomech.2014.07.019
Uhlrich, S. D., Silder, A., Beaupre, G. S., Shull, P. B., & Delp, S. L. (2018). Subject-specific neural networks for predicting lower-limb kinematics from wearable sensors. Journal of Biomechanics, 66, 1–7. https://doi.org/10.1016/j.jbiomech.2017.10.033
Dindorf, C., Teufl, W., Taetz, B., Bleser, G., & Fröhlich, M. (2020). Interpretability of input representations for gait classification using convolutional neural networks. Sensors, 20(18), 5115. https://doi.org/10.3390/s20185115
Camomilla, V., D’Anna, C., & Cappozzo, A. (2017). Gait analysis methodology: From laboratory to real-life applications. Journal of Biomechanics, 50, 1–3. https://doi.org/10.1016/j.jbiomech.2016.11.033
Li, G., Yu, Y., & Li, Y. (2020). Deep learning-based human activity recognition using inertial sensors: A survey. Sensors, 20(3), 646. https://doi.org/10.3390/s20030646
Reenalda, J., Maartens, E., Homan, L., & Buurke, J. H. (2016). Continuous three-dimensional analysis of running mechanics during a marathon by means of inertial measurement units. Journal of Biomechanics, 49(9), 1932–1937. https://doi.org/10.1016/j.jbiomech.2016.04.007
Eskofier, B. M., Kugler, P., Melzer, J., & Heinrich, K. (2013). Embedded classification of the human gait using kinematic features. Sensors, 13(11), 14623–14641. https://doi.org/10.3390/s131114623
Preatoni, E., Hamill, J., Harrison, A. J., Hayes, K., Van Emmerik, R. E. A., Wilson, C., & Rodano, R. (2013). Movement variability and skills monitoring in sports. Sports Biomechanics, 12(2), 69–92. https://doi.org/10.1080/14763141.2012.738700
Huang, Y., Wang, Z., & Wang, L. (2021). Human motion analysis using deep learning: A review. IEEE Transactions on Neural Networks and Learning Systems, 32(6), 1–16. https://doi.org/10.1109/TNNLS.2020.3015496
Mariani, B., Jiménez, M. C., Vingerhoets, F. J. G., & Aminian, K. (2013). On-shoe wearable sensors for gait and turning assessment of Parkinson’s disease patients. IEEE Transactions on Biomedical Engineering, 60(1), 155–158. https://doi.org/10.1109/TBME.2012.2227317
Zhou, H., Hu, H., & Harris, N. (2008). Application of wearable inertial sensors in human motion analysis: A survey. IEEE Sensors Journal, 8(11), 1–13. https://doi.org/10.1109/JSEN.2008.2006195
Oh, S. E., Choi, A., & Mun, J. H. (2019). Machine learning-based gait classification and prediction using spatiotemporal gait features. Medical Engineering & Physics, 72, 1–7. https://doi.org/10.1016/j.medengphy.2019.07.007
Cutti, A. G., Ferrari, A., Garofalo, P., Raggi, M., Cappello, A., & Ferrari, A. (2010). Outwalk: A protocol for clinical gait analysis based on inertial and magnetic sensors. Medical & Biological Engineering & Computing, 48(1), 17–25. https://doi.org/10.1007/s11517-009-0545-x
Kim, J., Lee, J., Park, S., & Kim, Y. (2018). Deep learning-based gait analysis for injury risk assessment in athletes. IEEE Access, 6, 56973–56982. https://doi.org/10.1109/ACCESS.2018.2873288
Van der Kruk, E., & Reijne, M. M. (2018). Accuracy of human motion capture systems for sport applications: State-of-the-art review. European Journal of Sport Science, 18(6), 806–819. https://doi.org/10.1080/17461391.2018.1463397
Tan, T., Zhang, Z., & Liu, Y. (2021). Vision-based gait analysis using deep learning: A review. Pattern Recognition, 113, 107768. https://doi.org/10.1016/j.patcog.2021.107768
Krupenevich, R. L., Rider, P. M., Domire, Z. J., & DeVita, P. (2015). Males and females respond differently to walking-induced fatigue. Journal of Biomechanics, 48(14), 1–7. https://doi.org/10.1016/j.jbiomech.2015.09.014
Storm, F. A., Buckley, C. J., & Mazzà, C. (2016). Gait event detection in laboratory and real life settings: Accuracy of ankle and waist sensor based methods. Gait & Posture, 50, 42–46. https://doi.org/10.1016/j.gaitpost.2016.08.012
Roetenberg, D., Luinge, H. J., & Slycke, P. J. (2013). Xsens MVN: Full 6DOF human motion tracking using miniature inertial sensors. Xsens Motion Technologies White Paper, 1–9. https://doi.org/10.1109/ICORR.2009.5209558
Stenum, J., Rossi, C., & Roemmich, R. T. (2021). Two-dimensional video-based analysis of human gait using pose estimation. PLoS ONE, 16(4), e0248440. https://doi.org/10.1371/journal.pone.0248440
Needham, L., Evans, M., Cosker, D. P., Wade, L., McGuigan, P., & Bilzon, J. (2021). The accuracy of marker less motion capture in estimating upper and lower limb kinematics during boxing. Sports Biomechanics, 20(5), 1–17. https://doi.org/10.1080/14763141.2021.1875274
D’Andrea, S. E., Wilhelm, N., & Jensen, J. L. (2023). Validity of marker less motion capture for estimating joint kinematics during athletic tasks. Journal of Biomechanics, 149, 111458. https://doi.org/10.1016/j.jbiomech.2023.111458
Kanko, R. M., Laende, E. K., Davis, E. M., Selbie, W. S., & Deluzio, K. J. (2021). Concurrent assessment of gait using marker-based and marker less motion capture. Journal of Biomechanics, 127, 110665. https://doi.org/10.1016/j.jbiomech.2021.110665
Mundt, M., Thomsen, W., Witter, T., Koeppe, A., David, S., Bamer, F., Potthast, W., & Markert, B. (2020). Prediction of ground reaction forces and joint moments based on kinematics and deep learning. PLoS ONE, 15(9), e0239808. https://doi.org/10.1371/journal.pone.0239808
Miller, R. H., & Hamill, J. (2009). Computer simulation of the effects of shoe cushioning on internal and external loading during running impacts. Computer Methods in Biomechanics and Biomedical Engineering, 12(4), 481–490. https://doi.org/10.1080/10255840902866861
Ancillao, A., Tedesco, S., Barton, J., & O’Flynn, B. (2018). Indirect measurement of ground reaction forces and moments by means of wearable inertial sensors: A systematic review. Sensors, 18(8), 2564. https://doi.org/10.3390/s18082564
Laidig, D., Lehmann, D., & Eskofier, B. M. (2021). Marker less motion capture systems in sports: A systematic review. Sensors, 21(14), 4790. https://doi.org/10.3390/s21144790
Colyer, S. L., Evans, M., Cosker, D. P., & Salo, A. I. T. (2018). A review of the evolution of vision-based motion analysis and the integration of AI in sports biomechanics. Sports Medicine, 48(8), 1–22. https://doi.org/10.1007/s40279-018-0944-2
Falbriard, M., Meyer, F., Mariani, B., Millet, G. P., & Aminian, K. (2018). Accurate estimation of running temporal parameters using foot-worn inertial sensors. Frontiers in Physiology, 9, 610. https://doi.org/10.3389/fphys.2018.00610
Morris, R., Stuart, S., McBarron, G., Fino, P. C., Mancini, M., & Curtze, C. (2019). Validity of mobility lab (Opal) inertial sensors for gait analysis. Gait & Posture, 71, 204–209. https://doi.org/10.1016/j.gaitpost.2019.04.025
Karatsidis, A., Jung, M., Schepers, H. M., Bellusci, G., de Zee, M., Veltink, P. H., & Andersen, M. S. (2019). Musculoskeletal model-based inverse dynamic analysis under ambulatory conditions using inertial sensors. Annals of Biomedical Engineering, 47(2), 372–387. https://doi.org/10.1007/s10439-018-02098-5
Dorschky, E., Camomilla, V., Davis, J., & Eskofier, B. M. (2023). Machine learning in clinical gait analysis: Past, present, and future. Gait & Posture, 100, 126–136. https://doi.org/10.1016/j.gaitpost.2022.12.012
Troje, N. F. (2002). Decomposing biological motion: A framework for analysis and synthesis of human gait patterns. Journal of Vision, 2(5), 371–387. https://doi.org/10.1167/2.5.2
Vanrenterghem, J., Nedergaard, N. J., Robinson, M. A., & Drust, B. (2017). Training load monitoring in team sports: A novel framework separating physiological and biomechanical load. Sports Medicine, 47(11), 2135–2142. https://doi.org/10.1007/s40279-017-0714-5
Bittencourt, N. F. N., Meeuwisse, W. H., Mendonça, L. D., Nettel-Aguirre, A., Ocarino, J. M., & Fonseca, S. T. (2016). Complex systems approach for sports injuries: Moving from risk factor identification to injury pattern recognition. British Journal of Sports Medicine, 50(21), 1309–1314. https://doi.org/10.1136/bjsports-2015-095850
Ferber, R., Osis, S. T., Hicks, J. L., & Delp, S. L. (2016). Gait biomechanics in the era of data science. Journal of Biomechanics, 49(16), 3759–3761. https://doi.org/10.1016/j.jbiomech.2016.10.033
Schöllhorn, W. I., Horst, F., & Müller, D. (2022). Artificial intelligence in sports biomechanics: Opportunities and challenges. Frontiers in Sports and Active Living, 4, 857913. https://doi.org/10.3389/fspor.2022.857913
Seethapathi, N., & Srinivasan, M. (2019). The metabolic cost of changing walking speeds is significant, indicates importance of gait transitions. Proceedings of the Royal Society B, 286(1912), 20191404. https://doi.org/10.1098/rspb.2019.1404
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Authors
This work is licensed under a Creative Commons Attribution 4.0 International License.
