Estimating hip impact velocity and acceleration from video-captured falls using a pose estimation algorithm
Open accessAbstract
Analyzing video footage of falls in older adults has emerged as an alternative to traditional lab studies. However, this approach is limited by the labor-intensive process of manually labeling body parts. To address this limitation, we aimed to validate the use of the AI-based pose estimation algorithm (OpenPose) in assessing the hip impact velocity and acceleration of video-captured falls. We analyzed 110 videos of 13 older adults (64.0 ± 5.9 years old) falling sideways in an experimental setting. By applying OpenPose to each video, we generated a time series of hip positions in the video, which were then analyzed using custom MATLAB code to calculate hip impact velocity and acceleration. These calculations were compared against ground truth measurements obtained from motion capture systems (VICON for hip impact velocity) and inertial measurement units (MC10 for hip impact acceleration). We examined the agreement between the ground truth and OpenPose measurements in terms of mean of absolute error (MAE), mean of absolute percentage error (MAPE), and bias (mean of error). Results showed that OpenPose had a good accuracy in estimating hip impact velocity with minimal bias (MAE: 0.17 ± 0.13 m/s, MAPE: 7.28 ± 5.21%; percent bias: - 1.27%). However, its estimation of hip impact acceleration (i.e., peak vertical hip acceleration at impact) showed poor accuracy (MAPE: 26.3 ± 19.4%), showing substantial underestimation in instances of high acceleration impacts (> 3.0 g). Further ANOVA analysis revealed OpenPose's ability to discern significant differences in hip impact velocity and acceleration based on the movement response utilized during the fall (e.g., stick-like fall, tuck-and-roll, knee block). This is the first study to validate the use of a pose estimation algorithm for identifying the hip impact kinematics in video-captured falls among older adults. Future validation studies involving diverse camera settings, fall contexts, and biomechanical parameters are warranted to extend this support for using pose estimation algorithms in this field.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Skill acquisition is better reflected in the consistency and smoothness of the trajectory rather than in suppressing peak forces governed by gravity.
“This indicates that skill acquisition is better reflected in the consistency and smoothness of the trajectory rather than in suppressing peak forces governed by gravity [13].”
From Safe Fall: Use of Predictive Modeling and Machine Vision Techniques for Fall Analysis and Fall Quality (2026) · cites this paper as [13]
The Results (Characteristics of hip impact velocity and acceleration; page unavailable) compare impact measures across fall strategies, and the Discussion addresses the accuracy of video-based acceleration estimates. Neither section evaluates skill acquisition, trajectory consistency or smoothness, or whether those measures reflect skill better than peak forces. Searches for those concepts found no passage addressing the comparison. (LLM, conf=0.76)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Sensitivity and False Alarm Rate of a Fall Sensor in Long-Term Fall Detection in the Elderly
Kangas, M., Korpelainen, R., Vikman, I., Nyberg, L., & Jämsä, T. J. (2014) · Gerontology · doi:10.1159/000362720 · Cited by 19,005 · see citing works
Biomechanics and Motor Control of Human Movement
Winter, D. A. (2009) · Wiley eBooks · doi:10.1002/9780470549148 · Cited by 6,112 · see citing works
User’s guide to correlation coefficients
Akoglu, H. (2018) · Turkish Journal of Emergency Medicine · doi:10.1016/j.tjem.2018.08.001 · Cited by 5,849 · see citing works
DeepLabCut: markerless pose estimation of user-defined body parts with deep learning
Mathis, A., Mamidanna, P., Cury, K. M., Abe, T., Murthy, V. N., Mathis, M. W., & Bethge, M. (2018) · Nature Neuroscience · doi:10.1038/s41593-018-0209-y · Cited by 5,187 · see citing works
The costs of fatal and non-fatal falls among older adults
Stevens, J. A., Corso, P. S., Finkelstein, E. A., & Miller, T. R. (2006) · Injury Prevention · doi:10.1136/ip.2005.011015 · Cited by 1,494 · see citing works
Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm
Bourke, A. K., O’Brien, J., & Lyons, G. M. (2006) · Gait & Posture · doi:10.1016/j.gaitpost.2006.09.012 · Cited by 823 · see citing works
AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time
Fang, H.-S., Li, J., Tang, H., Xu, C., Zhu, H., Xiu, Y., Li, Y., & Lu, C. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3222784 · Cited by 779 · see citing works
Type of Fall and Risk of Hip and Wrist Fractures: The Study of Osteoporotic Fractures
Nevitt, M. C., & Cummings, S. R. (1993) · Journal of the American Geriatrics Society · doi:10.1111/j.1532-5415.1993.tb07307.x · Cited by 571 · see citing works
Parkkari, J. P., Kannus, P., Palvanen, M., Natri, A., Vainio, J., Aho, H., VUORI, I. M., & Järvinen, M. (1999) · Calcified Tissue International · doi:10.1007/s002239900679 · Cited by 563 · see citing works
Deaths from Falls Among Persons Aged ≥65 Years — United States, 2007–2016
Burns, E. R., & Kakara, R. S. (2018) · MMWR Morbidity and Mortality Weekly Report · doi:10.15585/mmwr.mm6718a1 · Cited by 471 · see citing works
Evaluation of Accelerometer-Based Fall Detection Algorithms on Real-World Falls
Bagalà, F., Becker, C., Cappello, A., Chiari, L., Aminian, K., Hausdorff, J. M., Zijlstra, W., & Klenk, J. (2012) · PLoS ONE · doi:10.1371/journal.pone.0037062 · Cited by 464 · see citing works
Two-dimensional video-based analysis of human gait using pose estimation
Stenum, J., Rossi, C., & Roemmich, R. T. (2021) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1008935 · Cited by 325 · see citing works
Traumatic brain injury in older adults: characteristics, causes and consequences
Harvey, L. A., & Close, J. (2012) · Injury · doi:10.1016/j.injury.2012.07.188 · Cited by 280 · see citing works
A Systematic Review on Healthcare Analytics: Application and Theoretical Perspective of Data Mining
Islam, M. S., Hasan, M. M., Wang, X., Germack, H. D., & Noor‐E‐Alam, M. (2018) · Healthcare · doi:10.3390/healthcare6020054 · Cited by 268 · see citing works
Jakobsen, J. C., Gluud, C. N., Winkel, P., Lange, T., & Wetterslev, J. (2014) · BMC Medical Research Methodology · doi:10.1186/1471-2288-14-34 · Cited by 201 · see citing works
Ergonomic postural assessment using a new open-source human pose estimation technology (OpenPose)
Kim, W., Sung, J., Saakes, D. P., Huang, C., & Xiong, S. (2021) · International Journal of Industrial Ergonomics · doi:10.1016/j.ergon.2021.103164 · Cited by 192 · see citing works
Applications of Pose Estimation in Human Health and Performance across the Lifespan
Stenum, J., Cherry‐Allen, K. M., Pyles, C. O., Reetzke, R., Vignos, M. F., & Roemmich, R. T. (2021) · Sensors · doi:10.3390/s21217315 · Cited by 181 · see citing works
de Quadros, T., Lazzaretti, A. E., & Schneider, F. K. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2829815 · Cited by 179 · see citing works
Monitoring gait in multiple sclerosis with novel wearable motion sensors
Moon, Y., McGinnis, R. S., Seagers, K. A., Motl, R. W., Sheth, N., Wright, J. A., Ghaffari, R., & Sosnoff, J. J. (2017) · PLoS ONE · doi:10.1371/journal.pone.0171346 · Cited by 134 · see citing works
Self-citationUsing deep neural networks for kinematic analysis: Challenges and opportunities
Cronin, N. J. (2021) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2021.110460 · Cited by 124 · see citing works
Stenum, J., Hsu, M., Pantelyat, A. Y., & Roemmich, R. T. (2024) · PLOS Digital Health · doi:10.1371/journal.pdig.0000467 · Cited by 108 · see citing works
Lonini, L., Moon, Y., Embry, K., Cotton, R. J., McKenzie, K. A., Jenz, S. T., & Jayaraman, A. (2022) · Digital Biomarkers · doi:10.1159/000520732 · Cited by 103 · see citing works
Self-citationVideo-based Fall Detection for Seniors with Human Pose Estimation
Huang, Z., Liu, Y., Fang, Y., & Horn, B. K. P. (2018) · International Conference on Universal Village (UV) · doi:10.1109/uv.2018.8642130 · Cited by 98 · see citing works
Kinematic analysis of video-captured falls experienced by older adults in long-term care
Choi, W. J., Wakeling, J. M., & Robinovitch, S. N. (2015) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2015.02.025 · Cited by 88 · see citing works
Self-citationComputer Vision and Machine Learning-Based Gait Pattern Recognition for Flat Fall Prediction
Chen, B., Chen, C., Hu, J., Sayeed, Z., Qi, J., Darwiche, H. F., Little, B. E., Lou, S., Darwish, M. B., Foote, C. W., et al. (2022) · Sensors · doi:10.3390/s22207960 · Cited by 81 · see citing works
Safe landing strategies during a fall: Systematic review and meta-analysis
Moon, Y., & Sosnoff, J. J. (2017) · Archives of Physical Medicine and Rehabilitation · doi:10.1016/j.apmr.2016.08.460 · Cited by 79 · see citing works
Self-citationTrends in fall-related injuries among older adults treated in emergency departments in the USA
Orces, C. H., & Alamgir, H. (2014) · Injury Prevention · doi:10.1136/injuryprev-2014-041268 · Cited by 73 · see citing works
Laing, A. C., Feldman, F., Jalili, M., Tsai, C. M., & Robinovitch, S. N. (2011) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2011.08.016 · Cited by 69 · see citing works
Self-citationSideways fall-induced impact force and its effect on hip fracture risk: a review
Sarvi, M. N., & Luo, Y. (2017) · Osteoporosis International · doi:10.1007/s00198-017-4138-5 · Cited by 60 · see citing works
Automatic real-time occupational posture evaluation and select corresponding ergonomic assessments
Lin, P.-C., Chen, Y.-J., Wei‐Shin, C., & Lee, Y. (2022) · Scientific Reports · doi:10.1038/s41598-022-05812-9 · Cited by 58 · see citing works
Predicting 3-D Lower Back Joint Load in Lifting: A Deep Pose Estimation Approach
Mehrizi, R., Peng, X., Metaxas, D., Xu, X., Zhang, S., & Li, K. (2019) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2018.2884811 · Cited by 55 · see citing works
McGinnis, R. S., & Perkins, N. C. (2012) · Sensors · doi:10.3390/s120911933 · Cited by 52 · see citing works
Komisar, V., Dojnov, A., Yang, Y., Shishov, N., Chong, H., Yu, Y., Bercovitz, I., Cusimano, M. D., Becker, C., Mackey, D. C., et al. (2022) · BMC Geriatrics · doi:10.1186/s12877-022-03041-3 · Cited by 49 · see citing works
Self-citationShishov, N., Elabd, K., Komisar, V., Chong, H., & Robinovitch, S. N. (2021) · PLOS ONE · doi:10.1371/journal.pone.0258923 · Cited by 42 · see citing works
Self-citationRobinovitch, S. N., Dojnov, A., Komisar, V., Yang, Y., Shishov, N., Yu, Y., Bercovitz, I., Cusimano, M. D., Becker, C., Mackey, D. C., et al. (2022) · Age and Ageing · doi:10.1093/ageing/afac273 · Cited by 35 · see citing works
Self-citationThe Role of Fall Biomechanics in the Cause and Prevention of Bone Fractures in Older Adults
Komisar, V., & Robinovitch, S. N. (2021) · Current Osteoporosis Reports · doi:10.1007/s11914-021-00685-9 · Cited by 34 · see citing works
Self-citationMoon, Y., Bishnoi, A., Sun, R., Shin, J. C., & Sosnoff, J. J. (2018) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2018.12.002 · Cited by 28 · see citing works
Self-citationHindle, B. R., Keogh, J., & Lorimer, A. V. (2020) · Sensors · doi:10.3390/s20164586 · Cited by 23 · see citing works
Gould, Z. R., Mora-González, J., Aguiar, E. J., Schuna, J. M., Barreira, T. V., Moore, C. C., STAUDENMAYER, J. W., & Tudor-Locke, C. E. (2021) · International Journal of Behavioral Nutrition and Physical Activity · doi:10.1186/s12966-021-01167-y · Cited by 23 · see citing works
Self-citationGlinka, M. N., Cheema, K. P., Robinovitch, S. N., & Laing, A. C. (2013) · Journal of Applied Biomechanics · doi:10.1123/jab.29.5.563 · Cited by 21 · see citing works
Self-citationChair Size Design Based on User Height
Sydor, M., & Hitka, M. (2023) · Biomimetics · doi:10.3390/biomimetics8010057 · Cited by 20 · see citing works
Chen, L., Zanotto, T., Fang, J. C.-T., Scharf, E., Garcia, N., Luzania, A., Mukherjee, R., Alexander, N. B., & Sosnoff, J. J. (2024) · The Journals of Gerontology Series A · doi:10.1093/gerona/glae267 · Cited by 5 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 4
- [21]Marshal, S., Raj, S. A., Jebaseeli, T. J. & Niranjan, S. In 2023 2nd International Conference on Automation, Computing and Renewable Systems (ICACRS) 493–498.
- [23]Huang, Z., Liu, Y., Fang, Y. & Horn, B. K. P. In 2018 4th International Conference on Universal Village (UV) 1–4.
- [40]Needham, C. J. & Boyle, R. D. in International Conference on Virtual Storytelling.
- [44]Artacho, B. & Savakis, A. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7035–7044.
Cited by
Sorted by citations
Validation of a Markerless Multi-Camera Pipeline for Bouldering Fall Kinematics
Carretier, N., Beurienne, E., Beauséjour, M.-H., Gros, L., Bruna-Rosso, C., Dorsemaine, M., Behr, M., Bailly, N., & Clément, J. (2026) · Sensors · doi:10.3390/s26020662 · Cited by 2 · see citing works
Chen, L., Zanotto, T., Lee, J., Fang, J. R., Tabatabaei, A., Alexander, N. B., & Sosnoff, J. J. (2026) · Archives of Physical Medicine and Rehabilitation · doi:10.1016/j.apmr.2026.04.009 · Cited by 2 · see citing works
Self-citationDelCastillo-Andrés, O., Fernández-García, R., Pastor-Vicedo, J. C., Lira, M. A., Campos-Mesa, M. C., Castañeda-Vázquez, C., Genovesi, E., Krstulović, S., Kuvačić, G., Morvay-Sey, K., et al. (2026) · Sensors · doi:10.3390/s26082491 · Cited by 1 · see citing works
“Fall kinematics vary significantly across the lifespan; for instance, the elderly population exhibits different centre-of-mass dynamics, slower reflex times, and distinct injury mechanisms (such as lateral hip impacts leading to fractures) compared to pediatric populations [13,14].”
Analysis, Evaluation, and Prediction of Machine Learning-Based Animal Behavior Imitation
Qi, Y., Xiong, S., & Wu, B. (2025) · Electronics · doi:10.3390/electronics14142816
Michaels, R., Ehrlich, J. A., Son, J., Robinovitch, S. N., Sosnoff, J. J., & Moon, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5362007
Self-citationChen, L., Zanotto, T., Lee, J.-H., Fang, J. C.-T., Tabatabaei, A., Alexandar, N., & Sosnoff, J. J. (2025) · medRxiv · doi:10.1101/2025.07.22.25331998
Self-citationEnhancing industrial human pose estimation through a hybrid Transformer–CNN architecture
Rashid, M., Wang, J., & Ahmed, S. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08689-x
Michaels, R., Ehrlich, J., Mei, Y., Son, J., Robinovitch, S. N., Sosnoff, J. J., & Moon, Y. (2026) · PLoS ONE · doi:10.1371/journal.pone.0335108
Self-citationMichaels, R., Mei, Y., Robinovitch, S. N., Duenas, V. H., Sosnoff, J. J., & Moon, Y. (2026) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2026.113479
Self-citationHuman Pose Estimation for Sports Injury Analysis: A Review
Anija, & Gupta, S. (2026) · International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC) · doi:10.1109/assic70037.2026.11716942
- Authors
- Michaels, R., Barreira, T. V., Robinovitch, S. N., Sosnoff, J. J., & Moon, Y.
- Affiliations
- Syracuse University (US)
- Simon Fraser University (CA)
- University of Kansas Medical Center (US)
- Corresponding author
- Moon, Yaejin
- Venue
- Scientific Reports
- Published
- 2025-01-10
- Volume
- 15
- Issue
- 1
- Pages
- 1558-1558
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC11717977
- OpenAlex
- W4406210708
- Cited by
- 9
- References
- 42
- Citations by year
- 2026: 6 · 2025: 3
- FWCI
- 19.60
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Scientific Reports (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Health Sciences › Health Professions › Physical Therapy, Sports Therapy and Rehabilitation › Balance, Gait, and Falls Prevention
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Keywords
- falls in older adults, pose estimation, OpenPose, hip kinematics, inertial measurement unit, motion capture validation
- MeSH terms
- Acceleration, Accidental Falls, Aged, Algorithms, Biomechanical Phenomena, Female, Hip, Humans, Male, Middle Aged, Posture, Video Recording
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
