FREE SHIPPING over $40
OVER 10000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
Animals : an open access journal from MDPI2025; 15(15); 2281; doi: 10.3390/ani15152281

A Markerless Approach for Full-Body Biomechanics of Horses.

Abstract: The ability to quantify equine kinematics is essential for clinical evaluation, research, and performance feedback. However, current methods are challenging to implement. This study presents a motion capture methodology for horses, where three-dimensional, full-body kinematics are calculated without instrumentation on the animal, offering a more scalable and labor-efficient approach when compared with traditional techniques. Kinematic trajectories are calculated from multi-camera video data. First, a neural network identifies skeletal landmarks (markers) in each camera view and the 3D location of each marker is triangulated. An equine biomechanics model is scaled to match the subject's shape, using segment lengths defined by markers. Finally, inverse kinematics (IK) produces full kinematic trajectories. We test this methodology on a horse at three gaits. Multiple neural networks (NNs), trained on different equine datasets, were evaluated. All networks predicted over 78% of the markers within 25% of the length of the radius bone on test data. Root-mean-square-error (RMSE) between joint angles predicted via IK using ground truth marker-based motion capture data and network-predicted data was less than 10 degrees for 25 to 32 of 35 degrees of freedom, depending on the gait and data used for network training. NNs trained over a larger variety of data improved joint angle RMSE and curve similarity. Marker prediction error, the average distance between ground truth and predicted marker locations, and IK marker error, the distance between experimental and model markers, were used to assess network, scaling, and registration errors. The results demonstrate the potential of markerless motion capture for full-body equine kinematic analysis.
Get Full Text
Publication Date: 2025-08-05 PubMed ID: 40805071PubMed Central: PMC12345546DOI: 10.3390/ani15152281Google Scholar: Lookup
The Equine Research Bank provides access to a large database of publicly available scientific literature. Inclusion in the Research Bank does not imply endorsement of study methods or findings by Mad Barn.
LinkedInCopy
  • Journal Article

Summary

This research summary has been generated with artificial intelligence and may contain errors and omissions. Refer to the original study to confirm details provided. Submit correction.

The research article details a novel method to capture the movement of horses without using any physical markers. The motion capture methodology uses multi-camera video data and machine learning to accurately track and analyze equine movement, making this technique more efficient and practical than current methods.

Markerless Motion Capture Methodology

  • The new method presented in the study aims to quantify equine biomechanics using a fully markerless approach. This means the technique doesn’t require the physical placement of markers or devices on the horse’s body.
  • Through the analysis of multi-camera video data, a neural network is able to identify skeletal landmarks (which traditionally would have been marked) in each camera view.
  • The 3D location of each ‘virtual’ marker is then calculated using a technique called triangulation, which involves measuring distances using the geometry of triangles.

The Utilization of Equine Biomechanics Model

  • The next step involves using an equine biomechanics model. This model is scaled to match the particular shape of the horse being analyzed, using the segment lengths defined by the identified markers.
  • The final step involves using inverse kinematics (IK) which generates full kinematic trajectories, essentially determining the movement paths of the horse.

Validation of the Markerless Approach

  • To validate the markerless approach, the technique was tested on a horse at three different gaits.
  • More than 78% of the virtual markers were predicted accurately within 25% of the length of the horse’s radius bone in test data.
  • The root-mean-square error (a measure of the differences between values predicted by a model and the values observed) between joint angles predicted by IK and data collected using traditional marker-based motion tracking was impressively less than 10 degrees in most cases.

The Potential of the New Approach

  • The reported results highlight the potential of this new, non-invasive technique for biomechanical analysis of horses’ movement.
  • The technique promises more scalable and labor-efficient equine kinematic analysis, which could revolutionize evaluations in research, clinical settings and performance metrics.

Cite This Article

APA
Shaffer SK, Medjaouri O, Swenson B, Eliason T, Nicolella DP. (2025). A Markerless Approach for Full-Body Biomechanics of Horses. Animals (Basel), 15(15), 2281. https://doi.org/10.3390/ani15152281

Publication

Animals : an open access journal from MDPI
ISSN: 2076-2615
NlmUniqueID: 101635614
Country: Switzerland
Language: English
Volume: 15
Issue: 15
PII: 2281

Researcher Affiliations

Shaffer, Sarah K
  • Southwest Research Institute, 6220 Culebra Rd., San Antonio, TX 78238, USA.
Medjaouri, Omar
  • Southwest Research Institute, 6220 Culebra Rd., San Antonio, TX 78238, USA.
Swenson, Brian
  • Southwest Research Institute, 6220 Culebra Rd., San Antonio, TX 78238, USA.
Eliason, Travis
  • Southwest Research Institute, 6220 Culebra Rd., San Antonio, TX 78238, USA.
Nicolella, Daniel P
  • Southwest Research Institute, 6220 Culebra Rd., San Antonio, TX 78238, USA.

Grant Funding

  • N/A / Southwest Research Institute

Conflict of Interest Statement

The authors declare no conflicts of interest.

References

This article includes 61 references
  1. Kane A, Traub-Dargatz J, Losinger W, Garber L. The Occurrence and Causes of Lameness and Laminitis in the U.S. Horse Population. Proceedings of the Annual Convention of the AAEP; San Antonio, TX, USA. 26–29 November 2000.
  2. Keegan KG. Evidence-based lameness detection and quantification. Vet. Clin. N. Am. Equine Pract. 2007;23:403–423.
    doi: 10.1016/j.cveq.2007.04.008pubmed: 17616320google scholar: lookup
  3. Merridale-Punter MS, Wiethoelter AK, El-Hage CM, Hitchens PL. Prevalence and Factors Associated with Working Equid Lameness in Low- and Middle-Income Countries: A Systematic Review and Meta-Analysis. Animals 2022;12:3100.
    doi: 10.3390/ani12223100pmc: PMC9686919pubmed: 36428328google scholar: lookup
  4. Ross MW, Dyson SJ. Diagnosis and Management of Lameness in the Horse. Elsevier Health Sciences; St. Louis, MO, USA: 2010.
  5. Baxter GM, Stashak TS, Keegan KG. Adams and Stashak’s Lameness in Horses. John Wiley & Sons, Inc.; Hoboken, NJ, USA: 2020. Examination for Lameness; pp. 67–188.
  6. Pfau T, Fiske-Jackson A, Rhodin M. Quantitative assessment of gait parameters in horses: Useful for aiding clinical decision making?. Equine Vet. Educ. 2015;28:209–215.
    doi: 10.1111/eve.12372google scholar: lookup
  7. Serra Braganca FM, Rhodin M, van Weeren PR. On the brink of daily clinical application of objective gait analysis: What evidence do we have so far from studies using an induced lameness model?. Vet. J. 2018;234:11–23.
    doi: 10.1016/j.tvjl.2018.01.006pubmed: 29680381google scholar: lookup
  8. Starke SD, Oosterlinck M. Reliability of equine visual lameness classification as a function of expertise, lameness severity and rater confidence. Vet. Rec. 2019;184:63.
    doi: 10.1136/vr.105058pubmed: 30242083google scholar: lookup
  9. Hardeman AM, Egenvall A, Serra Braganca FM, Swagemakers JH, Koene MHW, Roepstorff L, van Weeren R, Bystrom A. Visual lameness assessment in comparison to quantitative gait analysis data in horses. Equine Vet. J. 2022;54:1076–1085.
    doi: 10.1111/evj.13545pmc: PMC9786350pubmed: 34913524google scholar: lookup
  10. . EquiGait: Sensor Based Gait Analysis. [(accessed on 10 January 2024)].
  11. . EquiMoves: An Advanced System for Quanitative Gait Analysis. [(accessed on 10 January 2024)].
  12. . The Equinosis with Lamness Locator. [(accessed on 10 January 2024)].
  13. . Qualysis: Animal Motion Capture. [(accessed on 10 January 2024)].
  14. Hardeman AM, Serra Braganca FM, Swagemakers JH, van Weeren PR, Roepstorff L. Variation in gait parameters used for objective lameness assessment in sound horses at the trot on the straight line and the lunge. Equine Vet. J. 2019;51:831–839.
    doi: 10.1111/evj.13075pmc: PMC6850282pubmed: 30648286google scholar: lookup
  15. Hardeman AM, Van Weeren PR, Serra Bragança FM, Warmerdam H, Bok HGJ. A first exploration of perceived pros and cons of quantitative gait analysis in equine clinical practice. Equine Vet. Educ. 2021;34:E438–E444.
    doi: 10.1111/eve.13505google scholar: lookup
  16. Pfau T, Landsbergen K, Davis BL, Kenny O, Kernot N, Rochard N, Porte-Proust M, Sparks H, Takahashi Y, Toth K. Comparing Inertial Measurement Units to Markerless Video Analysis for Movement Symmetry in Quarter Horses. Sensors 2023;23:8414.
    doi: 10.3390/s23208414pmc: PMC10610735pubmed: 37896509google scholar: lookup
  17. Lawin FJ, Bystrom A, Roepstorff C, Rhodin M, Almlof M, Silva M, Andersen PH, Kjellstrom H, Hernlund E. Is Markerless More or Less? Comparing a Smartphone Computer Vision Method for Equine Lameness Assessment to Multi-Camera Motion Capture. Animals 2023;13:390.
    doi: 10.3390/ani13030390pmc: PMC9913208pubmed: 36766279google scholar: lookup
  18. Crecan CM, Pestean CP. Inertial Sensor Technologies-Their Role in Equine Gait Analysis, a Review. Sensors 2023;23:6301.
    doi: 10.3390/s23146301pmc: PMC10386433pubmed: 37514599google scholar: lookup
  19. Braganca FMS, Brommer H, van den Belt AJM, Maree JTM, van Weeren PR, van Oldruitenborgh-Oosterbaan MMS. Subjective and objective evaluations of horses for fit-to-compete or unfit-to-compete judgement. Vet. J. 2020;257:105454.
    doi: 10.1016/j.tvjl.2020.105454pubmed: 32546354google scholar: lookup
  20. Wade L, Needham L, McGuigan P, Bilzon J. Applications and limitations of current markerless motion capture methods for clinical gait biomechanics. PeerJ 2022;10:e12995.
    doi: 10.7717/peerj.12995pmc: PMC8884063pubmed: 35237469google scholar: lookup
  21. Clayton HM, Schamhardt HC. Measurment Techniques for Gait Analysis. In: Back W., Clayton HM, editors. Equine Locomotion. Elsevier; Amsterdam, The Netherlands: 2013.
  22. Serra Braganca FM, Rhodin M, Wiestner T, Hernlund E, Pfau T, van Weeren PR, Weishaupt MA. Quantification of the effect of instrumentation error in objective gait assessment in the horse on hindlimb symmetry parameters. Equine Vet. J. 2018;50:370–376.
    doi: 10.1111/evj.12766pmc: PMC5900976pubmed: 29032614google scholar: lookup
  23. Feuser AK, Gesell-May S, Muller T, May A. Artificial Intelligence for Lameness Detection in Horses-A Preliminary Study. Animals 2022;12:2804.
    doi: 10.3390/ani12202804pmc: PMC9597839pubmed: 36290189google scholar: lookup
  24. Gupta V. Equine Gait Analysis, Body Part Tracking using DeepLabCut and Mask R-CNN and Biomechanical Parameter Extraction. Master’s Thesis. Auburn University; Auburn, AL, USA: 2021.
  25. Kallerud AS, Marques-Smith P, Bendiksen HK, Fjordbakk CT. Objective movement asymmetry in horses is comparable between markerless technology and sensor-based systems. Equine Vet. J. 2025;57:115–125.
    doi: 10.1111/evj.14089pmc: PMC11616950pubmed: 38566453google scholar: lookup
  26. Niknejad N, Caro JL, Bidese-Puhl R, Bao Y, Staiger EA. Equine Kinematic Gait Analysis Using Stereo Videography and Deep Learning: Stride Length and Stance Duration Estimation. J. ASABE 2023;66:865–877.
    doi: 10.13031/ja.15386google scholar: lookup
  27. Wang Y, Li J, Zhang Y, Sinnott RO. Identifying lameness in horses through deep learning. Proceedings of the 36th Annual ACM Symposium on Applied Computing (SAC’21); Virtual Event, Republic of Korea. 22–26 March 2021; New York, NY, USA: Association for Computing Machinery; 2021. pp. 976–985.
    doi: 10.1145/3412841.3441973google scholar: lookup
  28. Li C, Ghorbani N, Broomé S, Rashid M, Black MJ, Hernlund E, Kjellström H, Zuffi S. hSMAL: Detailed Horse Shape and Pose Reconstruction for Motion Pattern Recognition. arXiv. 2021 [(accessed on 1 January 2024)].
  29. Li C, Mellbin Y, Krogager J, Polikovsky S, Holmberg M, Ghorbani N, Black MJ, Kjellström H, Zuffi S, Hernlund E. The Poses for Equine Research Dataset (PFERD). Sci. Data 2024;11:497.
    doi: 10.1038/s41597-024-03312-1pmc: PMC11096353pubmed: 38750064google scholar: lookup
  30. Li C, Yang Y, Weng Z, Hernlund E, Zuffi S, Kjellström H. Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images. arXiv. 2024 [(accessed on 1 January 2024)].
  31. Li C, Hernlund E, Kjellstrom H, Zuffi S. CLHOP: Combined Audio-Video Learning for Horse 3D Pose and Shape Estimation. Computer Vision and Pattern Recognition (cs.CV) arXiv. 20242407.01244.
  32. Zuffi S, Mellbin Y, Li C, Hoeschle M, Kjellström H, Polikovsky S, Hernlund E, Black MJ. VAREN: Very Accurate and Realistic Equine Network. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); Seattle, WA, USA. 16–20 June 2024.
  33. Frazer L, Templin T, Eliason TD, Butler C, Hando B, Nicolella D. Identifying special operative trainees at-risk for musculoskeletal injury using full body kinematics. Front. Bioeng. Biotechnol. 2023;11:1293923.
    doi: 10.3389/fbioe.2023.1293923pmc: PMC10731296pubmed: 38125303google scholar: lookup
  34. Eliason TD, Nicolella D. Development of a Deep Learning Based Markerless Motion Capture System. Proceedings of the World Congress of Biomechanics Conference; Dublin, Ireland. 8–12 July 2018.
  35. Templin T, Eliason TD, Medjaouri O, Chambers D, Saylor K, Nicolella D. The Effect of Synthetic Training Data on the Performance of a Deep Learning Based Markerless Biomechanics System. Southwest Research Institute; San Antonio, TX, USA: 2020.
  36. Bonilla Lemos PL, Holz K, Kowalski EA, Fonseca Ribeiro P, Blake R, Ferreira Martins C. 2D Kinematic Analysis of the Esbarrada and Volta Sobre Patas Manoeuvres of Criollo Breed Horses Competing in Freio de Ouro. Animals 2024;14:2410.
    doi: 10.3390/ani14162410pmc: PMC11350687pubmed: 39199944google scholar: lookup
  37. Rohlf CM, Garcia TC, Marsh LJ, Acutt EV, le Jeune SS, Stover SM. Effects of Jumping Phase, Leading Limb, and Arena Surface Type on Forelimb Hoof Movement. Animals 2023;13:2122.
    doi: 10.3390/ani13132122pmc: PMC10340005pubmed: 37443919google scholar: lookup
  38. Symons JE, Garcia TC, Stover SM. Distal hindlimb kinematics of galloping Thoroughbred racehorses on dirt and synthetic racetrack surfaces. Equine Vet. J. 2014;46:227–232.
    doi: 10.1111/evj.12113pubmed: 23742040google scholar: lookup
  39. Banik P, Li L, Xishuang D. A Novel Dataset for Keypoint Detection of Quadruped Animals from Images. arXiv. 20212108.13958.
  40. Yu H, Xu Y, Zhang J, Zhao W, Guan Z, Tao D. AP-10K: A Benchmark for Animal Pose Estimation in the Wild. arXiv. 2021 [(accessed on 1 January 2024)].
  41. Kaiming H, Gkioxari G, Dollár P, Girshick R. Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision; Venice, Italy. 22–29 October 2017; pp. 2961–2969.
  42. Newell A, Yang K, Deng J. Stacked Hourglass Networks for Human Pose Estimation. arXiv. 20161603.06937.
  43. Sun K, Xiao B, Dong L, Wang J. Deep High-Resolution Representation Learning for Human Pose Estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition; Long Beach, CA, USA. 15–20 June 2019.
  44. Fischler MA, Bolles RC. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Commun. ACM 1981;24:381–395.
    doi: 10.1145/358669.358692google scholar: lookup
  45. Torralba A, Isola P, Freeman WT. Foundations of Computer Vision, Section 39: Camera Modeling and Calibration. MIT Press; Cambridge, MA, USA: 2024. [(accessed on 1 January 2024)] (Adaptive Computation and Machine Learning Series).
  46. Desmarais Y, Mottet D, Slangen P, Montesinos P. A review of 3D human pose estimation algorithms for markerless motion capture. Comput. Vis. Image Underst. 2021;212:103275.
    doi: 10.1016/j.cviu.2021.103275google scholar: lookup
  47. Matsuura A, Ohta E, Ueda K, Nakatsuji H, Kondo S. Influence of Equine Conformation on Rider Oscillation and Evaluation of Horses for Therapeutic Riding. J. Equine Sci. 2008;19:9–18.
    doi: 10.1294/jes.19.9pmc: PMC4019204pubmed: 24833950google scholar: lookup
  48. van Bijlert PA, Geijtenbeek T, Smit IH, Schulp AS, Bates KT. Muscle-Driven Predictive Physics Simulations of Quadrupedal Locomotion in the Horse. Integr. Comp. Biol. 2024;64:694–714.
    doi: 10.1093/icb/icae095pmc: PMC11428545pubmed: 39003243google scholar: lookup
  49. He H, Palm-Vlasak LS, Chen C, Banks SA, Biedrzycki AH. Quantification of equine stifle passive kinematics. Am. J. Vet. Res. 2023;84.
    doi: 10.2460/ajvr.22.10.0171pubmed: 36576802google scholar: lookup
  50. Setterbo J, Garcia T, Campbell I, Kim S, Hubbard M, Stover S. Forelimb Kinematics of Galloping Thoroughbred Racehorses Measured on Dirt, Synthetic, and Turf Track Surfaces (P235). The Engineering of Sport 7. Springer; Paris, France: 2009. pp. 437–446.
  51. Ripic Z, Nienhus M, Signorile J, Best T, Jacobs K, Eltoukhy M. A comparison of three-dimensional kinematics between markerless and marker-based motion capture in overground gait. J. Biomech. 2023;159:111793.
    doi: 10.1016/j.jbiomech.2023.111793pubmed: 37725886google scholar: lookup
  52. Virtanen P, Gommers R, Oliphant TE, Haberland M, Reddy T, Cournapeau D, Burovski E, Peterson P, Weckesser W, Bright J. SciPy 1.0: Fundamental algorithms for scientific computing in Python. Nat. Methods 2020;17:261–272.
    doi: 10.1038/s41592-019-0686-2pmc: PMC7056644pubmed: 32015543google scholar: lookup
  53. Vallat R. Pingouin: Statistics in Python. J. Open Source Softw. 2018;3:1026.
    doi: 10.21105/joss.01026google scholar: lookup
  54. Koo TK, Li MY. A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J. Chiropr. Med. 2016;15:155–163.
    doi: 10.1016/j.jcm.2016.02.012pmc: PMC4913118pubmed: 27330520google scholar: lookup
  55. Uchida TK, Seth A. Conclusion or Illusion: Quantifying Uncertainty in Inverse Analyses From Marker-Based Motion Capture due to Errors in Marker Registration and Model Scaling. Front. Bioeng. Biotechnol. 2022;10:874725.
    doi: 10.3389/fbioe.2022.874725pmc: PMC9174465pubmed: 35694232google scholar: lookup
  56. Chateau H, Degueurce C, Denoix JM. Effects of 6 degree elevation of the heels on 3D kinematics of the distal portion of the forelimb in the walking horse. Equine Vet. J. 2004;36:649–654.
    doi: 10.2746/0425164044848217pubmed: 15656490google scholar: lookup
  57. Chateau H, Degueurce C, Denoix JM. Three-dimensional kinematics of the equine distal forelimb: Effects of a sharp turn at the walk. Equine Vet. J. 2005;37:12–18.
    doi: 10.2746/0425164054406946pubmed: 15651728google scholar: lookup
  58. Chateau H, Degueurce C, Denoix JM. Three-dimensional kinematics of the distal forelimb in horses trotting on a treadmill and effects of elevation of heel and toe. Equine Vet. J. 2006;38:164–169.
    doi: 10.2746/042516406776563260pubmed: 16536387google scholar: lookup
  59. Clayton HM, Sha D, Stick J, Elvin N. 3D kinematics of the equine metacarpophalangeal joint at walk and trot. Vet. Comp. Orthop. Traumatol. 2007;20:86–91.
    pubmed: 17546207
  60. Halley SE, Bey MJ, Haladik JA, Lavagnino M, Arnoczky SP. Three dimensional, radiosteriometric analysis (RSA) of equine stifle kinematics and articular surface contact: A cadaveric study. Equine Vet. J. 2014;46:364–369.
    doi: 10.1111/evj.12127pmc: PMC3864602pubmed: 23802689google scholar: lookup
  61. Shaffer SK, Shelly K, Garcia TC, Samol MA, Hill AE, Fyhrie DP, Stover SM. In vitro motions of the medial and lateral proximal sesamoid bones under mid-stance load conditions are consistent with racehorse fracture configurations. J. Biomech. 2022;130:110888.
    doi: 10.1016/j.jbiomech.2021.110888pubmed: 34894442google scholar: lookup

Citations

This article has been cited 0 times.
Subscribe to our newsletter
Join 99,727 horse owners like you who receive our email updates on horse health and nutrition.