FREE SHIPPING over $40
OVER 9000 FIVE-STAR REVIEWS
5% OFF ALL SUBSCRIPTIONS
100% HAPPINESS GUARANTEE
Analyze Diet
0
Home / Equine Research Bank / Animals (Basel) / Is Markerless More or Less? Comparing a Smartphone Computer ...
Animals : an open access journal from MDPI2023; 13(3); 390; doi: 10.3390/ani13030390

Is Markerless More or Less? Comparing a Smartphone Computer Vision Method for Equine Lameness Assessment to Multi-Camera Motion Capture.

Abstract: Computer vision is a subcategory of artificial intelligence focused on extraction of information from images and video. It provides a compelling new means for objective orthopaedic gait assessment in horses using accessible hardware, such as a smartphone, for markerless motion analysis. This study aimed to explore the lameness assessment capacity of a smartphone single camera (SC) markerless computer vision application by comparing measurements of the vertical motion of the head and pelvis to an optical motion capture multi-camera (MC) system using skin attached reflective markers. Twenty-five horses were recorded with a smartphone (60 Hz) and a 13 camera MC-system (200 Hz) while trotting two times back and forth on a 30 m runway. The smartphone video was processed using artificial neural networks detecting the horse's direction, action and motion of body segments. After filtering, the vertical displacement curves from the head and pelvis were synchronised between systems using cross-correlation. This rendered 655 and 404 matching stride segmented curves for the head and pelvis respectively. From the stride segmented vertical displacement signals, differences between the two minima (MinDiff) and the two maxima (MaxDiff) respectively per stride were compared between the systems. Trial mean difference between systems was 2.2 mm (range 0.0-8.7 mm) for head and 2.2 mm (range 0.0-6.5 mm) for pelvis. Within-trial standard deviations ranged between 3.1-28.1 mm for MC and between 3.6-26.2 mm for SC. The ease of use and good agreement with MC indicate that the SC application is a promising tool for detecting clinically relevant levels of asymmetry in horses, enabling frequent and convenient gait monitoring over time.
Get Full Text
Publication Date: 2023-01-24 PubMed ID: 36766279PubMed Central: PMC9913208DOI: 10.3390/ani13030390Google 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 study aims to assess the efficacy of a smartphone-based computer vision application in the diagnosis of lameness in horses by comparing it with the traditional multi-camera system. Its findings suggest that the smartphone-based computer vision tool stands promising for frequent and convenient gait monitoring over time due to its ease of use and level of agreement with the traditional method.

Objective of the Study

  • The primary goal of this research was to evaluate a smartphone single camera (SC) markerless computer vision application’s capacity to assess lameness in horses.
  • The researchers sought to ascertain the reliability of the said smartphone application by comparing its metrics of vertical head and pelvis movement with that of a traditional optical multi-camera (MC) system which makes use of skin attached reflective markers.

Methodology

  • A total of 25 horses were employed for this experiment, each trotting twice on a 30-meter runway while being recorded with a smartphone at 60 Hz and a 13 camera MC-system at 200 Hz.
  • Using artificial neural networks, the recorded smartphone video was processed to detect and document the horse’s direction, action, and motion of body segments.
  • Following this, the vertical displacement curves from the head and pelvis were synchronized between the SC and MC systems using cross-correlation. This sequence generated 655 and 404 matching stride segmented curves for the head and pelvis, respectively.

Results and Findings

  • The trial mean difference between the two systems was found to be 2.2 mm (range 0.0-8.7 mm) for head movements and 2.2 mm (range 0.0-6.5 mm) for pelvis movements.
  • Within-trial standard deviations ranged between 3.1-28.1 mm for MC and between 3.6-26.2 mm for SC.
  • The agreement between the readings of the SC and MC systems suggested that a smartphone-based application could potentially serve as a valid tool for detecting asymmetry in horses at clinically significant levels.

Conclusion

  • The study concludes that the smartphone-based computer vision application can be a practical and promising tool for routine and convenient gait monitoring over time, due to its ease of use and its ability to produce results that are in good agreement with traditional, multi-camera systems.

Cite This Article

APA
Lawin FJ, Byström A, Roepstorff C, Rhodin M, Almlöf M, Silva M, Andersen PH, Kjellström H, Hernlund E. (2023). Is Markerless More or Less? Comparing a Smartphone Computer Vision Method for Equine Lameness Assessment to Multi-Camera Motion Capture. Animals (Basel), 13(3), 390. https://doi.org/10.3390/ani13030390

Publication

Animals : an open access journal from MDPI
ISSN: 2076-2615
NlmUniqueID: 101635614
Country: Switzerland
Language: English
Volume: 13
Issue: 3
PII: 390

Researcher Affiliations

Lawin, Felix Järemo
  • Sleip AI, Birger Jarlsgatan 58, 11426 Stockholm, Sweden.
Byström, Anna
  • Department of Anatomy, Physiology and Biochemistry, Swedish University of Agricultural Sciences, 75007 Uppsala, Sweden.
Roepstorff, Christoffer
  • Sleip AI, Birger Jarlsgatan 58, 11426 Stockholm, Sweden.
Rhodin, Marie
  • Department of Anatomy, Physiology and Biochemistry, Swedish University of Agricultural Sciences, 75007 Uppsala, Sweden.
Almlöf, Mattias
  • Sleip AI, Birger Jarlsgatan 58, 11426 Stockholm, Sweden.
Silva, Mudith
  • Sleip AI, Birger Jarlsgatan 58, 11426 Stockholm, Sweden.
Andersen, Pia Haubro
  • Department of Anatomy, Physiology and Biochemistry, Swedish University of Agricultural Sciences, 75007 Uppsala, Sweden.
Kjellström, Hedvig
  • KTH Royal Institute of Technology, Division of Robotics, Perception and Learning, 10044 Stockholm, Sweden.
Hernlund, Elin
  • Sleip AI, Birger Jarlsgatan 58, 11426 Stockholm, Sweden.
  • Department of Anatomy, Physiology and Biochemistry, Swedish University of Agricultural Sciences, 75007 Uppsala, Sweden.

Grant Funding

  • 2018.4.2-2084 / Marie-Claire Cronstedts Stiftelse
  • 2018- 00737 / Swedish research council FORMAS

Conflict of Interest Statement

The funder had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results. Authors affiliated to the company Sleip AI (F.J.L., C.R., M.A., M.S. and E.H.) declare a conflict of interest since the company provides a commercially available diagnostic tool for detecting lameness in horses from a smartphone. The developed computer vision technique is validated in the current paper.

References

This article includes 39 references
  1. Roepstorff C, Imogen Gmel A, Arpagaus S, Manuel Serra Bragança F, Hernlund E, Roepstorff L, Rhodin M, Andreas Weishaupt M. Modelling fore- and hindlimb peak vertical force differences in trotting horses using upper body kinematic asymmetry variables.. J Biomech 2022 May;137:111097.
    doi: 10.1016/j.jbiomech.2022.111097pubmed: 35468550google scholar: lookup
  2. Bell RP, Reed SK, Schoonover MJ, Whitfield CT, Yonezawa Y, Maki H, Pai PF, Keegan KG. Associations of force plate and body-mounted inertial sensor measurements for identification of hind limb lameness in horses.. Am J Vet Res 2016 Apr;77(4):337-45.
    doi: 10.2460/ajvr.77.4.337pubmed: 27027831google scholar: lookup
  3. Buchner HH, Savelberg HH, Schamhardt HC, Barneveld A. Head and trunk movement adaptations in horses with experimentally induced fore- or hindlimb lameness.. Equine Vet J 1996 Jan;28(1):71-6.
    doi: 10.1111/j.2042-3306.1996.tb01592.xpubmed: 8565958google scholar: lookup
  4. Parkes RS, Weller R, Groth AM, May S, Pfau T. Evidence of the development of 'domain-restricted' expertise in the recognition of asymmetric motion characteristics of hindlimb lameness in the horse.. Equine Vet J 2009 Feb;41(2):112-7.
    doi: 10.2746/042516408X343000pubmed: 19418737google scholar: lookup
  5. Holcombe AO. Seeing slow and seeing fast: two limits on perception.. Trends Cogn Sci 2009 May;13(5):216-21.
    doi: 10.1016/j.tics.2009.02.005pubmed: 19386535google scholar: lookup
  6. Keegan KG, Dent EV, Wilson DA, Janicek J, Kramer J, Lacarrubba A, Walsh DM, Cassells MW, Esther TM, Schiltz P, Frees KE, Wilhite CL, Clark JM, Pollitt CC, Shaw R, Norris T. Repeatability of subjective evaluation of lameness in horses.. Equine Vet J 2010 Mar;42(2):92-7.
    doi: 10.2746/042516409X479568pubmed: 20156242google scholar: lookup
  7. Hammarberg M, Egenvall A, Pfau T, Rhodin M. Rater agreement of visual lameness assessment in horses during lungeing.. Equine Vet J 2016 Jan;48(1):78-82.
    doi: 10.1111/evj.12385pmc: PMC4964936pubmed: 25399722google scholar: lookup
  8. Arkell M, Archer RM, Guitian FJ, May SA. Evidence of bias affecting the interpretation of the results of local anaesthetic nerve blocks when assessing lameness in horses.. Vet Rec 2006 Sep 9;159(11):346-9.
    doi: 10.1136/vr.159.11.346pubmed: 16963714google scholar: lookup
  9. McCracken MJ, Kramer J, Keegan KG, Lopes M, Wilson DA, Reed SK, LaCarrubba A, Rasch M. Comparison of an inertial sensor system of lameness quantification with subjective lameness evaluation.. Equine Vet J 2012 Nov;44(6):652-6.
    doi: 10.1111/j.2042-3306.2012.00571.xpubmed: 22563674google scholar: lookup
  10. Rhodin M, Egenvall A, Haubro Andersen P, Pfau T. Head and pelvic movement asymmetries at trot in riding horses in training and perceived as free from lameness by the owner.. PLoS One 2017;12(4):e0176253.
    doi: 10.1371/journal.pone.0176253pmc: PMC5404851pubmed: 28441406google scholar: lookup
  11. Müller-Quirin J, Dittmann MT, Roepstorff C, Arpagaus S, Latif SN, Weishaupt MA. Riding Soundness-Comparison of Subjective With Objective Lameness Assessments of Owner-Sound Horses at Trot on a Treadmill.. J Equine Vet Sci 2020 Dec;95:103314.
    doi: 10.1016/j.jevs.2020.103314pubmed: 33276930google scholar: lookup
  12. Pfau T, Noordwijk K, Sepulveda Caviedes MF, Persson-Sjodin E, Barstow A, Forbes B, Rhodin M. Head, withers and pelvic movement asymmetry and their relative timing in trot in racing Thoroughbreds in training.. Equine Vet J 2018 Jan;50(1):117-124.
    doi: 10.1111/evj.12705pmc: PMC5724686pubmed: 28548349google scholar: lookup
  13. Pfau T, Parkes RS, Burden ER, Bell N, Fairhurst H, Witte TH. Movement asymmetry in working polo horses.. Equine Vet J 2016 Jul;48(4):517-22.
    doi: 10.1111/evj.12467pubmed: 26037947google scholar: lookup
  14. Scheidegger MD, Gerber V, Dolf G, Burger D, Flammer SA, Ramseyer A. Quantitative Gait Analysis Before and After a Cross-country Test in a Population of Elite Eventing Horses.. J Equine Vet Sci 2022 Oct;117:104077.
    doi: 10.1016/j.jevs.2022.104077pubmed: 35820497google scholar: lookup
  15. Lopes M.A., Eleuterio A., Mira M.C.. Objective Detection and Quantification of Irregular Gait With a Portable Inertial Sensor-Based System in Horses During an Endurance Race—A Preliminary Assessment.. J. Equine Vet. Sci. 2018;70:123–129.
    doi: 10.1016/j.jevs.2018.08.008google scholar: lookup
  16. Kallerud AS, Fjordbakk CT, Hendrickson EHS, Persson-Sjodin E, Hammarberg M, Rhodin M, Hernlund E. Objectively measured movement asymmetry in yearling Standardbred trotters.. Equine Vet J 2021 May;53(3):590-599.
    doi: 10.1111/evj.13302pubmed: 32558997google scholar: lookup
  17. Maliye S, Voute LC, Marshall JF. Naturally-occurring forelimb lameness in the horse results in significant compensatory load redistribution during trotting.. Vet J 2015 May;204(2):208-13.
    doi: 10.1016/j.tvjl.2015.03.005pubmed: 25862395google scholar: lookup
  18. Pfau T, Witte TH, Wilson AM. A method for deriving displacement data during cyclical movement using an inertial sensor.. J Exp Biol 2005 Jul;208(Pt 13):2503-14.
    doi: 10.1242/jeb.01658pubmed: 15961737google scholar: lookup
  19. Keegan KG, Yonezawa Y, Pai PF, Wilson DA. Accelerometer-based system for the detection of lameness in horses.. Biomed Sci Instrum 2002;38:107-12.
    pubmed: 12085585
  20. Bosch S, Serra Bragança F, Marin-Perianu M, Marin-Perianu R, van der Zwaag BJ, Voskamp J, Back W, van Weeren R, Havinga P. EquiMoves: A Wireless Networked Inertial Measurement System for Objective Examination of Horse Gait.. Sensors (Basel) 2018 Mar 13;18(3).
    doi: 10.3390/s18030850pmc: PMC5877382pubmed: 29534022google scholar: lookup
  21. Hardeman AM, Serra Bragança 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 Nov;51(6):831-839.
    doi: 10.1111/evj.13075pmc: PMC6850282pubmed: 30648286google scholar: lookup
  22. Serra Bragança 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 Apr;234:11-23.
    doi: 10.1016/j.tvjl.2018.01.006pubmed: 29680381google scholar: lookup
  23. Aurand AM, Dufour JS, Marras WS. Accuracy map of an optical motion capture system with 42 or 21 cameras in a large measurement volume.. J Biomech 2017 Jun 14;58:237-240.
    doi: 10.1016/j.jbiomech.2017.05.006pubmed: 28549599google scholar: lookup
  24. LeCun Y., Bengio Y.. Convolutional networks for images, speech, and time series.. Handb. Brain Theory Neural Netw. 1995;3361:1995.
  25. Fukushima K.. Neocognitron: A hierarchical neural network capable of visual pattern recognition.. Neural Netw. 1988;1:119–130.
    doi: 10.1016/0893-6080(88)90014-7google scholar: lookup
  26. LeCun Y, Bengio Y, Hinton G. Deep learning.. Nature 2015 May 28;521(7553):436-44.
    doi: 10.1038/nature14539pubmed: 26017442google scholar: lookup
  27. Azhand A, Rabe S, Müller S, Sattler I, Heimann-Steinert A. Algorithm based on one monocular video delivers highly valid and reliable gait parameters.. Sci Rep 2021 Jul 7;11(1):14065.
    doi: 10.1038/s41598-021-93530-zpmc: PMC8263606pubmed: 34234255google scholar: lookup
  28. Wang J, Sun K, Cheng T, Jiang B, Deng C, Zhao Y, Liu D, Mu Y, Tan M, Wang X, Liu W, Xiao B. Deep High-Resolution Representation Learning for Visual Recognition.. IEEE Trans Pattern Anal Mach Intell 2021 Oct;43(10):3349-3364.
    doi: 10.1109/TPAMI.2020.2983686pubmed: 32248092google scholar: lookup
  29. Li C., Ghorbani N., Broomé S., Rashid M., Black M.J., Hernlund E., Kjellström H., Zuffi S.. hSMAL: Detailed Horse Shape and Pose Reconstruction for Motion Pattern Recognition.. arXiv 20212106.10102.
  30. Hatherley JJ. Limits of trust in medical AI.. J Med Ethics 2020 Jul;46(7):478-481.
    doi: 10.1136/medethics-2019-105935pubmed: 32220870google scholar: lookup
  31. Girshick R.. Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision Santiago, Chile. 7–13 December 2015; pp. 1440–1448.
  32. Long J., Shelhamer E., Darrell T.. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Boston, MA, USA. 7–12 June 2015; pp. 3431–3440.
  33. Bhat G., Lawin F.J., Danelljan M., Robinson A., Felsberg M., Gool L.V., Timofte R.. Learning what to learn for video object segmentation. Proceedings of the European Conference on Computer Vision Glasgow, UK. 23–28 August 2020; Berlin/Heidelberg, Germany: Springer; 2020. pp. 777–794.
  34. Bragança F.S., Roepstorff C., Rhodin M., Pfau T., Van Weeren P., Roepstorff L.. Quantitative lameness assessment in the horse based on upper body movement symmetry: The effect of different filtering techniques on the quantification of motion symmetry.. Biomed. Signal Process. Control. 2020;57:101674.
    doi: 10.1016/j.bspc.2019.101674google scholar: lookup
  35. Keegan KG, Yonezawa Y, Pai PF, Wilson DA, Kramer J. Evaluation of a sensor-based system of motion analysis for detection and quantification of forelimb and hind limb lameness in horses.. Am J Vet Res 2004 May;65(5):665-70.
    doi: 10.2460/ajvr.2004.65.665pubmed: 15141889google scholar: lookup
  36. Pfau T., Boultbee H., Davis H., Walker A., Rhodin M.. Agreement between two inertial sensor gait analysis systems for lameness examinations in horses.. Equine Vet. Educ. 2016;28:203–208.
    doi: 10.1111/eve.12400google scholar: lookup
  37. Bland JM, Altman DG. Statistical methods for assessing agreement between two methods of clinical measurement.. Lancet 1986 Feb 8;1(8476):307-10.
    doi: 10.1016/S0140-6736(86)90837-8pubmed: 2868172google scholar: lookup
  38. Keegan KG, Kramer J, Yonezawa Y, Maki H, Pai PF, Dent EV, Kellerman TE, Wilson DA, Reed SK. Assessment of repeatability of a wireless, inertial sensor-based lameness evaluation system for horses.. Am J Vet Res 2011 Sep;72(9):1156-63.
    doi: 10.2460/ajvr.72.9.1156pubmed: 21879972google scholar: lookup
  39. Wang Y., Li J., Zhang Y., Sinnott R.O.. Identifying lameness in horses through deep learning. Proceedings of the ACM Symposium on Applied Computing Virtual. 22–26 March 2021; pp. 976–985.
    doi: 10.1145/3412841.3441973google scholar: lookup

Citations

This article has been cited 1 times.
  1. Guyard KC, Montavon S, Bertolaccini J, Deriaz M. Validation of Alogo Move Pro: A GPS-Based Inertial Measurement Unit for the Objective Examination of Gait and Jumping in Horses.. Sensors (Basel) 2023 Apr 22;23(9).
    doi: 10.3390/s23094196pubmed: 37177397google scholar: lookup
Subscribe to our newsletter
Join 99,357 horse owners like you who receive our email updates on horse health and nutrition.