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 MDPI2020; 10(12); 2258; doi: 10.3390/ani10122258

Development and Validation of an Automated Video Tracking Model for Stabled Horses.

Abstract: Changes in behaviour are often caused by painful conditions. Therefore, the assessment of behaviour is important for the recognition of pain, but also for the assessment of quality of life. Automated detection of movement and the behaviour of a horse in the box stall should represent a significant advancement. In this study, videos of horses in an animal hospital were recorded using an action camera and a time-lapse mode. These videos were processed using the convolutional neural network Loopy for automated prediction of body parts. Development of the model was carried out in several steps, including annotation of the key points, training of the network to generate the model and checking the model for its accuracy. The key points nose, withers and tail are detected with a sensitivity of more than 80% and an error rate between 2 and 7%, depending on the key point. By means of a case study, the possibility of further analysis with the acquired data was investigated. The results will significantly improve the pain recognition of horses and will help to develop algorithms for the automated recognition of behaviour using machine learning.
Get Full Text
Publication Date: 2020-11-30 PubMed ID: 33266297PubMed Central: PMC7760072DOI: 10.3390/ani10122258Google 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 researchers have developed and tested a new automated system for tracking the movements of horses in their stalls using video, this system could help identify pain and improve the quality of life of horses.

Research Objective

The primary objective of this study was to develop and validate an automated tracking model for horses in a stable. The genesis of this innovation was the understanding that behavior changes in horses often stem from uncomfortable conditions. This model is intended to shed more light on how these behavioral changes can be identified and used to assess not only pain, but also the quality of life of these horses.

The Study Methodology

  • Videos of horses in an animal hospital were recorded using an action camera and a time-lapse mode. The primary aim was to automate the detection of the horse’s movements and behavior while it was in a box stall.
  • The videos were processed using a convolutional neural network named Loopy. Convolutional neural networks (CNN) are a class of deep-learning model most commonly applied to analyzing visual data.
  • Development of the model happened in stages, first by annotating key points, which were presumably specific locations or reference points on the body of the horse. Next, the network was trained to generate a predictive model. Finally, the accuracy of the model was evaluated by analyzing its sensitivity and error rate in detecting the annotated key points.

Findings

  • It was found that the model could detect key points – specifically, the nose, withers (the ridge between a horse’s shoulder blades), and tail – with over 80% sensitivity. The error rate varied between 2 and 7%, depending on the key point.
  • A case study was conducted to explore possible further analysis with the acquired data. This suggests the researchers believe the model could be utilized in other related applications or studies.

Implications

The overall gain from this research is twofold. Firstly, the results are expected to dramatically improve the ability to recognize pain in horses. This can influence veterinary practices and enhance the welfare of horses. Secondly, this research will aid the development of algorithms for the automated recognition of behavior using machine learning, possibly expanding its uses beyond horse behavior analysis to wider applications.

Cite This Article

APA
Kil N, Ertelt K, Auer U. (2020). Development and Validation of an Automated Video Tracking Model for Stabled Horses. Animals (Basel), 10(12), 2258. https://doi.org/10.3390/ani10122258

Publication

Animals : an open access journal from MDPI
ISSN: 2076-2615
NlmUniqueID: 101635614
Country: Switzerland
Language: English
Volume: 10
Issue: 12
PII: 2258

Researcher Affiliations

Kil, Nuray
  • Department of Anaesthesiology and Perioperative Intensive Care Medicine, Department for Companion Animals, Vetmeduni Vienna, 1210 Viena, Austria.
Ertelt, Katrin
  • Department of Anaesthesiology and Perioperative Intensive Care Medicine, Department for Companion Animals, Vetmeduni Vienna, 1210 Viena, Austria.
Auer, Ulrike
  • Department of Anaesthesiology and Perioperative Intensive Care Medicine, Department for Companion Animals, Vetmeduni Vienna, 1210 Viena, Austria.

Conflict of Interest Statement

The authors declare no conflict of interest

References

This article includes 41 references
  1. Price J, Catriona S, Welsh EM, Waran NK. Preliminary evaluation of a behaviour-based system for assessment of post-operative pain in horses following arthroscopic surgery.. Vet Anaesth Analg 2003 Jul;30(3):124-37.
    doi: 10.1046/j.1467-2995.2003.00139.xpubmed: 14498844google scholar: lookup
  2. Van Loon J.P.M., Back W., Hellebrekers L.J., Van Weeren P.R.. Application of a composite pain scale to objectively monitor horses with somatic and visceral pain under hospital conditions.. J. Equine Vet. Sci. 2010;30:641–649.
    doi: 10.1016/j.jevs.2010.09.011google scholar: lookup
  3. van Loon JPAM, Van Dierendonck MC. Objective pain assessment in horses (2014-2018).. Vet J 2018 Dec;242:1-7.
    doi: 10.1016/j.tvjl.2018.10.001pubmed: 30503538google scholar: lookup
  4. Dalla Costa E, Minero M, Lebelt D, Stucke D, Canali E, Leach MC. Development of the Horse Grimace Scale (HGS) as a pain assessment tool in horses undergoing routine castration.. PLoS One 2014;9(3):e92281.
    doi: 10.1371/journal.pone.0092281pmc: PMC3960217pubmed: 24647606google scholar: lookup
  5. Wathan J, Burrows AM, Waller BM, McComb K. Correction: EquiFACS: The Equine Facial Action Coding System.. PLoS One 2015;10(9):e0137818.
    pmc: PMC4559452pubmed: 26336096doi: 10.1371/journal.pone.0137818google scholar: lookup
  6. Gleerup KB, Forkman B, Lindegaard C, Andersen PH. An equine pain face.. Vet Anaesth Analg 2015 Jan;42(1):103-14.
    doi: 10.1111/vaa.12212pmc: PMC4312484pubmed: 25082060google scholar: lookup
  7. Gleerup K.B., Lindegaard C.. Recognition and quantification of pain in horses: A tutorial review.. Equine Vet. Educ. 2016;28:47–55.
    doi: 10.1111/eve.12383google scholar: lookup
  8. Dyson S., Berger J., Ellis D.A., Mullard J.. Development of an ethogram for a pain scoring system in ridden horses and its application to determine the presence of musculoskeletal pain.. J. Vet. Behav. 2018;23:47–57.
    doi: 10.1016/j.jveb.2017.10.008google scholar: lookup
  9. Lesimple C, Fureix C, De Margerie E, Sénèque E, Menguy H, Hausberger M. Towards a postural indicator of back pain in horses (Equus caballus).. PLoS One 2012;7(9):e44604.
    doi: 10.1371/journal.pone.0044604pmc: PMC3436792pubmed: 22970261google scholar: lookup
  10. Sénèque E, Lesimple C, Morisset S, Hausberger M. Could posture reflect welfare state? A study using geometric morphometrics in riding school horses.. PLoS One 2019;14(2):e0211852.
    doi: 10.1371/journal.pone.0211852pmc: PMC6363216pubmed: 30721258google scholar: lookup
  11. Morrel-Samuels P., Krauss R.M.. Cartesian analysis: A computer-video interface for measuring motion without physical contact. Behavior Research. Methods Instrum. Comput. 1990;22:466–470.
    doi: 10.3758/BF03203196google scholar: lookup
  12. Pereira P., Oliveira R.F.. A simple method using a single video camera to determine the three-dimensional position of a fish. Behavior Research. Methods Instrum. Comput. 1994;26:443–446.
    doi: 10.3758/BF03204663google scholar: lookup
  13. Santucci A.C.. An affordable computer-aided method for conducting Morris water maze testing.. Behav. Res. Methodsinstrum. Comput. 1995;27:60–64.
    doi: 10.3758/BF03203622google scholar: lookup
  14. Levitis DA, Lidicker WZ, Freund G. Behavioural biologists don't agree on what constitutes behaviour.. Anim Behav 2009 Jul 1;78(1):103-110.
    doi: 10.1016/j.anbehav.2009.03.018pmc: PMC2760923pubmed: 20160973google scholar: lookup
  15. Anderson DJ, Perona P. Toward a science of computational ethology.. Neuron 2014 Oct 1;84(1):18-31.
    doi: 10.1016/j.neuron.2014.09.005pubmed: 25277452google scholar: lookup
  16. Cooke SJ, Hinch SG, Wikelski M, Andrews RD, Kuchel LJ, Wolcott TG, Butler PJ. Biotelemetry: a mechanistic approach to ecology.. Trends Ecol Evol 2004 Jun;19(6):334-43.
    doi: 10.1016/j.tree.2004.04.003pubmed: 16701280google scholar: lookup
  17. Mathis A, Mamidanna P, Cury KM, Abe T, Murthy VN, Mathis MW, Bethge M. DeepLabCut: markerless pose estimation of user-defined body parts with deep learning.. Nat Neurosci 2018 Sep;21(9):1281-1289.
    doi: 10.1038/s41593-018-0209-ypubmed: 30127430google scholar: lookup
  18. Graving JM, Chae D, Naik H, Li L, Koger B, Costelloe BR, Couzin ID. DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning.. Elife 2019 Oct 1;8.
    doi: 10.7554/eLife.47994pmc: PMC6897514pubmed: 31570119google scholar: lookup
  19. Mathis MW, Mathis A. Deep learning tools for the measurement of animal behavior in neuroscience.. Curr Opin Neurobiol 2020 Feb;60:1-11.
    doi: 10.1016/j.conb.2019.10.008pubmed: 31791006google scholar: lookup
  20. Burla J.B., Ostertag A., Westerath H.S., Hillmann E.. Gait determination and activity measurement in horses using an accelerometer.. Comput. Electron. Agric. 2014;102:127–133.
    doi: 10.1016/j.compag.2014.01.001google scholar: lookup
  21. Eerdekens A., Deruyck M., Fontaine J., Martens L., Poorter E.D., Joseph W.. Automatic equine activity detection by convolutional neural networks using accelerometer data.. Comput. Electron. Agric. 2020;168:105–139.
    doi: 10.1016/j.compag.2019.105139google scholar: lookup
  22. Noldus LP, Spink AJ, Tegelenbosch RA. EthoVision: a versatile video tracking system for automation of behavioral experiments.. Behav Res Methods Instrum Comput 2001 Aug;33(3):398-414.
    doi: 10.3758/BF03195394pubmed: 11591072google scholar: lookup
  23. Lind NM, Vinther M, Hemmingsen RP, Hansen AK. Validation of a digital video tracking system for recording pig locomotor behaviour.. J Neurosci Methods 2005 Apr 30;143(2):123-32.
    doi: 10.1016/j.jneumeth.2004.09.019pubmed: 15814144google scholar: lookup
  24. Walton A, Branham A, Gash DM, Grondin R. Automated video analysis of age-related motor deficits in monkeys using EthoVision.. Neurobiol Aging 2006 Oct;27(10):1477-83.
    doi: 10.1016/j.neurobiolaging.2005.08.003pubmed: 16198447google scholar: lookup
  25. Bloemen H, Aerts JM, Berckmans D, Goedseels V. Image analysis to measure activity index of animals.. Equine Vet J Suppl 1997 May;(23):16-9.
    doi: 10.1111/j.2042-3306.1997.tb05044.xpubmed: 9354280google scholar: lookup
  26. Frost A.R., Tillett R.D., Welch S.K.. The development and evaluation of image analysis procedures for guiding a livestock monitoring sensor placement robot.. Comput. Electron. Agric. 2000;28:229–242.
    doi: 10.1016/S0168-1699(00)00129-0google scholar: lookup
  27. Martin BR, Prescott WR, Zhu M. Quantitation of rodent catalepsy by a computer-imaging technique.. Pharmacol Biochem Behav 1992 Oct;43(2):381-6.
    doi: 10.1016/0091-3057(92)90166-Dpubmed: 1332079google scholar: lookup
  28. Aydin A., Cangar O., Ozcan S.E., Bahr C., Berckmans D.. Application of a fully automatic analysis tool to assess the activity of broiler chickens with different gait scores.. Comput. Electron. Agric. 2010;73:194–199.
    doi: 10.1016/j.compag.2010.05.004google scholar: lookup
  29. Burke J., Nuthall P.L., McKinnon A.E.. An analysis of the feasibility of using image processing to estimate the live weight of sheep.. FHMG Res. Rep. 2004;2:6.
  30. Kashiha M.A., Bahr C., Ott S., Moons C.P., Niewold T.A., Tuyttens F., Berckmans D.. Automatic monitoring of pig locomotion using image analysis.. Livest. Sci. 2014;159:141–148.
    doi: 10.1016/j.livsci.2013.11.007google scholar: lookup
  31. Oczak M., Maschat K., Berckmans D., Vranken E., Baumgartner J.. Automatic estimation of number of piglets ina pen during farrowing, using image analysis.. Biosyst. Eng. 2016;151:81–89.
    doi: 10.1016/j.biosystemseng.2016.08.018google scholar: lookup
  32. Van Hertem T., Rooijakkers L., Berckmans D., Peña Fernández A., Norton T., Berckmans D., Vranken E.. Appropriate data visualisation is key to Precision Livestock Farming acceptance.. Comput. Electron. Agric. 2016;138:1–10.
    doi: 10.1016/j.compag.2017.04.003google scholar: lookup
  33. Venter P.J., Hanekom J.J.. Automatic detection of African elephant (Loxodonta africana) infrasonic vocalisations from recordings 2010). Biosyst. Eng. 2010;106:286–294.
    doi: 10.1016/j.biosystemseng.2010.04.001google scholar: lookup
  34. Pereira TD, Aldarondo DE, Willmore L, Kislin M, Wang SS, Murthy M, Shaevitz JW. Fast animal pose estimation using deep neural networks.. Nat Methods 2019 Jan;16(1):117-125.
    doi: 10.1038/s41592-018-0234-5pmc: PMC6899221pubmed: 30573820google scholar: lookup
  35. Bonneau M., Vayssade J.A., Troupe W., Arquet R.. Outdoor animal tracking combining neural network and time-lapse cameras.. Comput. Electron. Agric. 2020;168:6.
    doi: 10.1016/j.compag.2019.105150google scholar: lookup
  36. Nath T, Mathis A, Chen AC, Patel A, Bethge M, Mathis MW. Using DeepLabCut for 3D markerless pose estimation across species and behaviors.. Nat Protoc 2019 Jul;14(7):2152-2176.
    doi: 10.1038/s41596-019-0176-0pubmed: 31227823google scholar: lookup
  37. Zhou C., Zhang B., Lin K., Xu D., Chen C., Yang X., Sun C.. Near-infrared imaging to quantify the feeding behavior of fish in aquaculture.. Comput. Electron. Agric. 2017;135:233–241.
    doi: 10.1016/j.compag.2017.02.013google scholar: lookup
  38. Nasirahmadi A., Edwards S.A., Sturm B.. Implementation of machine vision for detecting behaviour of cattle and pigs.. Livest. Sci. 2017;202:25–38.
    doi: 10.1016/j.livsci.2017.05.014google scholar: lookup
  39. Anamika A.. Study of Techniques used for Medical image Segmentation and Computation of Statistical Test for Region Classification of Brain MRI.. Int. J. Inf. Technol. Comput. Sci. 2013;5:44–53.
    doi: 10.5815/ijitcs.2013.05.06google scholar: lookup
  40. Vayssade J.-A., Arquet R., Bonneau M.. Automatic activity tracking of goats using drone camera.. Comput. Electron. Agric. 2019;162:767–772.
    doi: 10.1016/j.compag.2019.05.021google scholar: lookup
  41. Bussières G, Jacques C, Lainay O, Beauchamp G, Leblond A, Cadoré JL, Desmaizières LM, Cuvelliez SG, Troncy E. Development of a composite orthopaedic pain scale in horses.. Res Vet Sci 2008 Oct;85(2):294-306.
    doi: 10.1016/j.rvsc.2007.10.011pubmed: 18061637google scholar: lookup

Citations

This article has been cited 6 times.
  1. Kim SM, Cho GJ. Analysis of Various Facial Expressions of Horses as a Welfare Indicator Using Deep Learning. Vet Sci 2023 Apr 10;10(4).
    doi: 10.3390/vetsci10040283pubmed: 37104439google scholar: lookup
  2. Feuser AK, Gesell-May S, Müller T, May A. Artificial Intelligence for Lameness Detection in Horses-A Preliminary Study. Animals (Basel) 2022 Oct 17;12(20).
    doi: 10.3390/ani12202804pubmed: 36290189google scholar: lookup
  3. Topczewska J, Bartman J, Kwater T. Assessing the utility value of Hucul horses using classification models, based on artificial neural networks. PLoS One 2022;17(7):e0271340.
    doi: 10.1371/journal.pone.0271340pubmed: 35881630google scholar: lookup
  4. Chen X, Yang T, Mai K, Liu C, Xiong J, Kuang Y, Gao Y. Holstein Cattle Face Re-Identification Unifying Global and Part Feature Deep Network with Attention Mechanism. Animals (Basel) 2022 Apr 18;12(8).
    doi: 10.3390/ani12081047pubmed: 35454293google scholar: lookup
  5. Zekoll T, Waldherr M, Tessmar-Raible K. Characterization of tmt-opsin2 in Medaka Fish Provides Insight Into the Interplay of Light and Temperature for Behavioral Regulation. Front Physiol 2021;12:726941.
    doi: 10.3389/fphys.2021.726941pubmed: 34744767google scholar: lookup
  6. Lencioni GC, de Sousa RV, de Souza Sardinha EJ, Corrêa RR, Zanella AJ. Pain assessment in horses using automatic facial expression recognition through deep learning-based modeling. PLoS One 2021;16(10):e0258672.
    doi: 10.1371/journal.pone.0258672pubmed: 34665834google scholar: lookup
Subscribe to our newsletter
Join 99,824 horse owners like you who receive our email updates on horse health and nutrition.