Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jan 13, 2026

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder
06:54

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder

Published on: March 4, 2018

14.7K

A deep learning-based markerless gait analysis model for dogs shows promising accuracy when validated with

Ji-Hwan Pahk1, Sung-Jun Park2, Ji-Hyun Seo2

  • 1Department of Veterinary Clinical Sciences, College of Veterinary Medicine and Research Institute for Veterinary Science, Seoul National University, Seoul, Korea.

American Journal of Veterinary Research
|January 6, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Novel dorsal occipito-cervical fixation using a patient-specific implant and drill guide for a complex craniocervical junction anomaly in a dog.

Veterinary surgery : VS·2026
Same author

Computed tomographic assessment of plate offset in modified tibial plateau levelling osteotomy with a precontoured plate with an anatomical design for treatment of cranial cruciate ligament rupture and medial patellar luxation in small-breed dogs: An in vitro study.

Australian veterinary journal·2026
Same author

10-millimeter radial tibial plateau-leveling osteotomy can achieve favorable outcomes with low complication rates in small-breed dogs.

American journal of veterinary research·2026
Same author

Integration of locking screw fixation into 3D-printed patient-specific porous titanium implants enhances osseointegration: an <i>in vivo</i> study in a rabbit bone defect model.

Journal of veterinary science·2025
Same author

Intra-articular injections of polynucleotides show promise in improving clinical outcomes compared to hyaluronic acid in small-breed dogs with osteoarthritis.

American journal of veterinary research·2025
Same author

Simultaneous Modified Tibial Plateau Leveling Osteotomy and Tibial Tuberosity Transposition for Grade IV Medial Patellar Luxation and Cranial Cruciate Ligament Disease in Small-Breed Dogs.

Animals : an open access journal from MDPI·2025
This summary is machine-generated.

A new deep learning model accurately analyzes canine gait using markerless video analysis, offering a promising tool for clinical veterinary assessments. Further validation is needed for widespread use in diverse breeds and settings.

Area of Science:

  • Veterinary Medicine
  • Biomechanical Analysis
  • Artificial Intelligence in Animal Health

Background:

  • Gait analysis is crucial for diagnosing canine lameness and monitoring recovery.
  • Traditional marker-based systems are time-consuming and require specialized equipment.
  • Markerless systems offer a more accessible approach to canine gait analysis.

Purpose of the Study:

  • To develop and validate a deep learning-based markerless gait analysis model for dogs.
  • To assess the model's accuracy against traditional 2-D marker-based systems.
  • To explore the clinical utility of markerless gait analysis in veterinary settings.

Main Methods:

  • A prospective observational study involving 408 client-owned dogs of various breeds.
  • Utilized smartphone video recordings (1080p, 30fps) on a straight walkway.
Keywords:
canine gait analysisdeep learningkinematicsmarkerless gait analysisveterinary biomechanics

More Related Videos

3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

11.3K
Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents
04:37

Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents

Published on: July 6, 2022

2.8K

Related Experiment Videos

Last Updated: Jan 13, 2026

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder
06:54

Clinical-oriented Three-dimensional Gait Analysis Method for Evaluating Gait Disorder

Published on: March 4, 2018

14.7K
3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

11.3K
Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents
04:37

Comprehensive Understanding of Inactivity-Induced Gait Alteration in Rodents

Published on: July 6, 2022

2.8K
  • Trained the ViTPose-L deep learning model on 20,000 markerless images and validated against veterinarian-placed markers.

    • Main Results:

    • The markerless model achieved high accuracy: 96.6% mean average precision, 2.29 mean normalized keypoint error, and 92.62% correct keypoints.
    • Performance surpassed existing benchmarks on public datasets.
    • Demonstrated strong canine landmark localization accuracy compared to 2-D marker-based data.

    Conclusions:

    • The deep learning markerless gait analysis system shows promising early-stage accuracy for canine landmark localization.
    • This technology has potential clinical utility for canine gait assessment.
    • Further validation across diverse breeds and environments is recommended before routine clinical adoption.