Identifying lameness in horses through deep learning

Animal pose estimation is important to understand animal behavior and injury. This is especially the case with horse lameness. In the past, studies have focused on combining trackable markers on animals with high-speed cameras to support gait detection. This is time consuming and often impractical. This paper explores the feasibility of using deep learning for markerless motion tracking. We trained a neural network to locate a horse's body parts, then analyzed whether the horse was lame based on their motion trajectory. Different animal pose estimation methods were studied using two state of the art convolutional network models. This paper presents the results of this work. A mobile application was also developed to test the practical application of marker-less recognition technology for detecting lameness in horses.

[1]  Kevin M. Cury,et al.  DeepLabCut: markerless pose estimation of user-defined body parts with deep learning , 2018, Nature Neuroscience.

[2]  H C Schamhardt,et al.  Head and trunk movement adaptations in horses with experimentally induced fore- or hindlimb lameness. , 1996, Equine veterinary journal.

[3]  Mikhail Kislin,et al.  Fast animal pose estimation using deep neural networks , 2018, Nature Methods.

[4]  Ephraim Maltz,et al.  Automatic lameness detection based on consecutive 3D-video recordings , 2014 .

[5]  Rich Caruana,et al.  An empirical comparison of supervised learning algorithms , 2006, ICML.

[6]  K. Keegan,et al.  Computer-assisted kinematic evaluation of induced compensatory movements resembling lameness in horses trotting on a treadmill. , 2005, American journal of veterinary research.

[7]  T D Albright,et al.  Visual motion perception. , 1995, Proceedings of the National Academy of Sciences of the United States of America.

[8]  Jing Hu,et al.  Detection of Workers Without the Helments in Videos Based on YOLO V3 , 2019, 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[9]  Shaon Bhatta Shuvo,et al.  MobileNet Model for Classifying Local Birds of Bangladesh from Image Content Using Convolutional Neural Network , 2019, 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT).

[10]  Lei Cheng,et al.  Some new deformation formulas about variance and covariance , 2012, 2012 Proceedings of International Conference on Modelling, Identification and Control.

[11]  G. Baxter.  Manual of Equine Lameness , 2022 .

[12]  Francesco Fioranelli,et al.  Animal Lameness Detection With Radar Sensing , 2018, IEEE Geoscience and Remote Sensing Letters.

[13]  Mohit Sewak,et al.  Practical Convolutional Neural Networks: Implement advanced deep learning models using Python , 2018 .

[14]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Dit-Yan Yeung,et al.  Learning a Deep Compact Image Representation for Visual Tracking , 2013, NIPS.

[16]  OpenStaxCollege.  Skewness and the Mean, Median, and Mode , 2013 .

[17]  J. Kidd.  Lameness in horses , 2011, Veterinary Record.

[18]  P. R. Weeren,et al.  Vertical movement symmetry of the withers in horses with induced forelimb and hindlimb lameness at trot , 2018, Equine veterinary journal.

[19]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[20]  Paolo Napoletano,et al.  CNN-based features for retrieval and classification of food images , 2018, Comput. Vis. Image Underst..

[21]  Matthias Bethge,et al.  Using DeepLabCut for 3D markerless pose estimation across species and behaviors , 2018 .

[22]  Yoshiharu Yonezawa,et al.  Evaluation of a sensor-based system of motion analysis for detection and quantification of forelimb and hind limb lameness in horses. , 2004, American journal of veterinary research.

[23]  Yoshiharu Yonezawa,et al.  Assessment of repeatability of a wireless, inertial sensor-based lameness evaluation system for horses. , 2011, American journal of veterinary research.

[24]  Daniel Berckmans,et al.  Comparison of a three-dimensional and two-dimensional camera system for automated measurement of back posture in dairy cows , 2014 .

[25]  Huosheng Hu,et al.  Human motion tracking for rehabilitation - A survey , 2008, Biomed. Signal Process. Control..

[26]  Andrea Fossati,et al.  Consumer Depth Cameras for Computer Vision , 2013, Advances in Computer Vision and Pattern Recognition.

[27]  Joseph Redmon,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[28]  Thomas Beth,et al.  Characteristics in human motion - from acquisition to analysis , 2003 .

[29]  Dongjian He,et al.  Lameness detection of dairy cows based on the YOLOv3 deep learning algorithm and a relative step size characteristic vector , 2020 .

[30]  H C Schamhardt,et al.  Modeling study of compensatory head movements in lame horses. , 1997, American journal of veterinary research.

[31]  Jumpei Matsumoto,et al.  Primate Markerless Pose Estimation and Movement Analysis Using DeepLabCut , 2019, 2019 Joint 8th International Conference on Informatics, Electronics & Vision (ICIEV) and 2019 3rd International Conference on Imaging, Vision & Pattern Recognition (icIVPR).

[32]  Joel Grus,et al.  Data Science from Scratch: First Principles with Python , 2015 .

[33]  Jacob M. Graving,et al.  DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning , 2019, bioRxiv.

[34]  S. May,et al.  Identification of hindleg lameness. , 1987, Equine veterinary journal.

[35]  Ali Al-Sherbaz,et al.  Sensor Data Classification for the Indication of Lameness in Sheep , 2017, CollaborateCom.