In this paper we present our preliminary work on model- based behavioral analysis of horse motion. Our approach is based on the SMAL model [21], a 3D articulated statistical model of animal shape. We define a novel SMAL model for horses based on a new template, skeleton and shape space learned from 37 horse toys. We test the accuracy of our hS- MAL model in reconstructing a horse from 3D mocap data and images. We apply the hSMAL model to the problem of lameness detection from video, where we fit the model to im- ages to recover 3D pose and train an ST-GCN network [17] on pose data. A comparison with the same network trained on mocap points illustrates the benefit of our approach.

@article{li2021hsmal,

title={hSMAL: Detailed horse shape and pose reconstruction for motion pattern recognition},

author={Li, Ci and Ghorbani, Nima and Broom{\'e}, Sofia and Rashid, Maheen and Black, Michael J and Hernlund, Elin and Kjellstr{\"o}m, Hedvig and Zuffi, Silvia},

journal={arXiv preprint arXiv:2106.10102},

year={2021}

}

For questions, please contact Ci Li: cil@kth.se