Predictive Modeling of Equine Activity Budgets Using a 3D Skeleton Reconstructed from Surveillance Recordings
This work addresses a domain-specific problem for equine health monitoring, but it is incremental as it applies existing pose estimation methods to a new dataset.
The authors tackled the problem of reconstructing 3D horse poses from surveillance videos to predict equine behavior, achieving results that showed bias towards pain-induced horses in behavioral predictions.
In this work, we present a pipeline to reconstruct the 3D pose of a horse from 4 simultaneous surveillance camera recordings. Our environment poses interesting challenges to tackle, such as limited field view of the cameras and a relatively closed and small environment. The pipeline consists of training a 2D markerless pose estimation model to work on every viewpoint, then applying it to the videos and performing triangulation. We present numerical evaluation of the results (error analysis), as well as show the utility of the achieved poses in downstream tasks of selected behavioral predictions. Our analysis of the predictive model for equine behavior showed a bias towards pain-induced horses, which aligns with our understanding of how behavior varies across painful and healthy subjects.