Cascaded regression for 3D pose estimation for mouse in fisheye lens distorted monocular images

We address the challenging problem of estimating 3D position of laboratory mouse key-points from monocular images acquired through a fisheye lens positioned very close to the mouse `home-cage'. This video acquisition system optical configuration is used when designing practical compact systems for large scale automated monitoring of mice in animal facility ventilated racks. The space constraints in the ventilated racks necessitate the use of fisheye lenses to ensures a more complete view of the home-cage. We extend a cascaded pose regression (CPR) algorithm that has proven to be successful for 2D pose estimation and introduce novel enhancements to the algorithm. Our 3D CPR algorithm reliably generates pose estimates starting from a rough initial pose estimate.