Adaptive Directional Walks For Pose Estimation From Single Body Depths
Jaehwan Kim, Jun-Suk Lee · 2020
In this paper, we introduce a novel body pose estimation method based on single depth images with our proposed random forest classifier, whereby it is possible to estimate the positions of joints directly with significant accuracy. We train randomized classification trees based on ajoint entropy objective function combined with the geodesic distances and directional vectors simultaneously, to estimate the probability distribution for the label of the directional vector towards a particular bodyjoint by considering the geodesic structural information. At a test step, an arbitrary point moves as much as the magnitude of the probability predicted adaptively by following the predefined kinematic graph, which is referred to as adaptive directional walks. Numerical and visual experiments with real datasets confirm the usefulness of the proposed method.