Multiview human pose estimation with unconstrained motions

We present a system for human pose estimation by using a single frame and without making assumptions on temporal coherence. The system uses 3D voxel data reconstructed from multiple synchronized video streams as input, and computes, for each frame, a skeleton model which best fits the body pose. This system adopts a hierarchical approach where the head and torso locations are found first based on template fitting with their specific shapes and dimensions. It is followed by a limb detection procedure that estimates the pose parameters of four limbs. However, a problem generally faced with skeleton models is the means to find adequate measurements to fit the model. In this paper, voxel data, together with two novel local shape features, are used for this purpose. Experiments show that this system is robust to several perturbations associated with the input data, such as voxel reconstruction errors and complex poses with self-contact, and also allows unconstrained motions, such as fast or unpredictable movements.