Learning a deep network with spherical part model for 3D hand pose estimation

Abstract

Hand pose estimation is a hot topic in recent years. It has been widely used in virtual reality since it provides an interface for communication between human and cyberspace. Hand pose estimation is difficult due to some challenges. First, we need to detect human hand which is very changeable. Second, the high degree of freedom leads to difficulties in pose estimation. In this paper, we aim to build a hand pose estimation system which can correctly detect human hand and estimate its pose. We design a model called spherical part model (SPM) and train a deep convolutional neural network using this model. As a result, our network can more accurately estimate hand pose based on prior knowledge of human hand. To demonstrate it, a complete experiment is conducted on two public and one self-build datasets. The results show that our system can outperform other state of the art works.