Pose estimation, tracking, and action recognition of articulated objects from depth images are important and challenging problems, which are normally considered separately. In this paper, a unied paradigm based on Lie group theory is proposed, which enables us to collectively address these related problems. Our approach is also applicable to a wide range of articulated objects. Empirically it is evaluated on lab animals including mouse and sh, as well as on human hand. On these applications, it is shown to deliver competitive results compared to the state-of-the-arts, and non-trivial baselines including convolutional neural networks and regression forest methods. Moreover, new sets of annotated depth data of articulated objects are created which, together with our code, are made publicly available.
International Journal of Computer Vision, 2016