High-quality non-intrusive human motion capture is necessary for acquistion of model-based free-viewpoint video of human actors. Silhouette-based approaches have demonstrated that...
Christian Theobalt, Joel Carranza, Marcus A. Magno...
This paper proposes a method for the rapid and precise estimation of human hand postures by combining 2-D appearance matching and 3-D model-based fitting. First a rough posture e...
We propose a generative statistical approach to human motion modeling and tracking that utilizes probabilistic latent semantic (PLSA) models to describe the mapping of image featu...
Abstract. There has been much effort invested in increasing the robustness of human body tracking by incorporating motion models. Most approaches are probabilistic in nature and se...