Recovering the 3D coordinates of various joints of the human body from an image is a critical first step for several model-based human tracking and optical motion capture systems....
We propose a method to find candidate 2D articulated model configurations by searching for locally optimal configurations under a weak but computationally manageable fitness functi...
We present a parametric method to automatically identify people in monocular low-resolution video by estimating the height and stride parameters of their gait. Stride parameters (...
In this paper we suggest a new approach for recovering 3-D depth from a field of surface normals. The surface normals are extracted from Synthetic Aperture Radar (SAR) images usin...
We propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition appro...
Jamie Shotton, Andrew Fitzgibbon, Mat Cook, Andrew...