We address the problem of estimating human pose in video sequences, where the rough location of the human has been detected. We exploit both appearance and motion information by defining suitable features of an image and its temporal neighbors, and learning a regression map to the parameters of a model of the human body using boosting techniques. Our work is intended to bridge the gap between e...

Estimation of three-dimensional articulated human pose and motion from images is a central problem in computer vision. Much of the previous work has been limited by the use of crude generative models of humans represented as articulated collections of simple parts such as cylinders. Automatic initialization of such models has proved difficult and most approaches assume that the size and shape o...

Learning body shape models from real-world data Brett Allen Co-Chairs of Supervisory Committee: Associate Professor Brian Curless Department of Computer Science and Engineering Associate Professor Zoran Popović Department of Computer Science and Engineering Creating realistic human characters is one of the most challenging topics in computer graphics, due to the subtleties of human motion and a...

This paper proposes a new method for model-based tracking of a human body in 3D motion from multiple views. The tracking is performed by estimating the pose increment of the body parts from multiple image sequences after establishing of tting an articulated model to the human body at the initial frame. The pose increment can be obtained from solving a system of linear equations. This calculatio...

The authors formulate the body pose estimation as a multi-dimensional nonlinear optimization problem, suitable to be approximately solved by a meta-heuristic, specifically, the particle swarm optimization (PSO). Starting from multi-view video sequences acquired in a studio environment, a full skeletal configuration of the human body is retrieved. They use a generic subdivision-surface body mode...