Motion capture and human pose reconstruction from a single-view video sequence
Digital Signal Processing
| Hi-index | 0.00 |
A framework for realistic rendering of a multi-layered human body model is proposed in this paper. The human model is composed of three layers: skeleton, muscle, and skin. The skeleton layer, represented by a set of joints and bones, controls the animation of the human body using inverse kinematics. Muscles are represented with action lines that are defined by a set of control points. An action line applies the force produced by a muscle on the bones and on the skin mesh. The skin layer is modeled as a 3D mesh and deformed during animation by binding the skin layer to both the skeleton and muscle layers. The skin is deformed by a two-step algorithm according to the current state of the skeleton and muscle layers. Performance experiments show that it is possible to obtain real-time frame rates for a moderately complex human model containing approximately 33,000 triangles on the skin layer.