Voxel data based marker-less human motion capture using geometry model

In this paper, we propose a novel approach for human posture estimation using geometry model. A volumetric reconstruction of a participant is obtained from multi-camera images. After definition of body model, the geometry model is fitted into the 3D human reconstructed volume. The gray theory, which is applicable to the prediction problem of a time-varying nonlinear system, is utilized to perform the forecasting job during tracking. Moreover, a hierarchical estimation is applied to avoid local optimum. Finally the posture is gained from the geometric parameter. Experimental results show the efficiency of the proposed algorithm and precision of posture estimation.