Remarks on 3D human body’s feature extraction from voxel reconstruction of human body posture

This paper investigates a human body posture estimation method based on back projection of human silhouette images extracted from multi-camera images. The multi-camera system consists based on a server-client system with local network of 1000 Base-T to achieve voxel reconstruction of 3D human body posture in real-time. In order to estimate feature points of the human body in the 3D space, the Reeb graph approach is applied to the voxel reconstruction of human body. To evaluate our proposed human body posture estimation method, 3D reconstruction experiments of human body posture and extraction experiments of human body´s feature points are carried out. The experimental system with six CCD cameras is composed and the experimental results confirm both the feasibility and effectiveness of the proposed system in the 3D human body posture estimation.