基于单台Kinect的高精度个性化人体建模方法

提出一种基于单台Kinect的高精度三维人体建模方法。首先使用一台Kinect对人体头部进行扫描，以获取高精度的头部点云数据；其次，在保持头部精确度的基础上对所获取的点云数据进行采样预处理；最后利用层次化的紧支撑径向基函数(CS-RBFs)将采样后的点云与已有的人体躯干进行拟合获得3D人体模型。仿真结果表明，该方法能够提高人体模型的精确度并提高建模速度。

Personalized Human Body Modeling with High Precision Based on Single Kine

A personalized human body modeling method with high precision based on single Kinect is proposed. Firstly, the high-precision point cloud of a human head using single Kinect is obtained. Then, the point cloud is preprocessed based on maintaining the accuracy of the head. Finally, by employing the hierarchical compactly supported radial basis function (CS RBFs), the sampled point cloud is fitted with the existing human body to get 3D human body model. Simulation results show that the proposed method can enhance accuracy and speed of human body modeling.