Human 3D Reconstruction and Identification Using Kinect Sensor

摘要

3D model of human body has been widely used in many applications including medical, health and security, since it is able to provide information on human body shape. This paper proposes a method to identify human based on the 3D model of the body and the depth data form the Kinect. The system firstly utilizes the coordinate points from the 3D model to calculate the selected anthropometry features of human body. Then, the features are compared with real time Kinect's depth acquisition to perform pose recognition and human identification. Eight candidates were involved in the reliability test of the system with each of them performed 6 trials, making a total of 48 trials. The overall reliability of the system in identifying the correct candidate was found to be 79.167%.