Reconstructing Three-Dimensional Human Poses: A Combined Approach of Iterative Calculation on Skeleton Model and Conformal Geometric Algebra

Abstract

Reconstructing three-dimensional (3D) human poses is an essential step in human bodyanimation. The purpose of this paper is to fill the gap in virtual reality research by reconstructingpostures in a high-precision human model. This paper presents a new approach for 3D human posereconstruction based on the iterative calculation of a skeleton model and conformal geometric algebra,captured by a monocular camera. By introducing the strip information of clothes and prior data ofdifferent human limbs, the location of joint points on the human body will not be affected by theocclusion problem. We then calculate the 3D coordinates of joint points based on the proposed methodof the iterative calculation of the skeleton model, which can solve the high-cost problem caused by theneed for multiple cameras or a depth camera. Subsequently, we utilize high-performance conformalgeometric algebra (CGA) in relation to rotation transformations in order to improve the adjustmentof the postures of the human limbs. Finally, realistic 3D human poses are reconstructed—specifically,the motion of the human limbs—using a rigid transformation of CGA and a smooth connection ofthe limb parts based on a high-precision model. Compared with the existing methods, the proposedapproach can obtain satisfactory and realistic 3D human pose estimation results using grid models.