Three-dimensional human body reconstruction method and system based on parametric human body template and inertia measurement

Abstract

The invention discloses a three-dimensional human body reconstruction method and system based on a template parametric human body template and inertia measurement. The method comprises the following steps of carrying out depth image shooting on a human body to obtain a single depth image; reading the steering measurement reading of an inertial measurement unit bound on the limbs of the human body;obtaining a matching point pair between the three-dimensional point cloud and the vertex of the reconstruction model and the vertex of the parametric human body model; obtaining an energy function and a human body attitude parameter according to the matching point pair and the steering measurement reading; solving the energy function, and aligning the reconstruction model and the vertex of the parametric human body model with the three-dimensional point cloud, so as to obtain a model; optimizing the conversion relation; and updating and supplementing the model through the depth map, and further optimizing human body form parameters of the parameterized human body template. The method is advantageous in that the solution is accurate and robust, the method is simple and feasible, and the running speed is in a real-time manner; and a wide application prospect is provided, and the method can be quickly realized on a hardware system such as a PC (personal computer) or a workstation.

Description

technical field [0001] The invention relates to the technical fields of computer vision and computer graphics, in particular to a three-dimensional human body reconstruction method and system based on parameterized human body templates and inertial measurement. Background technique [0002] Human 3D reconstruction is an important issue in the fields of computer graphics and computer vision. High-quality 3D human body models have broad application prospects and important application values ​​in the fields of film and television entertainment, demographic data analysis and other fields. [0003] However, in related technologies, the acquisition of high-quality human body 3D models is usually achieved by expensive laser scanners or multi-camera array systems. People remain absolutely still, and small movements will lead to obvious errors in the scan results; second, counterfeiting is expensive, and it is difficult to popularize it in the daily lives of ordinary people. Third,...

AI Technical Summary

Problems solved by technology

[0003] However, in related technologies, the acquisition of high-quality human body 3D models is usually achieved by expensive laser scanners or multi-camera array systems. People remain absolutely still, and small movements will lead to obvious errors in the scanning results; second, counterfeiting is expensive, and it is difficult to popularize it in the daily life of ordinary people

Third, the speed is slow, and it takes a long time to reconstruct a 3D human body model; fourth, it cannot handle fast movements. When the human body moves faster, the model reconstruction is often wrong due to inaccurate motion tracking.

Images