Human body real-time modeling system and modeling method based on dual kinect and rotating platform

Abstract

The invention provides a human body real-time modeling system and a modeling method thereof adopting a dual kinect and a rotating platform, comprising a geometric reconstruction module; a camera calibration module; a texture mapping module, etc. Through human body scanning, filtering and denoising, camera tracking and calibration, point cloud fusion and texture mapping, the final three-dimensionalhuman body model is obtained. The invention has the following advantages: the traditional ICP algorithm is improved, the speed of three-dimensional model reconstruction is accelerated, and the requirement of computer configuration is lowered; the real-timeness of human body reconstruction system is kept, the human body model is reconstructed in a short time, the requirement for stationary remaining for a long time on people is loweed, and no special clothes or props are needed; a cheap, fully automatic human body reconstruction system is built and developed, breaking through the traditionalhuman body reconstruction program funding, accuracy constraints; On the basis of geometric reconstruction, the high-quality texture is reconstructed by using the high-fidelity color image provided byKinect.

Description

technical field [0001] The invention relates to the field of computerized human body three-dimensional model reconstruction, in particular to a human body real-time modeling system and a modeling method using double Kinects and rotating platforms. Background technique [0002] Human body 3D model reconstruction has been a research hotspot in the fields of computer vision and photogrammetry. It is widely used in many aspects such as virtual fitting, game character model construction, and 3D printing of medical human organs. [0003] There are many traditional human body 3D reconstruction methods, such as methods based on 3D laser scanners, methods based on image matching, methods based on structured light systems, etc. However, these methods have great limitations. The methods based on 3D laser scanners are expensive and texture mapping is difficult. The method based on image matching cannot extract the surface features of the human body, and the reconstruction time period i...

AI Technical Summary

Problems solved by technology

However, this method has high requirements on machine performance, and it is prone to unresponsive situations on ordinary machines

At the same time, the 3D human body model obtained by this method is only a point cloud model without any texture features.

Therefore, the stability is not good and the scope of application is limited

Images