Real-time Restoration of 3D Human Shape and Posture without Markers

Abstract

The invention relates to a mark-point-free real-time restoration method of a three-dimensional human form and a gesture. The mark-point-free real-time restoration method faces toward a monocular depth video, and real-time restoration of the human form and the gesture is achieved by aid of a human body parameterized model. The mark-point-free real-time restoration method comprises the steps of 1) human body parameterized model extraction, wherein the human body parameterized model is decomposed into a form deformation sub model and a gesture deformation sub model, a human library is used for training the human body parameterized model to solve part of parameters, the characteristic vector parameter of the form deformation sub model is solved, and the weight of each rigid block in the linear skin deformation of the gesture deformation sub model is solved; 2) human body form offline restoration; 3) human body gesture online restoration. Through a linear deformation and variation method, change of each rigid block in the linear skin deformation of the gesture deformation sub model is solved in real time. Therefore, the gesture of a human body is restored on line.

Description

technical field [0001] The present invention belongs to the field of general image data processing, focuses on the restoration of three-dimensional human body shape and posture, and relates to a real-time three-dimensional human body restoration method without using marker points. Background technique [0002] The restoration of 3D human body shape and posture is an important issue in the field of general image data processing. It is a key technology for reconstructing a realistic and personalized virtual human, and it is also an important basis for many application problems such as human body reconstruction and processing. [0003] Personalized modeling of virtual human (also known as avatar) refers to the creation of a three-dimensional geometric model of a virtual human in a computer virtual scene, and the reconstructed virtual human not only has individual morphological characteristics, but also has individual posture characteristics. Then, for personalized modeling of a...

AI Technical Summary

Problems solved by technology

The US8139067B2 patent is mainly used for human body restoration without marker points, but it cannot achieve real-time effects. The data it faces is high-quality point clouds, not rough depth videos that are unavailable; US20110210915 patents can process depth data, but its working purpose is Estimation of human body posture, that is, to determine the joint segmentation of human body depth data, and estimate the human body posture

Therefore, there are no reports on the real-time restoration of the shape and posture of the human body for depth video.

Images