Three dimensional reconstruction method of human body surface under complex scene

Abstract

The invention relates to a three dimensional reconstruction method of human body surface under a complex scene. The invention automatically extracts the three dimensional information of the human bodysurface on the basis of robust image foreground extraction and information fusion theory. Firstly, the foreground image of a human body target is extracted from a multiple-view image collected by each camera, the probability of the foreground and background to which each point belongs is calculated to obtain the foreground similarity probability graph; then, the information of each view is fusedto calculate the occupation probability of space voxel by a human body, so that the three dimensional surface of the human body is reconstructed. The invention has the advantages of easy realization,strong robustness, high precision, high reconstruction speed and the like and can provide quick and reliable three dimensional surface of the human body in relevant application fields, such as man-machine interaction, virtual reality, human body information digitization, human body kinematic analysis and the like.

Description

technical field [0001] The invention relates to a three-dimensional reconstruction method of a human body surface in complex scenes, which can be widely used in the fields of human-computer interaction, virtual reality, digitization of human body information, video coding, human body motion analysis and the like. It belongs to the field of 3D reconstruction. Background technique [0002] With the increasing degree of social informatization and digitization, and the development of software and hardware technologies in the field of computer vision, relying on a single two-dimensional image information of a single human body collected by a single camera has been unable to meet more advanced applications. Using multiple cameras to collect three-dimensional information of the human body can simultaneously obtain information such as the size, spatial orientation, and color of the human body, providing information for related industries and fields (human-computer interaction, virtu...

AI Technical Summary

Problems solved by technology

However, the method based on a single silhouette has a big disadvantage: the anti-interference ability to noise and complex background is not strong, and the foreground extraction is difficult

But this method has two important disadvantages: First, this algorithm is very sensitive to the accuracy of camera calibration, and low calibration accuracy will cause the algorithm to crash

Second, this algorithm has high computational complexity and slow speed

Images