RGBD camera-based three-dimensional human body rapid modeling system

Abstract

The invention discloses an RGBD camera-based three-dimensional human body rapid modeling system. The system is executed through the following steps of: establishing a scanning array by utilizing a plurality of RGB-D cameras; calibrating the scanning array by using an automatic calibration technology, so as to obtain a calibrated matrix and automatically guide the calibrated matrix into a scanning system; enabling the RGB-D cameras in the array to independently scan a target object after the scanning is started, so as to obtain point cloud data of corresponding poses; processing the acquired point cloud data by utilizing a point cloud optimization technology, so as to obtain high-quality point clouds which can be used for triangular meshing; realizing reconstruction from the point clouds to a triangular patch model by utilizing a rapid triangular meshing algorithm; and obtaining a colored three-dimensional human body model by utilizing a color mapping technology. According to the system disclosed by the invention, a technology which is used for constructing the scanning matrix on the basis of the plurality of RGB-D cameras, rapidly acquiring human body feature data and realizing the construction of the human body three-dimensional model with high precision and refined color texture is provided.

Description

technical field [0001] The invention belongs to the interdisciplinary research field, is an important application of mechanical measurement, computer graphics, and image processing in engineering, and particularly relates to a three-dimensional human body rapid modeling system based on an RGBD camera. Background technique [0002] With the development of stereo vision technology and the gradual popularization of coordinate measurement equipment such as 3D scanners and laser radars, the acquisition of 3D point cloud models is getting faster and faster. At present, common depth image acquisition methods are divided into contact type and non-contact type, and non-contact type is further divided into active scanning and passive scanning. Non-contact active scanning commonly includes handheld laser systems, TOF (Time-of-Flight) cameras, structured light systems, and depth sensors. The handheld laser system emits a laser point or a linear laser beam on the object to be measured, ...

AI Technical Summary

Problems solved by technology

[0003] Existing 3D human body reconstruction technology uses one or two 3D scanners to cooperate with the turntable to realize the 3D feature scanning of the human body, and further realize the reconstruction of the 3D human body model; this method is limited by the rotation time of the turntable, and the scanning time is relatively long. At the same time, it is required that the scanning object should remain in a static state for a long time while scanning, which is not conducive to practical application

[0004] Or through the combination of low-resolution image contour and depth data, and then use the existing 3D human body template model to estimate the human body shape, and further realize 3D reconstruction. This method is not very accurate, and details such as faces and clothing are not obvious

Images