Three-dimensional model reconstruction method and device

Abstract

The invention discloses a three-dimensional model reconstruction method and device. The method comprises the steps of acquiring a first preset number of single lattice point projection images of a target object, and the single lattice point projection images are acquired based on a preset single lattice point projection image acquisition rule; Performing lattice point detection on each single lattice point projection image to obtain a plurality of lattice points; Wherein the lattice points are in one-to-one correspondence with the single lattice point projection images; And performing three-dimensional reconstruction on the target object based on the plurality of lattice points to obtain a three-dimensional model of the target object. The device is used for executing the method. Accordingto the three-dimensional model reconstruction method and device provided by the invention, the three-dimensional model reconstruction precision is improved.

Description

technical field [0001] The invention relates to the field of computer vision three-dimensional reconstruction, in particular to a three-dimensional model reconstruction method and device. Background technique [0002] 3D reconstruction technology refers to the use of cameras, projectors, laser scanners and other equipment to directly or indirectly obtain the depth of field data of the object to be reconstructed, and then establish a 3D model of the object through point cloud stitching and other technologies. As an important branch of computer vision technology, 3D reconstruction technology has a wide range of applications in augmented reality, cultural relic protection, industrial automation and robot applications. [0003] In the prior art, there are already a variety of 3D reconstruction methods, including a stereo vision method, a structured light method, and a Time of Flight (ToF for short) method. Stereo vision method is a commonly used 3D reconstruction method, includ...

AI Technical Summary

Problems solved by technology

However, the structured light method requires the projected structured light to be closer to the measurement distance of the object to be measured, because the farther the object to be measured is from the camera, the larger the projected pattern on the object will be, resulting in poorer accuracy of the acquired image. The accuracy of the corresponding 3D reconstruction is also worse, and this method is susceptible to the influence of smooth plane reflection when the object is reconstructed, which will further reduce the accuracy of reconstruction

ToF refers to the method of obtaining the distance by measuring the flight time interval between the transmitted signal and the received signal under the premise of a certain speed of light and sound. The transmitted signal can be ultrasonic or infrared, etc. However, the resolution of the ToF camera is very Low, and the ToF camera is easily affected by environmental factors, such as mixed pixels, external light sources, etc., resulting in inaccurate scene depth and low accuracy of 3D reconstruction

At the same time, the above-mentioned 3D reconstruction methods require point cloud stitching after the data is collected, and the stitching process needs to obtain the pose relationship between point clouds, and the pose between point clouds needs to rely on the position of external devices relationship, such as the positional relationship between the camera and the camera or the positional relationship between the camera and the projector. However, the pose relationship obtained by the above methods is not accurate enough, which will affect the accuracy of the final 3D model stitching.

Images