Three-dimensional point cloud reconstruction method and system, electronic equipment and storage medium

Abstract

The invention provides a three-dimensional point cloud reconstruction method and system, electronic equipment and a storage medium. The method comprises the steps: firstly obtaining target object structured light images of a left view field and a right view field of a three-dimensional camera, and determining phase distribution images of the left view field and the right view field based on the target object structured light images; performing layered downsampling on the phase distribution images of the left and right view fields to obtain phase images of multiple levels of the left and right view fields; performing equiphase pixel point matching on the phase image of the lowest level of the left and right view fields, and determining a parallax image of the lowest level; and finally, on the basis of the parallax image of the lowest level, determining the parallax image of the phase distribution images of the left and right view fields, and on the basis of the parallax image of the phase distribution images of the left and right view fields, performing three-dimensional point cloud reconstruction on the target object in the target object structured light image. According to the method, the left and right phase images with multiple resolution levels are used, and high-resolution stereo matching is guided step by step, so that the computing power overhead can be saved, the computing time can be shortened, and the occupied memory can be reduced.

Description

technical field [0001] The present invention relates to the technical field of three-dimensional reconstruction, in particular to a three-dimensional point cloud reconstruction method, system, electronic equipment and storage medium. Background technique [0002] At present, the 3D camera can reconstruct the 3D point cloud of the target scene. Compared with the conventional 2D camera, it has one more depth dimension information, which provides additional data processing freedom for various back-end development, and has important application value. . With the vigorous development of intelligent manufacturing and intelligent interaction technology, 3D cameras have increasingly become an indispensable basic hardware device and core data processing technology, and have broad applications in the fields of industrial manufacturing, biomedicine, mobile payment, and military navigation. Application prospects. [0003] Stereo cameras based on grating structured light have high meas...

AI Technical Summary

Problems solved by technology

In the case of a fixed projected fringe pattern, as the core link in point cloud computing, stereo matching has a relatively large computational overhead, which is not conducive to reducing the time-consuming calculation of 3D cameras, and will take up a lot of memory, greatly increasing the 3D point cloud. cost of refactoring

Images