Aircraft part three-dimensional reconstruction method based on multi-view stereo vision

Abstract

The invention discloses an aircraft part three-dimensional reconstruction method based on multi-view stereo vision, which comprises the following steps: collecting images of a tray and multi-aircraftparts based on multi-view stereo vision, and carrying out integral modeling on the tray and the multi-aircraft parts to obtain a three-dimensional model; Meanwhile, performing image segmentation and data acquisition of a complex background on the acquired two-dimensional image; And based on the two-dimensional segmented image and the three-dimensional model, segmenting the three-dimensional model,and completing the acquisition of each three-dimensional part and the positioning of the space coordinates. According to the method, the part identification work of full-automatic aircraft part spraying can be effectively solved, and all supports are provided for matching, spraying track extraction and mechanical arm positioning in a subsequent part model library.

Description

technical field [0001] The invention relates to the technical field of three-dimensional reconstruction, in particular to a method for three-dimensional reconstruction of aircraft parts based on multi-eye stereo vision. Background technique [0002] According to the actual production line, the current aircraft parts spraying industry is still based on the manual spraying assembly line, which is carried out through manual identification, decoration, spraying, and flipping. In order to realize the fully automatic production of aircraft parts spraying, design and develop the method of machine vision to realize the part recognition and complete the specific spraying track operation with the robot arm for each part. [0003] 1. 3D reconstruction technology [0004] With the continuous development of computer vision, the continuous innovation of 3D reconstruction technology has been promoted. 3D reconstruction technology mainly obtains the real information of the outside world t...

AI Technical Summary

Problems solved by technology

[0027] (2) To extract the size of each part, determine whether the part is offset, and determine the positioning coordinates of the part, it is necessary to obtain the contour information of the part. This problem cannot be solved directly based on edge detection and image segmentation. First, There are many types of parts, and secondly, the background color of the grid tray is the same as that of the parts, and it is more complicated than the appearance of the parts

[0028] (3) Model-based segmentation Due to the problems similar to the above-mentioned image segmentation, it faces great interference in 3D segmentation, and at the same time cannot obtain accurate positioning information and contour information for model segmentation

Images