Founded in 1971 >
Chinese Sci-tech Core Periodicals >
British Science Abstracts (SA, INSPEC) Indexed Journals >
United States, Cambridge Scientific Abstract: Technology (CSA: T) Indexed Journals >
United States, Ulrich's Periodicals Directory(UPD)Indexed Journals >
United States, Cambridge Scientific Abstract: Natural Science (CSA: NS) Indexed Journals >
Poland ,Index of Copernicus(IC) Indexed Journals >
International Standard Serial Number:
ISSN 1001-4551
Sponsor:
Zhejiang University;
Zhejiang Machinery and Electrical Group
Edited by:
Editorial of Journal of Mechanical & Electrical Engineering
Chief Editor:
ZHAO Qun
Vice Chief Editor:
TANG ren-zhong,
LUO Xiang-yang
Tel:
86-571-87041360,87239525
Fax:
86-571-87239571
Add:
No.9 Gaoguannong,Daxue Road,Hangzhou,China
P.C:
310009
E-mail:
meem_contribute@163.com
Abstract: Structure from motion (SfM) is a monocular multi-view technique for 3D reconstruction. Aiming at the problem of address speed and quality issues in SfM multi-view 3D reconstruction, an optimized method for improving the accuracy of SfM 3D reconstruction was proposed, taking the image capture of end-of-life components into consideration. Firstly, an experimental platform for image acquisition was established, guide shoes and camshaft cover were selected as the objects of study. Four key parameters were identified for their influence on the quality of reconstruction: image quality, number of images, shooting distance, and the number of viewpoints. Each of these factors was evaluated at three different levels, and an orthogonal experiment was designed. Then, in accordance with the experimental design, nine sets of images were collected for each of the two test subjects. These images were then processed using Reality Capture software to perform 3D modeling. Finally, the reconstruction results were evaluated based on three key metrics: the accuracy of the reconstructed point cloud and the model, the completeness of the reconstruction, and the efficiency of the reconstruction process. Orthogonal experiments were conducted, and the optimal parameter combination was obtained through range analysis. The research findings indicate that the number of images and the number of viewpoints significantly influence the quality of the 3D reconstruction. In contrast, the shooting distance and the quality of the images were found to have a less significant impact on the quality of the 3D reconstruction. These findings offer a reference for enhancing the speed and quality of imagebased 3D reconstruction.
Key words: monocular multiview; 3D reconstruction quality; 3D reconstruction speed; structure from motion (SfM); orthogonal experiment; images number; viewpoints number