Optimizing 3D reconstruction: Application of a vision foundation model for dimensional measurement

IF 4 2区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Journal of Constructional Steel Research Pub Date : 2024-10-23 DOI:10.1016/j.jcsr.2024.109087

Yan Zeng , Zhengqi Hua , Zejun Xiang , Yue Liao , Feng Huang , Xiaocheng Guo , Yingchuan Peng , Xuesi Liu

{"title":"Optimizing 3D reconstruction: Application of a vision foundation model for dimensional measurement","authors":"Yan Zeng , Zhengqi Hua , Zejun Xiang , Yue Liao , Feng Huang , Xiaocheng Guo , Yingchuan Peng , Xuesi Liu","doi":"10.1016/j.jcsr.2024.109087","DOIUrl":null,"url":null,"abstract":"<div><div>This study applies a vision foundation model to optimize the Point Cloud Data (PCD) reconstruction pipeline in digital photogrammetry, aiming to overcome the challenges of component PCD acquisition in Small and Medium Construction Projects (SMCP). A hardware device is designed and assembled for overlapping image acquisition. In order to alleviate computational and storage burdens, a vision foundation model is utilized for Region of Interest (ROI) selection before PCD reconstruction, for which a set of prompt optimization methods based on image similarity is proposed. The scale of the reconstructed PCD is calibrated based on the camera pose, enabling precise dimension measurement of the PCD. Two case studies confirm the effectiveness of the optimized method for dimension measurement, with tolerance below 2 mm, corresponding to 6.7 times the pixel accuracy. Furthermore, this method demonstrates substantial improvements in image storage, decreasing by over 84 %, and decreases of over 55 % in PCD storage and over 50 % in the computational time required for reconstruction. These outcomes underscore the practicality and efficiency of the introduced framework in addressing the challenges posed by batch component dimension measurement.</div></div>","PeriodicalId":15557,"journal":{"name":"Journal of Constructional Steel Research","volume":"224 ","pages":"Article 109087"},"PeriodicalIF":4.0000,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Constructional Steel Research","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0143974X24006370","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

This study applies a vision foundation model to optimize the Point Cloud Data (PCD) reconstruction pipeline in digital photogrammetry, aiming to overcome the challenges of component PCD acquisition in Small and Medium Construction Projects (SMCP). A hardware device is designed and assembled for overlapping image acquisition. In order to alleviate computational and storage burdens, a vision foundation model is utilized for Region of Interest (ROI) selection before PCD reconstruction, for which a set of prompt optimization methods based on image similarity is proposed. The scale of the reconstructed PCD is calibrated based on the camera pose, enabling precise dimension measurement of the PCD. Two case studies confirm the effectiveness of the optimized method for dimension measurement, with tolerance below 2 mm, corresponding to 6.7 times the pixel accuracy. Furthermore, this method demonstrates substantial improvements in image storage, decreasing by over 84 %, and decreases of over 55 % in PCD storage and over 50 % in the computational time required for reconstruction. These outcomes underscore the practicality and efficiency of the introduced framework in addressing the challenges posed by batch component dimension measurement.

查看原文本刊更多论文

优化 3D 重建：应用视觉基础模型进行尺寸测量

本研究应用视觉基础模型优化数字摄影测量中的点云数据（PCD）重建流水线，旨在克服中小型建设项目（SMCP）中点云数据组件采集的挑战。设计并组装了用于重叠图像采集的硬件设备。为了减轻计算和存储负担，在 PCD 重建前利用视觉基础模型进行感兴趣区域（ROI）选择，并为此提出了一套基于图像相似性的及时优化方法。重建后的 PCD 的比例根据相机姿态进行校准，从而实现了 PCD 的精确尺寸测量。两个案例研究证实了优化方法在尺寸测量方面的有效性，公差低于 2 毫米，相当于像素精度的 6.7 倍。此外，该方法在图像存储方面也有显著改善，减少了 84% 以上，PCD 存储减少了 55% 以上，重建所需的计算时间减少了 50% 以上。这些成果凸显了所引入的框架在应对批量元件尺寸测量所带来的挑战方面的实用性和高效性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Constructional Steel Research 工程技术-工程：土木

CiteScore

7.90

自引率

19.50%

发文量

550

审稿时长

46 days

期刊介绍： The Journal of Constructional Steel Research provides an international forum for the presentation and discussion of the latest developments in structural steel research and their applications. It is aimed not only at researchers but also at those likely to be most affected by research results, i.e. designers and fabricators. Original papers of a high standard dealing with all aspects of steel research including theoretical and experimental research on elements, assemblages, connection and material properties are considered for publication.