Semantic-guided automatic data acquisition for Terrestrial Laser Scanners in Civil Engineering

IF 9.6 1区工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY

Automation in Construction Pub Date : 2025-06-12 DOI:10.1016/j.autcon.2025.106337

Yan Xu , Yifeng Wang , Jianjun Yang , Tong Yu , Jian Zhang

{"title":"Semantic-guided automatic data acquisition for Terrestrial Laser Scanners in Civil Engineering","authors":"Yan Xu , Yifeng Wang , Jianjun Yang , Tong Yu , Jian Zhang","doi":"10.1016/j.autcon.2025.106337","DOIUrl":null,"url":null,"abstract":"<div><div>Terrestrial Laser Scanning (TLS) captures precise geometric data for civil infrastructures on status monitoring and digital model creation. However, TLS data collection requires manually setting the scanning range, which limits automation and can lead to redundant background data. This paper introduces an image semantic-guided TLS scanning mode for completely automatic data acquisition. Leveraging a vision-language large model, the measured structure, initialised as a text prompt of structure type, is projected into an image semantic mask. Based on the camera-TLS calibration, the image semantic mask is mapped into a 3D region within the TLS. The resulting multi-segment angular scan ranges are programmed into the TLS to conduct the scan. The effectiveness of text-driven image semantic segmentation is validated in common civil scenarios, including buildings, bridges, dams, and construction sites. The proposed automatic scanning mode is also tested at two construction sites, specifically targeting bridge's precast pier and a tower crane.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"177 ","pages":"Article 106337"},"PeriodicalIF":9.6000,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Automation in Construction","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0926580525003772","RegionNum":1,"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

Terrestrial Laser Scanning (TLS) captures precise geometric data for civil infrastructures on status monitoring and digital model creation. However, TLS data collection requires manually setting the scanning range, which limits automation and can lead to redundant background data. This paper introduces an image semantic-guided TLS scanning mode for completely automatic data acquisition. Leveraging a vision-language large model, the measured structure, initialised as a text prompt of structure type, is projected into an image semantic mask. Based on the camera-TLS calibration, the image semantic mask is mapped into a 3D region within the TLS. The resulting multi-segment angular scan ranges are programmed into the TLS to conduct the scan. The effectiveness of text-driven image semantic segmentation is validated in common civil scenarios, including buildings, bridges, dams, and construction sites. The proposed automatic scanning mode is also tested at two construction sites, specifically targeting bridge's precast pier and a tower crane.

Abstract Image

查看原文本刊更多论文

土木工程中地面激光扫描仪语义引导自动数据采集

地面激光扫描（TLS）技术为民用基础设施的状态监测和数字模型创建提供精确的几何数据。然而，TLS数据采集需要手动设置扫描范围，这限制了自动化，并可能导致冗余的后台数据。介绍了一种基于图像语义引导的TLS扫描模式，实现了数据的全自动采集。利用视觉语言大模型，将测量的结构初始化为结构类型的文本提示，并将其投影到图像语义掩码中。在摄像机-TLS标定的基础上，将图像语义掩码映射到TLS内的三维区域。产生的多段角扫描范围被编程到TLS中进行扫描。文本驱动图像语义分割的有效性在常见的民用场景中得到验证，包括建筑物、桥梁、水坝和建筑工地。本文还在两个施工现场对所提出的自动扫描模式进行了测试，具体针对桥梁的预制墩和塔吊。

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

Automation in Construction 工程技术-工程：土木

CiteScore

19.20

自引率

16.50%

发文量

563

审稿时长

8.5 months

期刊介绍： Automation in Construction is an international journal that focuses on publishing original research papers related to the use of Information Technologies in various aspects of the construction industry. The journal covers topics such as design, engineering, construction technologies, and the maintenance and management of constructed facilities. The scope of Automation in Construction is extensive and covers all stages of the construction life cycle. This includes initial planning and design, construction of the facility, operation and maintenance, as well as the eventual dismantling and recycling of buildings and engineering structures.