无人机视觉驱动的装配式钢结构柱智能测量

张伟; 谈晗; 章军; 高珂; 朱宏平

doi:10.13206/j.gjgS26072702.R1

无人机视觉驱动的装配式钢结构柱智能测量

doi: 10.13206/j.gjgS26072702.R1

张伟^1,2,
谈晗¹,
章军²,
高珂¹,
朱宏平^1, ,

1. 华中科技大学土木与水利工程学院, 武汉 430074;
2. 中建科工集团有限公司, 广东深圳 518054

基金项目:

中建科工科技研发项目（ZJKG-2024-KT-14）。

详细信息

作者简介:
张伟，硕士，高级工程师，2025010222@hust.edu.cn。

通讯作者:
朱宏平，博士，教授，2011210038@hust.edu.cn。

计量
- 文章访问数: 5
- HTML全文浏览量: 1
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2026-07-27

UAV Vision-Driven Intelligent Measurement for Prefabricated Steel Columns

Zhang Wei^1,2,
Tan Han¹,
Zhang Jun²,
Gao Ke¹,
Zhu Hongping^{1
, ,}

1. School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China;
2. China Construction Science and Industry Co., Ltd., Shenzhen 518054, China

摘要

摘要: 装配式钢结构建造为结构施工提供了高效路径，也对现场安装精度提出更高要求。针对大型施工现场柱构件数量多、传统人工逐点测量效率较低，以及正射影像覆盖范围大、单柱在整幅影像中占比较小的问题，构建了面向矩形钢柱批量测量的两阶段粗到精处理框架。第一阶段采用YOLO11-OBB实现柱构件有向粗定位，并依据柱群方向分布进行图像旋转和粗定位框二次校正，以快速获得包含完整柱顶轮廓且方向统一的局部测量区域；第二阶段利用EdgeNAT获得局部边缘响应，经轮廓精化获得像素级候选角点，并采用二维高斯拟合求解亚像素坐标。该两阶段处理方式将大范围场景中的目标搜索与局部高精度边界测量相分离，主要解决仅依赖目标检测框难以满足尺寸测量精度要求，以及直接对整幅影像进行精细边缘搜索时背景干扰大、处理范围大的问题。两阶段处理完成后，再依据正射影像仿射参数计算构件尺寸，并通过控制点四参数转换输出柱角点工程坐标。某在建工厂项目试验表明，在110 m航高、正射影像地面采样距离（GSD）约18.5 mm/pixel的条件下，以4根柱的钢尺实测值为参考，8个长（宽）尺寸的平均绝对误差和平均相对误差分别为18.75 mm和2.21%。0.074 km²试验区域无人机现场影像采集约11 min，后续正射建模约1.5 h、算法处理约0.5 min，且均可在现场采集完成后离线处理，体现了该方法面向多构件批量复核的自动化作业优势。
- 智能建造 /
- 无人机视觉 /
- 钢结构柱 /
- 施工定位 /
- 尺寸测量
Abstract: Prefabricated steel structure construction provides an efficient path for structural construction and also places higher demands on on-site installation accuracy. To address the large number of column components at large-scale construction sites， the low efficiency of traditional manual point-by-point measurement， the wide coverage of orthophotos， and the small proportion of individual columns in the overall image， this study establishes a two-stage rough-to-fine measurement framework for batch inspection of rectangular steel columns at large-scale construction sites. In the first stage， YOLO11-OBB is used for oriented coarse localization of column components， and image rotation and secondary correction of the coarse localization boxes are performed according to the column-group orientation distribution， so as to rapidly obtain unified local measurement regions containing the complete column-top contours. In the second stage， EdgeNAT is used to obtain local edge responses， pixel-level candidate corners are obtained through contour refinement， and two-dimensional Gaussian fitting is applied to estimate subpixel coordinates.This two-stage processing decouples target search in large-scale scenes and local high-precision boundary measurement into separate tasks， and primarily addresses the difficulty of meeting dimensional measurement accuracy requirements when relying only on detection boxes， as well as the strong background interference and large processing scope encountered when directly searching for precise edges in the full orthophoto. After the two stages， column dimensions are calculated from the orthophoto affine parameters， and column-corner engineering coordinates are output through a four-parameter transformation based on control points. Field experiments under a flight altitude of 110 m and an orthophoto ground sample distance （GSD） of approximately 18.5 mm/pixel showed that， for eight length （width） dimensions of four columns， with tape-measured values as reference， the mean absolute error and mean relative error were 18.75 mm and 2.21%， respectively. UAV image acquisition over the 0.074 km² test area required approximately 11 min， and orthophoto reconstruction and algorithm processing required approximately 1.5 h and 0.5 min， respectively； the latter two steps can be performed offline after field data acquisition， demonstrating the framework’s suitability for automated batch inspection of multiple components.
- smart construction /
- UAV vision /
- steel column /
- construction positioning /
- dimensional measurement

HTML全文

参考文献(16)

[1]	中华人民共和国住房和城乡建设部,中华人民共和国国家发展和改革委员会,中华人民共和国科学技术部,等. 住房和城乡建设部等部门关于推动智能建造与建筑工业化协同发展的指导意见[J]. 建筑监督检测与造价,2020,13（4）:11-14.
[2]	Klasson A,Crocetti R,Hansson E F. Slender steel columns:how they are affected by imperfections and bracing stiffness[J]. Structures,2026,8:35-43.
[3]	张慕尧. 工程测绘中RTK测量技术特点与具体应用[J]. 中华建设,2025（2）:107-109.
[4]	Sestras P,Badea G,Badea A,et al. Land surveying with UAV photogrammetry and LiDAR for optimal building planning[J]. Automation in Construction,2025,173:106092.
[5]	Ersoz A,Pekcan O. UAV-based automated earthwork progress monitoring using deep learning with image inpainting[J]. Automation in Construction,2025,175:106211.
[6]	Jiang S,Cheng Y,Zhang J. Vision-guided unmanned aerial system for rapid multiple-type damage detection and localization[J]. Structural Health Monitoring,2023,22（1）:319-337.
[7]	余加勇,李锋,薛现凯,等. 基于无人机及Mask R-CNN的桥梁结构裂缝智能识别[J]. 中国公路学报,2021,34（12）:80-90.
[8]	李继光. 基于改进YOLOv10的大跨钢结构锈蚀损伤智能实时检测方法研究[J]. 建筑结构,2025,55（24）:129-135.
[9]	肖雄武. 具备结构感知功能的倾斜摄影测量场景三维重建[J]. 测绘学报,2019,48（6）:802.
[10]	孙杰,谢文寒,白瑞杰. 无人机倾斜摄影技术研究与应用[J]. 测绘科学,2019,44（6）:145-150.
[11]	赵永强,饶元,董世鹏,等. 深度学习目标检测方法综述[J]. 中国图象图形学报,2020,25（4）:629-654.
[12]	Khanam R,HussainM. YOLOv11:an overview of the key architectural enhancements[PP/OL]. Vl.（2024-10-23）[ 2026-06-30]. https://arxiv.org/abs/2410.17725.
[13]	Jie J,Guo Y,Wu G,et al. EdgeNAT:transformer for efficient edge detection[PP/OL]. Vl.（2024-08-20）[ 2026-06-30]. https://arxiv.org/abs/2408.10527.
[14]	Canny J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8（6）:679-698.
[15]	Su Z,Liu W,Yu Z,et al. Pixel difference networks for efficient edge detection[PP/OL]. Vl.（2021-08-16）[ 2026-06-30]. https://arxiv.org/abs/2108.07009.
[16]	Pu M,Huang Y,Liu Y,et al. EDTER:edge detection with transformer[PP/OL]. arXiv:2203. 08566 v 1,arXiv,2022-03-16[ 2026-06-30]. https://arxiv.org/abs/2203.08566.