冬奥场馆临时支承架体安装质量快速检测

doi:10.13474/j.cnki.11-2246.2023.0080

测绘通报 ›› 2023, Vol. 0 ›› Issue (3): 99-103.doi: 10.13474/j.cnki.11-2246.2023.0080

• 工程测量分会年会（2022年）优选论文 • 上一篇下一篇

冬奥场馆临时支承架体安装质量快速检测

贺亦峰, 邹进贵, 龚小强, 张澜

武汉大学测绘学院, 湖北武汉 430079

收稿日期:2022-07-06 发布日期:2023-04-04
作者简介:贺亦峰(1995-),男,博士生,主要研究方向为数字图像及点云处理。E-mail:heyifeng@whu.edu.cn
基金资助:
国家自然科学基金（41871373）

Rapid inspection on installation quality of temporary support frame in Winter Olympic venues

HE Yifeng, ZOU Jingui, GONG Xiaoqiang, ZHANG Lan

School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, China

Received:2022-07-06 Published:2023-04-04

摘要/Abstract

摘要： 2022北京冬奥会的绝大部分赛事保障基础设施均以临时设施为主，这些临时设施大多建在脚手架上，需要插销实现“骨骼”的固定和连接。然而，整个场馆的插销多达数十万枚，利用人工检测难以实现。因此，迫切需要构建一套能对支承架体上插销的安装质量进行自动快速检测的软件系统。本文提出了一种基于Faster RCNN目标检测网络的插销安装质量检测方法，并自主研发了周转型支承架体安全检测软件及四摄像头组合硬件设备，大大提高了工作效率，不仅实现了自动化安全检查，还保证了97%以上的检测正确率，为冬奥会临时设施安全保驾护航。

关键词: Faster RCNN网络, 安全检测, 自动实时检测, 2022北京冬奥会

Abstract: Most of the infrastructure for the 2022 Beijing Winter Olympics are temporary facilities,which are mainly built on scaffolding. Bolts are required for pinning and linking of "skeletons". However, there are hundreds of thousands of bolts in the entire venue, which means the manual detection is not realistic.Therefore, it is urgent to build a system that can automatically and real-timely detect the installation quality of the bolts on the support frame. A detection method of bolt installation quality based on Faster RCNN target detection network is proposed in this paper. In addition, a support frame safety detection software and four-camera combined hardware equipment are developed independently, which greatly improves work efficiency. The strategy not only realizes automatic safety inspection, but also ensures more than 97% detection accuracy, ensuring the safety of temporary facilities for the Winter Olympics.

Key words: Faster RCNN target detection network, security detection, automatic real-time detection, 2022 Beijing Winter Olympics

中图分类号:

P258

贺亦峰, 邹进贵, 龚小强, 张澜. 冬奥场馆临时支承架体安装质量快速检测[J]. 测绘通报, 2023, 0(3): 99-103.

HE Yifeng, ZOU Jingui, GONG Xiaoqiang, ZHANG Lan. Rapid inspection on installation quality of temporary support frame in Winter Olympic venues[J]. Bulletin of Surveying and Mapping, 2023, 0(3): 99-103.

参考文献

[1] 雍黎, 单倩澜. 冬奥临时设施安全这些"黑科技"保驾护航[N]. 科技日报, 2022-01-07(2).
[2] 龚小强, 邹进贵, 孟丽媛. 基于目标检测和角点检测的近景摄影测量控制点自动提取[J]. 测绘通报, 2020(S1):173-175.
[3] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[4] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). San Diego, CA:IEEE, 2005:886-893.
[5] GIRSHICK R, DONAHUE J, DARRELL T, et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus, OH:IEEE, 2014:580-587.
[6] UIJLINGS J R, VAN DE SANDE K E A, GEVERS T, et al.Selective search for object recognition[J]. International Journal of Computer Vision, 2013, 104(2):154-171.
[7] GIRSHICK R. Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision (ICCV). Santiago:IEEE, 2016:1440-1448.
[8] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
[9] 马京振, 陈换新, 朱新铭, 等. 利用Faster R-CNN进行立交桥自动识别与定位[J]. 测绘通报, 2021(3):28-32.
[10] 程瑞, 高建, 邢强, 等. 一种优化的Faster R-CNN小目标检测方法[J]. 测绘通报, 2021(9):21-27.
[11] 冯小雨, 梅卫, 胡大帅. 基于改进Faster R-CNN的空中目标检测[J]. 光学学报, 2018, 38(6):250-258.
[12] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2022-07-01]. https://arxiv.org/abs/1409.1556.
[13] 王忠塬. 基于改进Faster RCNN的小目标检测技术研究[D]. 长春:长春理工大学, 2021.

冬奥场馆临时支承架体安装质量快速检测

Rapid inspection on installation quality of temporary support frame in Winter Olympic venues

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价