非接触式单目视觉高精度自动沉降监测

doi:10.13474/j.cnki.11-2246.2025.0524

测绘通报 ›› 2025, Vol. 0 ›› Issue (5): 145-151.doi: 10.13474/j.cnki.11-2246.2025.0524

• 技术交流 • 上一篇

非接触式单目视觉高精度自动沉降监测

宋维凯¹, 柯福阳¹, 魏民², 黄钰洲², 朱尚峻²

1. 南京信息工程大学软件学院, 江苏南京 210044;
2. 南京信息工程大学遥感与测绘工程学院, 江苏南京 210044

收稿日期:2024-09-26 发布日期:2025-06-05
通讯作者: 柯福阳。E-mail:kefuyang@nuist.edu.cn
作者简介:宋维凯(1998—),男,硕士,研究方向为计算机视觉。E-mail:11940756248q9.com
基金资助:
江苏省地质工程环境智能监控工程研究中心开放基金研究计划(2023-ZNIKJ1-08);2022年度第六期“333人才”培养支持资助项目(BRA2022042);江苏省自然资源科技项目(关键技术研发)(JSZRKJ202404)

Non-contact monocular vision high-precision automatic settlement monitoring

SONG Weikai¹, KE Fuyang¹, WEI Min², HUANG Yuzhou², ZHU Shangjun²

1. School of Software, Nanjing University of Information Science and Technology, Nanjing 210044, China;
2. School of Remote Sensing and Surveying Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China

Received:2024-09-26 Published:2025-06-05

摘要/Abstract

摘要： 单目视觉沉降监测是一种新型的非接触式监测方法,然而受背景复杂、基准标靶安装要求高等问题的影响,有时无法满足单目视觉沉降监测的需求。因此,本文提出了一种非接触式单目视觉高精度自动沉降监测方法。首先,在待监测区域安装测量标靶,通过目标检测算法YOLOv10s完成标靶的识别;其次,采用基于边缘的最小二乘椭圆拟合法求解标靶的中心点像素坐标;然后,基于相机成像原理进行推导,通过一种改进的世界坐标计算方法求解标靶中心点像素坐标对应的世界坐标;最后,以监测区域的第1帧图像为基准求解真实的沉降值。通过室外模拟沉降试验,将单目视觉计算值与电子水准仪测量值对比,并以两者的绝对误差作为评价指标,通过改变标靶与相机之间的距离验证其与该方法监测精度的关系。当相机与标靶之间的距离为5 m时,最大绝对误差为2.784 mm,最小绝对误差为0.246 mm;当距离为10 m时,最大绝对误差为4.071 mm,最小绝对误差为0.42 mm。标靶与相机的距离越远精度越低,但在10 m距离、沉降值250 mm以内,该方法的平均绝对误差为1.543 mm。

关键词: 单目视觉, 沉降监测, YOLOv10s, 像素坐标, 世界坐标, 电子水准仪

Abstract: Monocular visual settlement monitoring represents a novel non-contact monitoring approach. Nevertheless, challenges arise from intricate backgrounds and stringent benchmark target installation prerequisites, occasionally impeding the efficacy of this method for settlement monitoring. This paper introduces a non-contact monocular vision method for high-precision automatic settlement monitoring. Initially, the measurement target is positioned within the designated monitoring area, and target identification is achieved utilizing the YOLOv10s target detection algorithm. Subsequently, the edge-based least squares ellipse fitting technique is employed to determine the pixel coordinates of the target's center point. Following this, leveraging the principles of camera imaging, a derivation process is conducted to establish the world coordinates corresponding to the pixel coordinates of the target's center point using an enhanced world coordinate computation approach. Ultimately, the actual displacement value is computed with the initial frame image of the monitored area serving as the reference. Through outdoor simulation settlement experiments, we compare the monocular visual calculated value with the electronic level measurement value, using their absolute error as the evaluation metric. By varying the distance between the camera and the target, we assess the monitoring accuracy of the proposed method. At a distance of 5 m, the maximum absolute error is 2.784 mm, and the minimum is 0.246 mm. When the distance is increased to 10 m, the maximum absolute error rose to 4.071 mm, with a minimum of 0.42 mm. The experimental results demonstrate that as the distance between the target and the camera increases, the accuracy decreases. However, within a distance range of up to 10 m and a settlement value of 250 mm, the average absolute error of the method stands at 1.543 mm.

Key words: monocular vision, settlement monitoring, YOLOv10s, pixel coordinates, world coordinates, electronic level

中图分类号:

P258

宋维凯, 柯福阳, 魏民, 黄钰洲, 朱尚峻. 非接触式单目视觉高精度自动沉降监测[J]. 测绘通报, 2025, 0(5): 145-151.

SONG Weikai, KE Fuyang, WEI Min, HUANG Yuzhou, ZHU Shangjun. Non-contact monocular vision high-precision automatic settlement monitoring[J]. Bulletin of Surveying and Mapping, 2025, 0(5): 145-151.

参考文献

[1] 杨志勇,朱钢.富含生活垃圾土层浅埋暗挖隧道变形实测分析[J].地下空间与工程学报,2023,19(S1):345-352.
[2] 彭仪普,李剑,黄毅,等.边坡开挖支护三维变形监测与数值模拟研究[J].沈阳建筑大学学报(自然科学版),2023,39(6):961-969.
[3] CHAO Tieyan,LIANG Hui,GE Yuwei,et al.An IoT-based early warning system for settlement monitoring using differential pressure static level[C]//Proceedings of the 26th International Conference on Advanced Communications Technology (ICACT).Pyeong Chang:IEEE,2024:1-5.
[4] 邱卫林.基于计算机视觉的铁路路基沉降监测方法研究[D].武汉:华中科技大学,2017.
[5] 闵永智,党建武,张振海.图像式无砟轨道表面沉降在线监测系统[J].光学精密工程,2013,21(6):1621-1627.
[6] 肖和华,金鼎沸.基于机器视觉的路基沉降监测方法研究[J].铁道科学与工程学报,2015,12(6):1365-1368.
[7] 蒋进波.基于计算机视觉的深基坑周边密集建筑群沉降监测方法[J].建筑结构,2022,52(S2):2451-2458.
[8] XING Jinghong,ZHANG Mingxin.Research on roadbed settlement measurement technology based embedded computer vision[C]//Proceedings of 2014 International Conference on Information Science,Electronics and Electrical Engineering.Sapporo:IEEE,2014:551-553.
[9] KARPIK A P,MAKEEV A V,MAREEV A V,et al.Evaluation of OpenCV-and laser pointer-based vertical displacement sensor for structure health monitoring[C]//Proceedings of 2023 IEEE XVI International Scientific and Technical Conference Actual Problems of Electronic Instrument Engineering (APEIE).Novosibirsk,Russian Federation:IEEE,2023:1340-1343.
[10] CHEN I H,HO S C,SU M B.Computer vision application programming for settlement monitoring in a drainage tunnel[J].Automation in Construction,2020,110:103011.
[11] LEE J J,SHINOZUKA M.A vision-based system for remote sensing of bridge displacement[J].NDT & E International,2006,39(5):425-431.
[12] 蓝章礼,张洪,周建庭.基于激光和视频的桥梁挠度测量新系统[J].仪器仪表学报,2009,30(11):2405-2410.
[13] 赵尘衍,徐亚明,张涛.单目视觉位移在线监测系统的设计与实现[J].测绘通报,2016(6):121-124.
[14] 何松晟.边坡表面变形的双目视觉监测及预警方法研究[D].成都:西南石油大学,2018.
[15] BUSCA G,CIGADA A,MAZZOLENI P,et al.Vibration monitoring of multiple bridge points by means of a unique vision-based measuring system[J].Experimental Mechanics,2014,54(2):255-271.
[16] 白冰川.基于双目视觉的边坡表面位移监测方法研究[D].大连:大连理工大学,2023.
[17] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas:IEEE,2016:779-788.
[18] WANG Ao,CHEN Hui,LIU Lihao,et al.YOLOv10:real-time end-to-end object detection[EB/OL].[2024-08-15].https://arxiv.org/abs/2405.14458v2.
[19] 田俊英,伍济钢,赵前程.视觉系统中摄像机标定方法研究现状及展望[J].液晶与显示,2021,36(12):1674-1692.
[20] ZHANG Z.A flexible new technique for camera calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[21] TRIGGS B.Autocalibration and the absolute quadric[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Juan,PR:IEEE,1997:609-614.
[22] MAYBANK S J,FAUGERAS O D.A theory of self-calibration of a moving camera[J].International Journal of Computer Vision,1992,8(2):123-151.
[23] 王建兵,姚海峰,刘智,等.基于椭圆拟合法的湍流扰动光斑质心提取[J].激光与光电子学进展,2024,61(13):281-288.

非接触式单目视觉高精度自动沉降监测

Non-contact monocular vision high-precision automatic settlement monitoring

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	黄鑫, 张继文, 于永堂, 徐传召, 张率, 曾涛, 王竞革. 基于北斗卫星导航系统的地下车库深基坑沉降监测与分析[J]. 测绘通报, 2023, 0(9): 18-24.
[2]	石银涛, 胡超, 赵钢, 侯婷婷. PS-InSAR技术在长江堤防沉降监测中的应用[J]. 测绘通报, 2023, 0(7): 142-148.
[3]	高建东, 王勇, 安江雷, 姜俊狄. 一种多源地面沉降监测数据融合方法及其应用[J]. 测绘通报, 2023, 0(10): 158-162,172.
[4]	曾学宏, 赵义花. 利用SBAS-InSAR技术分析西宁市地面沉降监测及驱动因素[J]. 测绘通报, 2022, 0(6): 137-142.
[5]	李佳豪, 周吕, 马俊, 杨飞, 咸凌霄. 利用PS-InSAR技术进行城市地铁沿线形变监测与机理分析[J]. 测绘通报, 2022, 0(4): 20-25.
[6]	李治泓, 朱庆, 吴学群, 郭永欣. 多视觉变量与单目视觉线索组合的三维地质模型增强可视化分析[J]. 测绘通报, 2022, 0(12): 7-13.
[7]	祝昕刚, 明生. 时序InSAR技术应用于高压输电线路附近的地表形变灾害防控[J]. 测绘通报, 2021, 0(7): 92-97.
[8]	付振华, 邓瑞芝. 一种基于单目视觉的无人机仿地飞行方法[J]. 测绘通报, 2021, 0(11): 128-130.
[9]	刘少平, 杨永波, 张东升, 赵芳, 邹宇. 一种改进的单目视觉桥梁挠度非接触测量方法[J]. 测绘通报, 2021, 0(10): 98-102.
[10]	熊鹏, 左小清, 李勇发, 谢文斌, 游洪, 王志红. InSAR技术在高速公路灾害辅助识别中的应用[J]. 测绘通报, 2020, 0(8): 87-91.
[11]	宋中华, 田慧, 宋帅. Trimble S9/S9 HP全站仪在铁路顶管施工路基面的精密沉降监测中的应用[J]. 测绘通报, 2020, 0(6): 153-155.
[12]	郭若南, 蒋郡祥, 牛小骥, 史俊波. IMU辅助下的单目视觉坐标传递[J]. 测绘通报, 2020, 0(3): 7-11.
[13]	窦超, 赵利江, 张生鹏, 刘雨鑫, 马国宝. 利用InSAR数据的格尔木市地表沉降监测[J]. 测绘通报, 2020, 0(10): 123-126.
[14]	盛超, 潘树国, 赵涛, 曽攀, 黄砺枭. 基于图像语义分割的动态场景下的单目SLAM算法[J]. 测绘通报, 2020, 0(1): 40-44.
[15]	曾攀, 潘树国, 黄砺枭, 王帅, 赵涛. 基于加权预积分和快速初始化的惯性辅助单目前端模型[J]. 测绘通报, 2019, 0(8): 8-13,19.