机器视觉技术在大坝表面变形监测中的适用性研究  

Application of Machine Vision Technology in Dam Surface Deformation Monitoring

作　　者：许孝臣[1,2] 薛磊磊 李峰 戴春华[1,2] 葛国昌[1,2] 徐金英 XU Xiao-chen;XUE Lei-lei;LI Feng;DAI Chun-hua;GE Guo-chang;XU Jin-ying(Zhejiang Institute of Hydraulics&Estuary,Hangzhou 310000,China;Zhejiang Guangchuan Engineering Consulting Corporation,Hangzhou 310020,China;Zhejiang Tongji Vocational College of Science and Technology,Hangzhou 310000,China)

机构地区：[1]浙江省水利河口研究院,浙江杭州310000 [2]浙江广川工程咨询有限公司,浙江杭州310020 [3]浙江同济科技职业学院,浙江杭州310000

出　　处：《水电能源科学》2024年第9期125-129,共5页Water Resources and Power

基　　金：浙江省水利厅科技计划项目(RB2128);浙江省基础公益研究计划项目(LGF19E090007);浙江省水利河口研究院院长基金项目(岩土A22001)。

摘　　要：针对大坝表面变形自动化监测中GNSS系统垂直位移监测精度低、费用昂贵和静力水准仪布设难度大、维修成本高等问题,利用机器视觉技术对大坝表面变形进行监测。室内试验结果表明,相机与标靶距离在100 m范围内,机器视觉的测量精度可达到亚毫米级,且水平和垂直变形位移精度相近。由误差分析可知,标靶与相机的距离与测量精度有明显的相关性,而环境因素是影响远距离监测精度的重要因素,并利用大坝视准线原理优化了机器视觉监测系统。最后以浙江省大力塘水库为试点,对大坝表面变形进行实时监测,结果表明,机器视觉技术完全可满足实际工程需求,且优化后的机器视觉测量技术可明显提高监测数据的精度和稳定性。Aiming at the problems of low accuracy,high cost,difficulty in laying static level and high maintenance cost of GNSS system in automatic monitoring of dam surface deformation,this paper uses machine vision technology to monitor dam surface deformation.Laboratory experiment results show that the measurement accuracy of machine vision can reach sub-millimeter level when the distance between the camera and the target is within 100 m,and the horizontal and vertical deformation and displacement accuracy are similar.It can be seen from the error analysis that the distance between the target and the camera has obvious correlation with the measurement accuracy.Environmental factors are important factors that affect the accuracy of remote monitoring,and the machine vision monitoring system is optimized by using the principle of dam sight line.Taking Dalitang Reservoir in Zhejiang Province as a pilot project,real-time monitoring of dam surface deformation is carried out.The results show that the machine vision technology can fully meet the needs of practical engineering,and the optimized machine vision measurement technology can significantly improve the accuracy and stability of monitoring data.

关 键 词：机器视觉 大坝表面变形 视准线原理 图像处理 误差分析 

分 类 号：TV698.1[水利工程—水利水电工程]