基于机器视觉技术单点多目标结构位移监测.docVIP

基于机器视觉技术单点多目标结构位移监测 　　摘要：基于机器视觉的动态位移监测技术，由于其具有的非接触、实时性、远距离、便携性等优点近年来得到了较快发展。本文提出了一种基于机器视觉技术的单点多目标结构位移监测方法，详细阐述了基于数字图像处理技术的模板匹配算法和多目标位移计算方法。采用工业数码相机和高倍变焦镜头，利用图像化编程语言LabVIEW开发了单点多目标位移监测系统，并对该系统进行了试验研究。研究结果表明，基于机器视觉技术的单点多目标结构位移监测方法现实可行，适用于大型结构的同步多点振动或转动位移监测。 　　关键词：结构健康监测；机器视觉；模板匹配；LabVIEW；单点多目标 　　中图分类号：TU198+.3文献标识码：A 　　Single-point multi-target structural displacement monitoring based on machine vision technology 　　Zhang Xiao-ming 1Fan Ke-qing1Ye Xiao-wei2 　　(1. School of Information Engineering, Wuyi University, Jiangmen 529020, China) 　　2. College of Civil Engineering and Architecture, Zhejiang University, Hangzhou 310058, China.) 　　Abstract: Machine vision-based dynamic displacement monitoring technology has gained rapid development in recent years due to its advantages in terms of non-contact, real-time, long-distance, easy to implementation, etc. In this paper, a single-point multi-target structural displacement monitoring method based on machine vision technology is proposed. The pattern matching algorithm based on the digital image processing technology as well as the multi-target displacement calculation method are presented in detail. A single-point multi-target structural displacement monitoring system is developed by use of the industrial digital camera and the high-power zoom lens, together with the graphical programming language LabVIEW. The results of the laboratory tests demonstrate that the method of single-point multi-target structural displacement monitoring based on the machine vision technology is feasible, and suitable for synchronous monitoring of the multi-target oscillatory or rotational displacement of large-scale structures. 　　Keywords: structural health monitoring; machine vision; pattern matching; LabVIEW; single-point multi-target 　　 　　0．引言 　　结构健康监测已经成为土木工程领域重要的研究课题之一。结构的实时动态变形、振动或转动位移监测是结构健康监测和故障诊断监测中重要的研究内容，也是分析工程结构力学特性的一个基本物理参数。基于机器视觉技术的新兴结构位移监测方法因其具有的远距离、非接触、实时性等优点近年来在国内外得到了较快发展[1-2]。Li等[3]提出了基于图像运动模糊算法的机器视觉方法用于测量结构振动振幅，并对单个被测物体进行试验研究