基于计算机视觉的框架结构动态位移识别方法  

DYNAMIC DISPLACEMENT RECOGNITION METHOD OF FRAME STRUCTURE IN COMPUTER VISION

作　　者：何沐阳 何嘉壹 孙晓丹[3] HE Muyang;HE Jiayi;SUN Xiaodan(School of Civil Engineering,Harbin Institute of Technology,Harbin 150090,China;School of Information Science and Engineering,Harbin Institute of Technology(Weihai),Shandong Weihai 264209,China;School of Aerospace and Architectural Engineering,Harbin Engineering University,Harbin 150001,China)

机构地区：[1]哈尔滨工业大学土木工程学院,哈尔滨150090 [2]哈尔滨工业大学(威海)信息科学与工程学院,山东威海264209 [3]哈尔滨工程大学航天与建筑工程学院,哈尔滨150001

出　　处：《低温建筑技术》2024年第8期137-140,共4页Low Temperature Architecture Technology

摘　　要：工程结构的安全性日益受到人们的关注,如何快速评估结构的安全性成为该领域研究的热点和难点。结构产生的形变位移是结构安全评估较为直观的变量之一。传统接触式方法往往受到客观因素限制;非接触式方法可以快速准确获取结构位移,如何提升基于计算机视觉的位移监测精度是该领域研究的焦点之一。文中提出一种非接触式与接触式相结合的结构动态位移数据处理方法,将结构视觉标靶动态轨迹转化成像素位移后与将加速度传感器数据转化成的位移进行卡尔曼滤波,模拟出结构的真实位移,并用结构模态参数识别对文中方法可行性进行验证。研究结果表明,文中方法可以获得结构动态位移,并且监测效果准确度高。The safety of engineering structures is increasingly receiving attention,and how to quickly evaluate the safety of structures has become a hot and difficult research topic in this field.The deformation displacement generat⁃ed by the structure is one of the intuitive variables in structural safety assessment.How to improve the accuracy of displacement monitoring based on computer vision is one of the focuses of research in this field.This article propos⁃es a structural dynamic displacement data processing method that combines non-contact and contact methods.The dynamic trajectory of the structural visual target is converted into pixel displacement,and then Kalman filtering is performed on the displacement converted from the accelerometer data to simulate the true displacement of the struc⁃ture.The feasibility of the proposed method is verified by identifying structural modal parameters.The research re⁃sults indicate that the method proposed in this paper obtains dynamic displacement of structures and has high moni⁃toring accuracy.

关 键 词：计算机视觉 位移识别 比例因子 模态识别 

分 类 号：TU201.4[建筑科学—建筑设计及理论]