基于视频图像和神经网络的位移测量的实现与分析  

Realization and analysis of a displacement measuring method based on video-image processing and ANN

作　　者：侯杰[1] 钱稼茹[1] 张微敬[2] 潘鹏[1] 

机构地区：[1]清华大学土木工程系结构工程与振动教育部重点实验室,北京100084 [2]北京工业大学建工学院城市与工程安全减灾省部共建教育部重点实验室,北京100022

出　　处：《实验技术与管理》2009年第9期25-29,共5页Experimental Technology and Management

基　　金：十一五国家科技支撑计划(批准号:2006BAJ13B03-02)

摘　　要：由于工程或实验室现场情况的复杂性,常用的位移测量方法往往难以采用,而视频图像可以实现非接触实时位移测量。测量位置及镜头成像的畸变会造成成像平面与实物坐标系之间存在复杂的非线性映射关系。探讨了视频图像测量技术的基本原理,采用BP神经网络技术构建成像平面与实物坐标之间的非线性映射关系,提出了基于视频图像和神经网络技术的二维位移测量的实现方法。采用数码相机、标定板和计算机程序,验证了该测量方法的准确性和可行性。Because of the complex situation of laboratory and construction site,the contact displacement mea-suring method may not work well.A non-contact measuring method can be realized by means of video and image s capturing and processing.But due to the measurement position and lens s distortion,there is a nonlinear relationship between the image plane in the camera and the actual position of target.The basic theory of video-image displacement measuring method is displayed and artificial neural network（ANN） technology is adopted to establish the nonlinear relationship between the image plane and the position of the target. A two dimensional displacement measuring method based on video-image and ANN technology is introduced in detail. The precision and feasibility of this method are verified by a test with a camera, a calibration panel and a computer program.

关 键 词：位移测量 视频 图像 人工神经网络 

分 类 号：TH822[机械工程—仪器科学与技术] TP391.4[机械工程—精密仪器及机械]