基于图像的建筑物轮廓测量  

Measurement of building′s contour based on image

作　　者：姜虹[1] 

机构地区：[1]西安工业大学计算机科学与工程学院,陕西西安710032

出　　处：《西安工程大学学报》2012年第3期342-345,350,共5页Journal of Xi’an Polytechnic University

基　　金：国家自然科学基金资助项目(30871220)

摘　　要：针对施工中对建筑物进行测量中过程的复杂性、持续时间长的问题,提出一种用摄影测量建筑物的方法.该方法只需要对建筑物进行拍摄以及测量建筑物到相机的距离即可以对建筑物的参数进行测量.针对相机制造工艺中不可避免存在的畸变进行标定,得出相机的畸变参数和焦距等,再根据畸变参数对图像进行矫正,并使用Canny边缘检测算法提取建筑物的轮廓.应用结果表明该方法可以还原建筑物的真实轮廓.Measurement of buildings,which is complex and takes a long time,is often needed in the construction.Against this situation,a method which measure buildings by photogrammetry was put forward.This method can measure buildings only by picture of targets and the distance between buildings and camera.Due to manufacturing process is not perfect,there is inevitable distortion in camera,so the picture get from this camera also have distortion,which greatly affect following measurement.So calibration of camera first is done to get the distortion parameters and focal length,second the original picture is corrected by parameters above,then Canny algorithm is used to extract contours of buildings.

关 键 词：相机标定 平滑 边缘检测 CANNY算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]