基于双目图像三维重构的桥梁表观缺陷智能测量  

Intelligent measurement of pit defects in bridge structures based on 3D reconstruction of binocular images

作　　者：宋祖广 国璟 陈志豪 王高新 SONG Zuguang;GUO Jing;CHEN Zhihao;WANG Gaoxin(Suqian Highway Development Center,Suqian,Jiangsu 650041,China;CCCC Second Harbor Third Engineering Co.,Ltd.,Zhenjiang,Jiangsu 212000,China;China University of Mining and Technology,Xuzhou,Jiangsu 221116,China)

机构地区：[1]宿迁市公路事业发展中心,江苏宿迁650041 [2]中交二航局第三工程有限公司,江苏镇江212000 [3]中国矿业大学,江苏徐州221116

出　　处：《江苏建筑职业技术学院学报》2023年第4期8-12,共5页Journal Of Jiangsu Vocational Institute of Architectural Technology

基　　金：盐城至洛阳国家高速公路江苏宿城至泗洪段SS-1施工标段基于无人机双目成像的桥梁品质工程测量技术及示范(00-00-JSFW-20230203-029)。

摘　　要：提出基于双目图像三维重构的桥梁结构坑洞缺陷智能测量方法,首先利用基于双目成像的坑洞缺陷高清全彩三维重构方法,建立坑洞缺陷的三维空间全貌模型,其次利用基于闭合轮廓线的坑洞缺陷信息智能测量方法,从三维空间全貌模型中自动提取坑洞缺陷参数信息,最后对所提方法进行实验验证。结果表明:三维重构方法具有较好的高清全彩三维重构效果,三维重构模型的坑洞病害特征清晰可见,几何形状相似程度高,真实反映实际缺陷的三维形状和色彩特征,智能测量方法可以自动测量坑洞缺陷的坑洞面积和坑洞深度,实验测量精度较高且最大误差仅为1.3%。该方法可替代传统费时费力的人工测量方式,智能化和自动化程度高,有助于降本增效。This paper proposes an intelligent measurement method for pit defects in civil structure based on three-dimensional reconstruction of binocular image.First,using the high-definition full-color three-dimensional reconstruction method of pothole defects based on binocular imaging,a three-dimensional spatial full-picture model of pothole defects is established;then,using the intelligent measurement method of pit defect information based on closed contour lines,the defect parameter information from the three-dimensional spatial panorama model is automatically extracted;finally,experimental verification and real bridge application of the proposed method is carried out.The results show that the three-dimensional reconstruction method has a good high-definition full-color three-dimensional reconstruction effect;the pothole disease characteristics of the three-dimensional reconstruction model are clearly visible,the geometric shape similarity is high,and the three-dimensional shape and color characteristics of the actual defects can be truly reflected;the intelligent measurement method can automatically measure the pit area and pit depth of the pit defect,and the experimental measurement accuracy is high and the maximum error is only 1.3%.This method is highly intelligent and automated,which can replace the traditional time-consuming and labor-intensive manual measurement method,and help to reduce costs and increase efficiency.

关 键 词：桥梁结构 表观缺陷 双目图像 三维重构 智能测量 

分 类 号：TU398.9[建筑科学—结构工程]