摘要
城乡自建房屋的违规改建现象时有发生,是不可忽略的安全隐患。传统的房屋巡检主要依靠人工方式,存在效率低、主观性强等问题,进而影响巡检结果的可靠性。为此,提出了基于三维视觉的房屋智能巡检方法。基于融合式SLAM技术实现巡检点云数据的实时采集;对多次巡检数据进行配准,并采用基于kd-tree的半径搜索法进行点云增减识别,找出改建部分;对改建部分进行区域生长分割并获取点云OBB包围盒,根据其几何尺寸信息进行简单的构件分类。进一步,定义考虑构件重要性的表面积变化率参数,可初步评价改建后结构的安全性。通过对某自建房进行巡检试验发现,上述方法能够快速、高效地获取待测房屋外立面的点云数据,有效识别房屋的改建部分,并基于构件特征进行改扩建后房屋的危险性评估,实现了巡检流程的自动化与智能化。
Ilegal reconstruction of self-built buildings in urban and rural areas occurs from time to time,which is a hidden danger that cannot be ignored.Traditional building inspection mainly relies on manual methods,which have problems such as low efficiency and high subjectivity,thus affecting the reliability of inspection results.This paper proposes an intelligent method for building inspection based on 3D vision.Based on the technology of fusion SLAM,the point cloud data are collected in real time.Multiple inspection data are registered,and the radius search method based on kd-tree is used to identify the increase or decrease parts of the point cloud and find out the reconstructed parts.The reconstructed parts are segmented by region growing algorithm and the OBB bounding boxes of them are obtained,and simple component classification is performed according to the geometry information of the bounding boxes.Furthermore,the surface area change rate parameter is defined considering the importance of the components,which can preliminarily evaluate the safety of the reconstructed structure.Taking the inspection of a self-built building as an example,the results demonstrate that the method outlined above can efficiently and quickly obtain point cloud data of the building facade to be inspected.This enables effective identification of any altered parts of the building and allows for an assessment of the danger of the building based on the characteristics of the components,thus realizing the automation and intelligence of the inspection process.
作者
冯楚乔
刘宇飞
岳岩
樊健生
张晋勋
王聪颖
FENG Chuqiao;LIU Yufei;YUE Yan;FAN Jiansheng;ZHANG Jinxun;WANG Congying(Department of Civil Engineering,Tsinghua University,Beijing 100084,China;Key Laboratory of Civil Engineering Safety and Durability of China Ministry of Education,Tsinghua University,Beijing 100084,China;Beijing Urban Construction Group Co.,Ltd,Beijing 100088,China;Beijing Urban Construction Real Estate Development Co.,Ltd,Beijing 100088,China)
出处
《建筑结构学报》
EI
CAS
CSCD
北大核心
2024年第6期133-142,共10页
Journal of Building Structures
基金
国家自然科学基金项目(52192662)。
关键词
房屋巡检
三维视觉
点云配准
改建识别
构件分类
危险性评估
building inspection
3D vision
point cloud registration
reconstruction identification
component classification
risk assessment
