基于计算机视觉的混凝土缺陷检测研究综述  

A Review of Concrete Defect Detection Based on Computer Vision

作　　者：姜韶华[1] 蒋希晗 Jiang Shaohua;Jiang Xihan(Dalian University of Technology,Department of Construction Management,Dalian 116024,China)

机构地区：[1]大连理工大学建设管理系,大连116024

出　　处：《土木建筑工程信息技术》2023年第4期14-21,共8页Journal of Information Technology in Civil Engineering and Architecture

基　　金：国家自然科学基金面上项目“数据与知识双驱动的建筑工程施工质量智能合规性检查与问题防治研究”(编号:52078101)。

摘　　要：混凝土缺陷对混凝土结构的安全性和稳定性造成的威胁不容小觑,因此,定期的缺陷检测对混凝土结构的维护至关重要。相较于主观低效的人工视觉检测,计算机视觉因在混凝土缺陷检测的自动化方面具有显著优势而成为近年来的研究热点,但目前缺乏该领域的全面综述。因此,本文旨在综合分析计算机视觉技术在混凝土缺陷检测领域的研究进展,对混凝土缺陷检测涉及的计算机视觉算法进行分类,总结现存的技术难点并分析未来研究方向,为该领域的后续研究提供一定的参考。Concrete defects pose a considerable threat to the safety and stability of concrete structures,so regular defect detection is essential for the maintenance of concrete structures.Compared with subjective and inefficient manual visual inspection,computer vision enjoys significant advantages in the automation of concrete defect detection,which has become a research hot spot in recent years.However,there is still a lack of comprehensive review in this field currently.Therefore,this paper aims to comprehensively analyze the research progress of computer vision technique in the field of concrete defect detection and classify the computer vision algorithms involved in concrete defect detection.Thereafter the paper summarizes the existing technical difficulties and analyzes the future research directions,which can provide a certain reference for the subsequent research in this field.

关 键 词：缺陷检测 混凝土结构 计算机视觉 深度学习 机器学习 

分 类 号：TU17[建筑科学—建筑理论]