摘要
基于深度学习的混凝土缺陷检测通过提供结构状况的初始评估,可有效降低基础设施运营风险以及节约维护成本。文中归纳了近年来混凝土缺陷检测技术的研究进展,对相关研究的已有成果进行分析,讨论对比了各类检测方法的差异及优缺点。对可用于混凝土缺陷检测的图像数据集进行了梳理与介绍,再从实际应用出发,对混凝土缺陷检测中可能会存在的问题进行梳理,阐述与分析了能解决相应检测问题的相关研究。最后,针对该研究后续可能的发展方向进行展望。
Concrete defect detection based on deep learning can effectively reduce infrastructure operation risks and save maintenance costs by providing an initial assessment of structural conditions.This paper analyzes the research progress of concrete defect detection technologies in recent years,analyzes the existing achievements of related researches,and discusses and compares the differences,advantages and disadvantages of various detection methods.The image datasets that can be used for concrete defect detection are sorted out and introduced.Then,starting from the practical application,the possible problems in concrete defect detection are sorted out,and the related research that can solve the corresponding detection problems is expounded and analyzed.Finally,the possible future development directions of the research are prospected.
作者
王嘉敏
武文红
牛恒茂
石宝
乌尼尔
郝旭
张超
付荣升
WANG Jiamin;WU Wenhong;NIU Hengmao;SHI Bao;WU Nier;HAO Xu;ZHANG Chao;FU Rongsheng(College of Information Engineering,Inner Mongolia University of Technology,Hohhot 010080,China;College of Construction Engineering and Surveying and Mapping,Inner Mongolia Technical College of Construction,Hohhot 010080,China)
出处
《计算机科学》
北大核心
2025年第S1期347-358,共12页
Computer Science
基金
国家自然科学基金(62066035)
内蒙古自治区高等学校科学技术研究项目(NJZY22374)
内蒙古自治区自然科学基金(2024QN06021)。
关键词
深度学习
混凝土缺陷
卷积神经网络
目标检测
语义分割
实例分割
Deep learning
Concrete defect
Convolutional neural network
Target detection
Semantic segmentation
Instance segmentation
