Acoustic Inspection of Concrete Structures Using Active Weak Supervision and Visual Information
Acoustic Inspection of Concrete Structures Using Active Weak Supervision and Visual Information
复制标题
DOI：
10.3390/s20030629
复制
发表时间：
2020-01
期刊：
影响因子：
--
通讯作者：
J. Kasahara;A. Yamashita;H. Asama
中科院分区：
文献类型：
--
作者：
J. Kasahara;A. Yamashita;H. Asama
混凝土结构在大多数现代社会中占有重要地位。近年来，对这些结构进行检测的需求越来越受到关注，并且对检测方法的自动化提出了很高的要求。声学方法，如锤击试验，是最流行的无损检测方法之一。提出了一种基于主动弱监控和视觉信息的混凝土结构缺陷检测方法。基于音频和位置信息，主动向用户查询样本对的相似性。这些用于将特征空间转换为有利的特征空间，以弱监督的方式，用于聚类缺陷和非缺陷样本，并通过位置信息进行增强。实验室条件下和现场条件下进行的实验证明了所提出的方法的有效性。
Concrete structures are featured heavily in most modern societies. In recent years, the need to inspect those structures has been a growing concern and the automation of inspection methods is highly demanded. Acoustic methods such as the hammering test are one of the most popular non-destructive testing methods for this task. In this paper, an approach to defect detection in concrete structures with active weak supervision and visual information is proposed. Based on audio and position information, pairs of samples are actively queried to a user on their similarity. Those are used to transform the feature space into a favorable one, in a weakly supervised fashion, for clustering defect and non-defect samples, reinforced by position information. Experiments conducted in both laboratory conditions and in field conditions proved the effectiveness of the proposed method.