Weakly Supervised Acoustic Defect Detection in Concrete Structures Using Clustering-Based Augmentation

Abstract

The automation of inspection methods for concrete structures is a pressing issue worldwide. Weakly supervised approaches, i.e., approaches based on supervision in other forms than traditional class labels, offer a unique mix of automation and human involvement that is highly effective for critical tasks such as inspection work. Generating weak supervision is less tedious than generating training data for supervised learning approaches. However, since it is less informative, high amounts of weak supervision are often needed. In practice, it is often the case that only scarce amounts of weak supervision are available. In this article, we propose a novel approach for weakly supervised acoustic defect detection in concrete structures that augment human-provided weak supervision. Experiments in both laboratory and field conditions showed that the proposed method allows for considerable performance gains for low amounts of weak supervision.

An Internal Defect Detection Algorithm for Concrete Blocks Based on Local Mean Decomposition-Singular Value Decomposition and Weighted Spatial-Spectral Entropy

“…Machine learning-based defect detection algorithms generally have high defect recognition accuracy. Machine learning algorithms require many relevant datasets for training, so are mainly suitable for defect detection in fixed scenarios [35]. The synthetic aperture focusing algorithm leverages time-delay superposition and fluctuation equation theory to reconstruct defect images predicated on the amplitude or wave velocity of ultrasound.…”