Image-based Detection of Surface Defects in Concrete during Construction

TL;DR

This paper presents a machine learning approach for automating the detection of honeycomb defects in concrete structures during construction, using image analysis with Mask R-CNN and EfficientNet-B0, and provides a new dataset for research.

Contribution

It introduces a new dataset of concrete honeycomb images, compares web-scraped and real inspection data, and applies two deep learning models for defect detection.

Findings

Both models effectively detect honeycombs in concrete images.

Web images lack the variability of real inspection images.

The dataset is publicly available for further research.

Abstract

Defects increase the cost and duration of construction projects as they require significant inspection and documentation efforts. Automating defect detection could significantly reduce these efforts. This work focuses on detecting honeycombs, a substantial defect in concrete structures that may affect structural integrity. We compared honeycomb images scraped from the web with images obtained from real construction inspections. We found that web images do not capture the complete variance found in real-case scenarios and that there is still a lack of data in this domain. Our dataset is therefore freely available for further research. A Mask R-CNN and EfficientNet-B0 were trained for honeycomb detection. The Mask R-CNN model allows detecting honeycombs based on instance segmentation, whereas the EfficientNet-B0 model allows a patch-based classification. Our experiments demonstrate that both approaches are suitable for solving and automating honeycomb detection. In the future, this solution can be incorporated into defect documentation systems.