CNN-Based Deep Architecture for Reinforced Concrete Delamination Segmentation Through Thermography

TL;DR

This paper proposes a CNN-based deep learning framework using DenseNet architecture for accurate segmentation of concrete delamination in thermographic images, addressing challenges posed by environmental variations and irregular shapes.

Contribution

It introduces a novel application of DenseNet for thermography-based delamination segmentation, improving accuracy over traditional methods.

Findings

DenseNet-based model achieved high segmentation accuracy.

The approach is robust to temperature contrast variations.

Effective in profiling irregular delamination shapes.

Abstract

Delamination assessment of the bridge deck plays a vital role for bridge health monitoring. Thermography as one of the nondestructive technologies for delamination detection has the advantage of efficient data acquisition. But there are challenges on the interpretation of data for accurate delamination shape profiling. Due to the environmental variation and the irregular presence of delamination size and depth, conventional processing methods based on temperature contrast fall short in accurate segmentation of delamination. Inspired by the recent development of deep learning architecture for image segmentation, the Convolutional Neural Network (CNN) based framework was investigated for the applicability of delamination segmentation under variations in temperature contrast and shape diffusion. The models were developed based on Dense Convolutional Network (DenseNet) and trained on thermal images collected for mimicked delamination in concrete slabs with different depths under experimental setup. The results suggested satisfactory performance of accurate profiling the delamination shapes.