Optimized U-shape convolutional neural network with a novel training strategy for segmentation of concrete cracks

Abstract

Crack detection is a vital component of structural health monitoring. Several computer vision-based studies have been proposed to conduct crack detection on concrete surfaces, but most cases have difficulties in detecting fine cracks. This study proposes a deep learning-based model for automatic crack detection on the concrete surface. Our proposed model is an encoder–decoder model which uses EfficientNet-B7 as the encoder and U-Net’s modified expansion path as the decoder. To overcome the challenges in the detection of fine cracks, we trained our model with a new training strategy on images extracted from an open-access dataset and achieved a 96.98% F1 score for unseen test data. Moreover, we evaluated our method on CrackForest Dataset and achieved a 97.06% F1 score which outperforms all the existing methods. The robustness of the proposed model is investigated using the various numbers of training data, and the optimal data size for training this model is presented. The results show that although deep learning models acquire a large number of data, this model works with limited data, without any degradation in its performance. Furthermore, the novel training strategy used in this study, significantly improves the model’s accuracy in detecting different types of cracks.