Die Hang, Jianxi Yang, Shixin Jiang, Hao Li, Xiaoxue Zou, Chuncheng Tang, and Die Liu
Mesh crack detection, encoder–decoder structure, lightweight convolutional module, efficient channel attention, max-pooling, mean-pooling
Cracks are one of the most common anomalies in concrete structures, affecting their safety, and thus have received much attention. However, most of the previous studies have focused on regular cracks, while fewer studies have analysed mesh cracks. Due to the characteristics of early appearance and high complexity, mesh cracks cause severe damage to concrete structures. Therefore, the automatic detection of mesh cracks is crucial to the safety of concrete structures. As mesh cracks consist of many fine branches, which can cause discontinuous results, this paper proposes a lightweight mesh crack detection model (MCM-Net) based on an efficient attention mechanism. The proposed network adopts an encoder–decoder structure and introduces improved efficient channel attention that assigns high weights to crack pixels. The introduction of lightweight convolutional modules into the proposed network reduces the computational cost, while the superposition of max- pooling and mean-pooling enables the extraction of more minutiae pixels. The proposed network is verified by experiments on the crack-detection (CD) and bridge-crack-image (BCI) datasets. The experimental results show that the proposed network can improve the stability and computational efficiency of mesh crack detection.
Important Links:
Go Back
