Lightweight Neural Network for Real-Time Crack Detection on Concrete Surface in Fog

Abstract

Cracks are one of the most common factors that affect the quality of concrete surfaces, so it is necessary to detect concrete surface cracks. However, the current method of manual crack detection is labor-intensive and time-consuming. This study implements a novel lightweight neural network based on the YOLOv4 algorithm to detect cracks on a concrete surface in fog. Using the computer vision algorithm and the GhostNet Module concept for reference, the backbone network architecture of YOLOv4 is improved. The feature redundancy between networks is reduced and the entire network is compressed. The multi-scale fusion method is adopted to effectively detect cracks on concrete surfaces. In addition, the detection of concrete surface cracks is seriously affected by the frequent occurrence of fog. In view of a series of degradation phenomena in image acquisition in fog and the low accuracy of crack detection, the network model is integrated with the dark channel prior concept and the Inception module. The image crack features are extracted at multiple scales, and BReLU bilateral constraints are adopted to maintain local linearity. The improved model for crack detection in fog achieved an mAP of 96.50% with 132 M and 2.24 GMacs. The experimental results show that the detection performance of the proposed model has been improved in both subjective vision and objective evaluation metrics. This performs better in terms of detecting concrete surface cracks in fog.

TransMF: Transformer-Based Multi-Scale Fusion Model for Crack Detection

“…YOLOv3-Lite [26] uses the deep separable convolution to extract features, and utilizes the feature pyramid to preserve semantic information at different levels. A crack detection method based on the YOLOv4 algorithm is proposed in [34], which achieves good crack detection results with a lower trained model weight. To overcome the complicated and uneconomical disadvantages of traditional crack detection methods, a pavement crack detection network [35] is proposed to combine YOLOv5 and Transformer.…”

An modified intelligent real-time crack detection method for bridge based on improved target detection algorithm and transfer learning

“…Research has shown that the You Only Look Once (YOLO) series algorithm performs outstandingly among many object detection networks (Du et al, 2021). In the YOLO model, integrating the attention module or improving the feature extraction network can enhance the sensitivity of the model to the target features (Yao et al, 2019;Yang et al, 2022a;Liu et al, 2022;Zhang et al, 2023a;Kao et al, 2023); combining the depth-separable convolution or replacing the lightweight feature extraction network, a lightweight target detection network for real-time detection of cracks on the structure surface can be obtained (Zhang et al, 2020a;Yao et al, 2021a;Yang et al, 2022b;Zhang et al, 2022;Zhang et al, 2023b;Jin et al, 2023); introducing the focal loss function or transfer learning can improve the recognition accuracy of the model. Deep learning has been gradually applied to bridge crack detection (Zhang et al, 2020b;Yao et al, 2021b;Teng et al, 2022).…”