Abstract
Many structures in civil engineering are symmetrical. Crack detection is a critical task in the monitoring and inspection of civil engineering structures. This study implements a lightweight neural network based on the YOLOv4 algorithm to detect concrete surface cracks. In the extraction of backbone and the design of neck and head, the symmetry concept is adopted. The model modules are improved to reduce the depth and complexity of the overall network structure. Meanwhile, the separable convolution is used to realize spatial convolution, and the SPP and PANet modules are improved to reduce the model parameters. The convolutional layer and batch normalization layer are merged to improve the model inference speed. In addition, using the focal loss function for reference, the loss function of object detection network is improved to balance the proportion of the cracks and the background samples. To comprehensively evaluate the performance of the improved method, 10,000 images (256 × 256 pixels in size) of cracks on concrete surfaces are collected to build the database. The improved YOLOv4 model achieves an mAP of 94.09% with 8.04 M and 0.64 GMacs. The results show that the improved model is satisfactory in mAP, and the model size and calculation amount are greatly reduced. This performs better in terms of real-time detection on concrete surface cracks.
Highlights
As one of the most common materials in civil engineering, concrete is widely used in dams, buildings, tunnels, bridges, and other infrastructure
It can be concluded that the improved model exhibits almost no loss in mean average precision (mAP) compared to the high-performance algorithms, but the model size and calculation amount are greatly reduced
A real-time concrete surface crack detection method based on the improved YOLOv4 is proposed
Summary
As one of the most common materials in civil engineering, concrete is widely used in dams, buildings, tunnels, bridges, and other infrastructure. As a common defect in civil engineering, cracks affect the health of structures, and lead to other problems [1]. The traditional detection method relies on human vision, which has high cost but low detection efficiency, and the detection results depend on subjective human judgment. To solve these problems, researchers have proposed many methods of automatically detecting concrete surface defects [2,3]. Researchers have proposed many methods of automatically detecting concrete surface defects [2,3] These methods usually have heavy workloads and low precision, and adequately cannot meet the demand. IPTs are usually used to help inspectors detect defects, but the final results are still obtained relying on manual judgment [9]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
