Abstract

Concrete bridge crack detection is critical to guaranteeing transportation safety. The introduction of deep learning technology makes it possible to automatically and accurately detect cracks in bridges. We proposed an end-to-end crack detection model based on the convolutional neural network (CNN), taking the advantage of atrous convolution, Atrous Spatial Pyramid Pooling (ASPP) module and depthwise separable convolution. The atrous convolution obtains a larger receptive field without reducing the resolution. The ASPP module enables the network to extract multi-scale context information, while the depthwise separable convolution reduces computational complexity. The proposed model achieved a detection accuracy of 96.37% without pre-training. Experiments showed that, compared with traditional classification models, the proposed model has a better performance. Besides, the proposed model can be embedded in any convolutional network as an effective feature extraction structure.

Highlights

  • Bridges play a significant role in daily life

  • We proposed an end-to-end model based on the convolutional neural network to

  • We proposed an end-to-end model based on the convolutional neural network to detect bridge cracks automatically

Read more

Summary

Introduction

Bridges play a significant role in daily life. Regular bridge checks are important for maintaining the structural health and reliability of bridges. Bridge crack is one of the main damages of bridges, and its detection is an important task for bridge maintenance. Traditional bridge detection methods rely on human visual inspection, so the detection efficiency and accuracy cannot be guaranteed. Machine learning and computer vision were applied to the field of crack detection [1,2,3,4,5], and achieved good results. The modern convolutional neural network (CNN) was first proposed by LeCun et al [6] in 1989

Methods
Results
Discussion
Conclusion
Full Text
Paper version not known

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 call