Abstract
Concrete pavement defects are an important indicator reflecting the safety status of pavement. However, it is difficult to accurately detect the concrete pavement cracks due to the complex concrete pavement environment, such as uneven illumination, deformation and potential shadows, etc. In order to solve these problems, we propose the crack detection algorithm of concrete pavement with convolutional neural network. Firstly, our method is used to classify cracks first and detect the classified crack images, different deep learning models are used in these two parts to achieve different functions. Secondly, in the crack classification section, in view of the low proportion of effective concrete pavement crack images in the mass images collected by crack detection vehicle, the output dimension of FC2 layer of LeNet-5 model is modified before crack detection. It can accurately identify the concrete pavement cracks from several types of disturbance characteristics by training the classification model. Finally, in order to improve the efficiency of crack detection, the algorithm scales the network model horizontally and accesses the convolution layer with the kernel size of $1\times 1$ , $3\times 3$ . Experiments show that the $F_{1} $ of our algorithm reaches to 0.896 in CFD dataset. Compared with VGG16, U-Net and Percolation, it is 25.2%, 2.8%, 39.1% improvement of $F_{1} $ respectively. For Cracktree200 dataset, the $F_{1} $ is 0.892. Compared with VGG16, U-Net and Percolation, it is 50.3%, 16.6%, 68.9% improvement of $F_{1} $ respectively. For DeepCrack dataset, the $F_{1} $ is 0.901. Compared with VGG16, U-Net and Percolation, it is 53%, 5.2%, 52.2% improvement of $F_{1} $ respectively.
Highlights
Cracks are one of primary forms of early diseases on concrete pavement, which reduce the service life of pavement and endanger driving safe
With the development of digital image processing technology, many researchers have proposed a variety of detection methods for concrete pavement crack detection
We named the dataset as Crack Classification Dataset 1500 (CCD1500)
Summary
Cracks are one of primary forms of early diseases on concrete pavement, which reduce the service life of pavement and endanger driving safe. In 2019, Ni et al [22] proposed a new crack width detection method based on Zernike moment operator It used dual-scale convolutional neural networks to detect cracks width. In 2018, Dorafshan et al [25] compared the performance of six common edge detectors and convolutional neural networks in crack detection of concrete images. This method trains convolutional neural network in the ‘‘big data’’ Imagenet database through migration learning Experiments show that this method has good effect. Gopalakrishnan [28] gave a narrative review of the recently published research on pavement distress detection based on deep learning, comparing the overall framework, network architecture and crack detection performance of these papers.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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
