Abstract
In order to solve the problem of difficulties in pavement distress detection in the field of pavement maintenance, a pavement distress detection algorithm based on a new deep learning method is proposed. Firstly, an image data set of pavement distress is constructed, including large-scale image acquisition, expansion and distress labeling; secondly, the FReLU structure is used to replace the leaky ReLU activation function to improve the ability of two-dimensional spatial feature capture; finally, in order to improve the detection ability of this model for long strip pavement distress, the strip pooling method is used to replace the maximum pooling method commonly used in the existing network, and a new method is formed which integrates the FReLU structure and the strip pooling method, named FS-Net in this paper. The results show that the average accuracy of the proposed method is 4.96% and 3.67% higher than that of the faster R-CNN and YOLOv3 networks, respectively. The detection speed of 4 K images can reach about 12 FPS. The accuracy and computational efficiency can meet the actual needs in the field of road detection. A set of lightweight detection equipment for highway pavement was formed in this paper by purchasing hardware, developing software, designing brackets and packaging shells, and the FS-Net was burned into the equipment. The recognition rate of pavement distress is more than 90%, and the measurement error of the crack width is within ±0.5 mm through application testing. The lightweight detection equipment for highway pavement with burning of the pavement distress detection algorithm based on FS-Net can detect pavement conditions quickly and identify the distress and calculate the distress parameters, which provide a large amount of data support for the pavement maintenance department to make maintenance decisions.
Highlights
The starting point of this paper is to develop a set of lightweight detection equipment; the single camera is used to shoot the pavement and the pavement distress is quickly detected and evaluated, which is suitable for the daily pavement round check of road maintenance and management departments
When constructing the data set of a pavement distress dataset, the first thing to be determined is the classification of pavement distress
Due to regular pavement maintenance, there are obvious repaired cracks on the ordinary pavement, which need to be distinguished from the pavement cracks
Summary
Sun [1] proposed the method of nonlinear filtering to enhance the images; Wang [2] and Wu [3] proposed a processing method of image denoising using Shearlet transform; Yan [4] first used a specific median filter to enhance the image and used the edge detection algorithm based on gray morphological operator when detecting cracks. The advantage of these kinds of methods is their high detection speed, but the disadvantage is the limited types of detectable distresses and their weak generalization ability. The accuracy of the algorithm has been verified; at present, the recognition rate of cracks, potholes, repaired cracks and repaired potholes is more than 90%
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
