Pixelwise asphalt concrete pavement crack detection via deep learning‐based semantic segmentation method

Abstract

Explicit gaps exist between the advanced deep learning technologies and the less satisfied pixel-level crack detection algorithms. Therefore, this research sought to bridge this gap via outlining the deep neural network model for pixelwise pavement crack detection. Two state-of-the-art deep neural network models are constructed for the semantic segmentation of crack images. The first architecture, VGGCrackU-net, is composed of 10 3 Â 3 convolutional layers, 4 max-pooling layers, 4 up-sampling layers, and 4 concatenate operations. Another architecture, ResCrackU-net, is composed of 7-level residual units with a total of 22 convolutional layers. Asphalt concrete pavement crack images are collected by smartphones, action cameras, and automatic pavement monitoring systems from diverse functional classes of AC pavements. The crack images are manually labeled and double-checked by trained operators for quality insurance. After that, 500 crack images are randomly divided into training, validating, and test datasets according to the ratio of 3:1:1. Both architectures are trained on GPU facilitated Keras platform with Python version of 3.5, which demonstrated fast convergence. Results prove that the proposed models exhibit significant advantages for pixelwise crack detection when compared with the performance of widely used FCN net and PSPnet. Meanwhile, ResCrackU-net slightly outperforms VGGCrackU-net, which, however, can provide acceptable results as well. Though significant false negative and false positive errors are observed in both network models, the contributions are noticeable, which can provide innovative guidance for future work in figuring out solutions to the problems.

Permanent Deformation Monitoring and Remaining Life Prediction of Asphalt Pavement Combining Full-Scale Accelerated Pavement Testing and FEM

“…(1) To analyze the rutting evolution law in depth from three aspects: rutting section morphology, rutting development law, and rutting deformation mechanism. (2) To establish the FE model with more precise parameters and verify the reliability with rutting monitoring data in the full-scale APTand actual road in service.…”

“…Te residual dynamic modulus under diferent loading times was obtained through repeated loading tests of 1800 times, 2700 times, 3600 times, 4500 times, and 5400 times. Te test results were transformed and ftted according to (2) to establish the relationship between damage and loading time (t).…”

“…Asphalt pavement is the main pavement form of highgrade highways in China [1][2][3][4][5][6]. Rutting, one of the typical failure modes of asphalt pavement with a semirigid base in high-temperature areas, seriously damages the pavement quality and durability and afects driving safety and comfort [7][8][9][10][11].…”

“…(2) A Burgers model considering the damaging efect of creep parameters was proposed as a constitutive equation of the rutting prediction model based on the monitoring data and laboratory values. Te simulated results were in good agreement with the measured results, with an error of 7.9% compared to the APT data.…”

A deep learning semantic segmentation network with attention mechanism for concrete crack detection

“…[17][18][19] Yang et al 20 used fully convolutional network (FCN) with a backbone VGG19 to detect concrete crack, where training time was lower than CrackNet 21 on account of the end-to-end structure. Huyan et al 22 adopted two U-Net with backbone VGGNet and ResNet to perform pavement crack segmentation task from good quality images without noise, which exhibited significant advantages compared to FCN. Li et al 23 proposed FCN with a backbone DenseNet121 to analyze smartphone images for automatic detection of four damages in the concrete structure.…”