Virtual generation of pavement crack images based on improved deep convolutional generative adversarial network

To solve the problems associated with a small sample size during intelligent road detection, a virtual image set generation method for asphalt pavement cracks is proposed based on improved deep convolutional generative adversarial networks (DCGANs). First, a small set of sample crack images is collected and used as the basic image set to perform filtering, gamma transformation, and other processes, whereby crack feature recognition is enhanced. Second, a variational autoencoder (VAE) is used to encode real crack images. The latent variable values obtained from the VAE are provided as input to the DCGAN model generator, and the model hyperparameters are optimized. Subsequently, the adaptive moment estimation (Adam) optimizer is used to reoptimize the model and thereby improve the model convergence speed and generalization ability. The proposed method has the advantages of both VAE and DCGAN. Finally, a pavement crack classification detection model based on faster region convolutional neural network (Faster R-CNN) is used to evaluate the reliability of the generated crack images. The results show that the augmented dataset of the proposed method with the detection model has an average precision of 90.32%, which is higher than that of the conventional method evaluated using the same test dataset. The proposed method generates virtual crack images that are moderately identical to real ones, thereby solving the problem of insufficient image datasets of cracks in specific road sections. The method also provides data assurance for the intelligentization of pavement crack detection and the reduction of pavement maintenance costs.

Automated summary

An improved method based on deep convolutional generative adversarial networks for generating virtual image sets to address the issue of small sample size in intelligent road detection is proposed. By utilizing both VAE and DCGAN advantages, the method generates virtual crack images, which are evaluated for reliability using a Faster R-CNN detection model, achieving an average precision of 90.32%.