Integrated APC-GAN and AttuNet Framework for Automated Pavement Crack Pixel-Level Segmentation: A New Solution to Small Training Datasets

Pavement crack segmentation using deep learning methods can improve crack segmentation accuracy, but in many cases the training dataset is lacking or uneven, making it insufficient to train an accurate segmentation model. In this work, an integrated APC-GAN and AttuNet framework is proposed as an automated pavement surface crack pixel-level segmentation solution for small training datasets. First, an Automated Pavement Crack Generative Adversarial Network (APC-GAN) is designed for the pavement cracks data as an image augmentation method, which is modified and improved from a traditional Deep Convolutional Generative Adversarial Network (DCGAN). Then, a novel pixel-level semantic segmentation structure, Attention modified U-Net (AttuNet), is proposed by introducing the attention module into the convolutional network structure. In order to assess the performance of our proposed framework, an open-source dataset DeepCrack is used, which only contains 300 training images. The results show that our proposed APC-GAN could augment the datasets by producing more clear and distinct pavement images than DCGAN and the generated images could feature more diversity than traditional image augmentation methods. APC-GAN demonstrated higher accuracy than DCGAN and traditional image augmentation methods. Apparently, our proposed APC-GAN and AttuNet framework gains the highest value in the evaluation metrices, including recall, F1 score, mean Intersection over Union (mIoU) and mean Pixel Accuracy (mPA) among all models including U-Net, DeepLabv3, FCN, and LRASPP.

Automated summary

In this study, an integrated APC-GAN and AttuNet framework is proposed for the automated pixel-level segmentation of pavement surface cracks. The proposed APC-GAN is designed as an image augmentation method and the AttuNet structure incorporates an attention module into the convolutional network. The performance of the framework is evaluated using the DeepCrack dataset, which contains only 300 training images. The results show that APC-GAN outperforms DCGAN and traditional image augmentation methods in generating clear and diverse pavement images, and the proposed framework achieves the highest performance metrics compared to other models.