A generative adversarial network approach for removing motion blur in the automatic detection of pavement cracks
Yu Zhang, Lin Zhang
Abstract
Advancements in infrastructure management have significantly benefited from automatic pavement crack detection systems, relying on image processing enhanced by high-resolution imaging and machine learning. However, image and motion blur substantially challenge the accuracy of crack detection and analysis. Nevertheless, research on mitigating motion blur remains sparse. This study introduces an effective image processing system adept at deblurring and segmentation, employing a generative adversarial network (GAN) with UNet as the generator and Wasserstein GAN with Gradient Penalty (WGAN-gp) as the loss function. This approach performs exceptionally in deblurring pavement crack images and improves segmentation accuracy. Models were trained with sharp and artificially blurred images, with WGAN-gp surpassing other loss functions in effectiveness. This research innovatively suggests assessing deblurring quality through segmentation accuracy in addition to peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), revealing that PSNR and SSIM may not fully capture deblurring effectiveness for pavement crack images. An extensive evaluation of various generators, including UNet, lightweight UNet, TransUNet, DeblurGAN, DeblurGAN-v2, and MIMO-UNet, identifies the superior performance of UNet on simulated motion blur. Validation with actual motion-blurred images confirms the effectiveness of the proposed model. These findings demonstrate that GAN-based models have great potential in overcoming motion blur challenges in pavement crack detection systems, marking a notable advancement in the field.