An Adversarial Dual-Branch Network for Nonhomogeneous Dehazing in Tunnel Construction

Abstract

The tunnel construction area poses significant challenges for the use of vision technology due to the presence of nonhomogeneous haze fields and low-contrast targets. However, existing dehazing algorithms display weak generalization, leading to dehazing failures, incomplete dehazing, or color distortion in this scenario. Therefore, an adversarial dual-branch convolutional neural network (ADN) is proposed in this paper to deal with the above challenges. The ADN utilizes two branches of the knowledge transfer sub-network and the multi-scale dense residual sub-network to process the hazy image and then aggregate the channels. This input is then passed through a discriminator to judge true and false, motivating the network to improve performance. Additionally, a tunnel haze field simulation dataset (Tunnel-HAZE) is established based on the characteristics of nonhomogeneous dust distribution and artificial light sources in the tunnel. Comparative experiments with existing advanced dehazing algorithms indicate an improvement in both PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity) by 4.07 dB and 0.032 dB, respectively. Furthermore, a binocular measurement experiment conducted in a simulated tunnel environment demonstrated a reduction in the relative error of measurement results by 50.5% when compared to the haze image. The results demonstrate the effectiveness and application potential of the proposed method in tunnel construction.

Efficient Haze Removal from a Single Image Using a DCP-Based Lightweight U-Net Neural Network Model

“…It is characterized by deciding what to focus on at the channel level and where to focus at the pixel level and capturing features by emphasizing them. To remove haze in adverse conditions such as tunnels, Shi et al [ 20 ] constructed a GAN-based double-branching neural network. The neural network is characterized by the parallel operation of a sub-neural network with an encoder–decoder structure to extract low-frequency features and a multi-scale dense residual sub-neural network to supplement the details of the image.…”