Single-Image Defogging Algorithm Based on Improved Cycle-Consistent Adversarial Network

Abstract

With the wave of artificial intelligence and deep learning sweeping the world, there are many algorithms based on deep learning for image defog research. However, there is still serious color distortion, contrast reduction, incomplete fog removal, and other problems. To solve these problems, this paper proposes an improved image defogging network based on the traditional cycle-consistent adversarial network. We add the self-attention module and atrous convolution multi-scale feature fusion module on the basis of the traditional CycleGAN network to enhance the feature extraction capability of the network. The perceptual loss function is introduced into the loss function of the model to enhance the texture sense of the generated image. Finally, by comparing several typical defogging algorithms, the superiority of the defogging model proposed in this paper is proved qualitatively and quantitatively. Among them, on the indoor synthetic data set, the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measurement (SSIM) of the network designed by us can reach 23.22 and 0.8809, respectively. On the outdoor synthetic data set, the PSNR and SSIM of our designed network can be as high as 25.72 and 0.8859, respectively. On the real data set, the PSNR and SSIM of our designed network can reach 21.02 and 0.8166, respectively. It is proved that the defogging network in this paper has good practicability and universality.

Multi-Scale Adaptive Feature Network Drainage Pipe Image Dehazing Method Based on Multiple Attention

“…The dark channel is an image prior used to analyze and estimate the transmittance of hazy image scenes. In most outdoor natural images, at least in some local areas, there is a channel with very low pixel values, that is, the dark channel [9].…”

An image defog iteration algorithm for optimal estimation of atmospheric light direction

“…From formula (1), in order to obtain the fog-free scene image J(x) for a given observation image I (x), the transmission rate function t (x) and the atmospheric light vector A must be estimated. In addition, according to literature [9] , the direct scene transmission image J (x) can be expressed as formula (10):…”

“…This poses challenges in various applications, such as surveillance, target recognition, traffic management and military investigations. Therefore, the defogging of outdoor images has gained attention in recent years and holds significant application potential [1]. Image defogging methods can be categorized into two types: fog map enhancement and physical imaging model-based restoration [2].…”

Adaptive wavelet transform defogging scheme for real-time video restoration with field programmable gate array implementation

“…The rapid proliferation of smart cities has prompted the need for image processing smart devices to meet the demands of miniaturization, real-time processing, and high-definition imaging capabilities. 2 Image defogging encompasses three main approaches: image enhancement, 3 convolutional neural networks, 4 and image recovery. [5][6][7] In recent years, image recovery has garnered increased attention, focusing on the retrieval of scene transmission maps based on atmospheric scatter models.…”

“…Image defogging encompasses three main approaches: image enhancement, 3 convolutional neural networks, 4 and image recovery 5 – 7 In recent years, image recovery has garnered increased attention, focusing on the retrieval of scene transmission maps based on atmospheric scatter models 5 .…”