Attention-Gate-Based Model with Inception-like Block for Single-Image Dehazing

Abstract

In recent decades, haze has become an environmental issue due to its effects on human health. It also reduces visibility and degrades the performance of computer vision algorithms in autonomous driving applications, which may jeopardize car driving safety. Therefore, it is extremely important to instantly remove the haze effect on an image. The purpose of this study is to leverage useful modules to achieve a lightweight and real-time image-dehazing model. Based on the U-Net architecture, this study integrates four modules, including an image pre-processing block, inception-like blocks, spatial pyramid pooling blocks, and attention gates. The original attention gate was revised to fit the field of image dehazing and consider different color spaces to retain the advantages of each color space. Furthermore, using an ablation study and a quantitative evaluation, the advantages of using these modules were illustrated. Through existing indoor and outdoor test datasets, the proposed method shows outstanding dehazing quality and an efficient execution time compared to other state-of-the-art methods. This study demonstrates that the proposed model can improve dehazing quality, keep the model lightweight, and obtain pleasing dehazing results. A comparison to existing methods using the RESIDE SOTS dataset revealed that the proposed model improves the SSIM and PSNR metrics by at least 5–10%.

New Nighttime Dehazing Algorithm Based On Dark Channel Prior Enhancement

“…While existing nighttime dehazing algorithms, such as those proposed by Li and Chen et al [27,28], have made progress in addressing the challenges of nighttime dehazing, they still face difficulties in accurately estimating the transmittance of the light source region.This can cause an increase in the pixel value of the light source region after dehazing, subsequently resulting in the diffusion of the light source.To overcome this issue,we propose an adaptive light source matrix mechanism based on the work of Yao et al [30],as presented in Eq. [3] below.…”

“…In Eq. [3],C x represents the photometric value of each pixel.|I x − A x | max is used as the threshold value to distinguish between the light source region and the nonlight source region.In addition,d(x, m) epresents the distance from other pixels to the selected light source,k x is the impact matrix of each light source.…”

“…Haze is caused by tiny particles in the air,which make images unclear.Clear and sharp images are necessary for computer vision tasks like object detection [1][2][3][4],surveillance,and self-driving cars [5][6].Therefore,various image dehazing techniques have gained popularity.These techniques are essential to improve image acquisition systems and clear up images captured during hazy weather.…”

An Adaptive Kernels Layer for Deep Neural Networks Based on Spectral Analysis for Image Applications

“…Other works, such as [ 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 ], implemented what is known as Inception-like blocks, which use deep conventional networks, and the residual connections introduced in [ 26 ] to extract the outputs from each layer and concatenated them for the output, as shown in the example in Figure 4 , mimicking the operation using the Inception layer depth-wise by allowing the extracted feature at multiple receptive fields to be processed at the output layer. However, while this approach can be suitable for certain applications such as classification, a drop in the spatial features accumulates as we move deeper, diminishing the spatial accuracy of the larger LRF values, as illustrated in Figure 5 , where it can be seen that a bias towards features at the centre starts to increase, impairing the capability of the layer to accurately position where the feature is located and decreasing its efficiency in applications such as object detection.…”