Single image dehazing using deep neural networks

Hodges, Cameron; Bennamoun, Mohammed; Rahmani, Hossein

doi:10.1016/j.patrec.2019.08.013

Cited by 46 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This sub-section presents the assessment metrics for the image quality. In this study, three objective evaluation indicators are mainly used to evaluate the enhanced patterns: mean square error [34,35] (MSE)，peak signal-to-noise ratio [36,38] (PSNR) and structural similarity [39,40] (SSIM).…”

Section: Performance Evaluation Metricsmentioning

confidence: 99%

Traditional pattern enhancement based on improved singular value decomposition and gamma function in the frequency domain

Yan

Yuan

et al. 2023

Preprint

View full text Add to dashboard Cite

Aiming at the problems of blurring and distortion of traditional patterns, an enhancement method to improve resolution and contrast is proposed.First, the discrete wavelet transform, stationary wavelet transform, and interpolation algorithm are used to obtain high-resolution images of traditional patterns. Then, the improved singular value matrix coefficients and the reconstructed gamma function are used to enhance the image contrast to obtain high-resolution and contrast-enhanced patterns. The experimental results show that the evaluation indexes such as mean square error, peak signal-to-noise ratio, and structural similarity corresponding to this method are improved compared with other comparison methods. It can effectively improve the quality of traditional patterns and is of great significance to the research on the restoration and protection of traditional patterns.

show abstract

Section: Performance Evaluation Metricsmentioning

confidence: 99%

Traditional pattern enhancement based on improved singular value decomposition and gamma function in the frequency domain

Yan

Yuan

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Hodges et al [32] developed a deep learning-based restoration model (DLR) of weather degraded images. In this, a deep learning model is utilized to train the samples using unmatched images.…”

Section: Related Workmentioning

confidence: 99%

Efficient Single Image Dehazing Model Using Metaheuristics-Based Brightness Channel Prior

Kehar

Chopra²,

Singh

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Haze degrades the spatial and spectral information of outdoor images. It may reduce the performance of the existing imaging models. Therefore, various visibility restoration models approaches have been designed to restore haze from still images. But restoring the haze is an open area of research. Although the existing approaches perform significantly better, they are not so effective against a large haze gradient. Also, the effect of hyperparameters tuning issue is also ignored. Therefore, a brightness channel prior (BCP) based dehazing model is proposed. The gradient filter is utilized to improve the transmission map computed using the gradient filter. Nondominated Sorting Genetic Algorithm is also used to optimize the initial parameters of the BCP approach. The comparative analysis shows that BCP performs effectively across a wide range of haze degradation levels without causing any visible artifacts.

show abstract

“…For instance, Sakaridis et al [15] proposed a convolution neural network (CNN) based model to generate synthetic fog on real vehicle images to investigate defogging algorithms in the traffic environments. Hodges et al [16] manipulated the dehazing model by a dehazing network to reform the full image and a discriminator network to fine tunning the enhancement weights parameters to increase the vehicle detection performance on a dataset of synthetic foggy/hazy images. Li et al [17] presented a benchmark including both synthetic and real-world rainy images with some rain types to investigate deraining algorithms in traffic monitoring scene and vehicle detection.…”

Section: Introductionmentioning

confidence: 99%

DAWN: Vehicle Detection in Adverse Weather Nature Dataset

Kenk,

Hassaballah

2020

Preprint

View full text Add to dashboard Cite

Recently, self-driving vehicles have been introduced with several automated features including lane-keep assistance, queuing assistance in traffic-jam, parking assistance and crash avoidance. These self-driving vehicles and intelligent visual traffic surveillance systems mainly depend on cameras and sensors fusion systems. Adverse weather conditions such as heavy fog, rain, snow, and sandstorms are considered dangerous restrictions of the functionality of cameras impacting seriously the performance of adopted computer vision algorithms for scene understanding (i.e., vehicle detection, tracking, and recognition in traffic scenes). For example, reflection coming from rain flow and ice over roads could cause massive detection errors which will affect the performance of intelligent visual traffic systems. Additionally, scene understanding and vehicle detection algorithms are mostly evaluated using datasets contain certain types of synthetic images plus a few real-world images. Thus, it is uncertain how these algorithms would perform on unclear images acquired in the wild and how the progress of these algorithms is standardized in the field. To this end, we present a new dataset (benchmark) consisting of real-world images collected under various adverse weather conditions called DAWN. This dataset emphasizes a diverse traffic environment (urban, highway and freeway) as well as a rich variety of traffic flow. The DAWN dataset comprises a collection of 1000 images from real-traffic environments, which are divided into four sets of weather conditions: fog, snow, rain and sandstorms. The dataset is annotated with object bounding boxes for autonomous driving and video surveillance scenarios. This data helps interpreting effects caused by the adverse weather conditions on the performance of vehicle detection systems.

show abstract

Single image dehazing using deep neural networks

Cited by 46 publications

References 25 publications

Traditional pattern enhancement based on improved singular value decomposition and gamma function in the frequency domain

Traditional pattern enhancement based on improved singular value decomposition and gamma function in the frequency domain

Efficient Single Image Dehazing Model Using Metaheuristics-Based Brightness Channel Prior

DAWN: Vehicle Detection in Adverse Weather Nature Dataset

Contact Info

Product

Resources

About