Fast and Efficient Visibility Restoration Technique for Single Image Dehazing and Defogging

Abstract

Poor weather conditions are detrimental to transportation systems and increase the likelihood of road accidents. Haze and fog are the most responsible atmospheric parameters affecting visibility and hence the traffic performance. The intelligent driving assistance systems developed for automatic vehicles use clear vision for various smart applications like keeping within the correct lane and recognize traffic signs. Bad weather decreases the visibility significantly based on the intensity of fog and haze. So, there is a need for the restoration of clear visibility. This paper introduces a novel visibility restoration approach based on thresholding and gamma transformation method. A step-by-step process for the proposed method is as follows. First, the proper selection of an atmospheric light value is responsible for the validation of the color and contrast of the recovered images. The threshold process makes it possible to estimate atmospheric light. Then, accurately estimating the transmission depth from object to object in small time is the most challenging aspect due to unequal distribution. To solve the problem, the gamma transformation method is used to correctly estimate the depth. Finally, restore the scene radiance from the hazy and foggy images. The experimental results show that the proposed measurement ensures good uniformity about qualitative and quantitative evaluation using eight performance metrics: contrast gain, percentage of saturated pixels, blind contrast assessment, structural similarity index measure (SSIM), image visibility measurement (IVM), mean square error (MSE), visual contrast measure (VCM), and peak signal-to-noise ratio (PSNR). The proposed algorithm excels in previous works in terms of processing time and visibility restoration results comparable to sophisticated state-of-the-art techniques.INDEX TERMS Atmospheric light, transmission map, gamma correction, performance metrics, processing time.

Efficient Framework for Real-Time Color Cast Correction and Dehazing Using Online Algorithms to Approximate Image Statistics

“…Yang and Wang [16] have suggested using a power-law function instead of minimum operation to address the blocking artifacts. Similarly, Kumari et al [17] propose a combination of median and gamma transformation to refine the transmission map. Cai et al [18] have trained a 3layer Convolutional Neural Network (CNN) to directly estimate the transmission from the input foggy image.…”

“…The estimated transmission is, however, processed through a bilateral filter (Degree of Smoothing = 0.03, Spatial Sigma=4). FIGURE 7 shows the transmission map for a few sample foggy images estimated using (17) after filtering. Transmission estimated using Kaiming [12] has also been shown for comparison.…”

Improving Semantic Segmentation Under Hazy Weather for Autonomous Vehicles Using Explainable Artificial Intelligence and Adaptive Dehazing Approach

“…In most cases, Deep Learning (DL) networks detect and segment road scenes from the images captured by sensors in the AVs. But, Unfortunately, heavy haze damages the outdoor environments, which affects DL networks' regular operations and has an unfavorable effect on their performance much as it does on human vision, leading to significant visibility deterioration [1] [2]. The impact of low visibility causes degraded image qualities which results in erroneous detection, and false negatives result in poor decisions, ultimately leading to vehicle accidents.…”