A Systematic Review on Foggy Datasets: Applications and Challenges

In the early mornings and the late nights of winter season, the majority of road accidents occur every year despite less traffic due to the poor visibility of drivers in the presence of fog. The researchers developed various computational intelligence algorithms for image defogging to improve the visibility of drivers. The main intention of this paper is to analyse the various types of foggy image and video databases with their pros and cons. The challenges in collecting the datasets, such as illumination variation, inconstant camera angle, occlusion, and background cluttering are discussed. This paper also demonstrates the inter-dependency of some datasets. Some datasets comprise original images, while some datasets are the extension of pre-existing datasets. Some datasets are restricted to foggy images and present images in other weather conditions such as snowfall and rain. This paper presents a novel dataset of hazy images called hazy unpaired dataset for road safety (HUDRS), depicting hazy and haze-free images. The existing defogging techniques are applied on HUDRS. The different defogging datasets are compared in terms of their hardware and software specifications.