SIDE—A Unified Framework for Simultaneously Dehazing and Enhancement of Nighttime Hazy Images

Abstract

Single image dehazing is a difficult problem because of its ill-posed nature. Increasing attention has been paid recently as its high potential applications in many visual tasks. Although single image dehazing has made remarkable progress in recent years, they are mainly designed for haze removal in daytime. In nighttime, dehazing is more challenging where most daytime dehazing methods become invalid due to multiple scattering phenomena, and non-uniformly distributed dim ambient illumination. While a few approaches have been proposed for nighttime image dehazing, low ambient light is actually ignored. In this paper, we propose a novel unified nighttime hazy image enhancement framework to address the problems of both haze removal and illumination enhancement simultaneously. Specifically, both halo artifacts caused by multiple scattering and non-uniformly distributed ambient illumination existing in low-light hazy conditions are considered for the first time in our approach. More importantly, most current daytime dehazing methods can be effectively incorporated into nighttime dehazing task based on our framework. Firstly, we decompose the observed hazy image into a halo layer and a scene layer to remove the influence of multiple scattering. After that, we estimate the spatially varying ambient illumination based on the Retinex theory. We then employ the classic daytime dehazing methods to recover the scene radiance. Finally, we generate the dehazing result by combining the adjusted ambient illumination and the scene radiance. Compared with various daytime dehazing methods and the state-of-the-art nighttime dehazing methods, both quantitative and qualitative experimental results on both real-world and synthetic hazy image datasets demonstrate the superiority of our framework in terms of halo mitigation, visibility improvement and color preservation.

Visibility Enhancement and Fog Detection: Solutions Presented in Recent Scientific Papers with Potential for Application to Mobile Systems

“…During the nighttime, the process is more challenging; due to multiple scattering phenomena, most daytime dehazing methods become invalid. The paper [ 49 ] proposes a novel unified nighttime hazy image enhancement framework that approaches both haze removal and illumination enhancement problems simultaneously. A big plus is the fact that most current daytime dehazing methods can be incorporated into nighttime dehazing tasks based on the proposed framework.…”

Vehicle Detection Using Deep Learning Technique in Tunnel Road Environments

“…Figure 8c shows a dark channel image, representing the lowest brightness in each RGB channel of that in (b). Using the image in Figure 8b, the atmospheric light L is estimated using the method reported by Dubok et al [23]. The transmission map (Figure 8d) t(x) is estimated using the atmospheric light L. Using the atmospheric light L and transmission map t(x), and image with a smoothed brightness and removed noise is generated, as shown in Figure 8e.…”

Low‐light image haze removal with light segmentation and nonlinear image depth estimation

“…What is more, the illumination is extremely weak and the active light glow can cover image details which is not taken into account in the common daytime dehazing research methods such as the dark channel prior(DCP) [4] and the color attenuation prior (CAP) [10]. In recent years, many novel methods are proposed such as color transfer [12], maximum reflectance prior [13], glow decomposition [15], bright alpha blending [18], image multiscale fusion [19,20], simultaneously dehazing and enhancement [25]. However, color shift and light glow still exist and they are not solved well after removing haze.…”

“…As a result, ambient illumination is dim and haze remains in low‐light restored images. Although the method proposed by [25] combines dehazing process with enhancement properly, some haze still exists in their dehazing results. According to the above description, we find that the current mainstream low‐light image dehazing methods estimate the atmosphere light and transmission from a global perspective, and do not consider the difference of atmosphere light and transmission between light source regions and non‐light source regions, which will lead to insufficient estimation accuracy.…”