Lower Bound on Transmission Using Non-Linear Bounding Function in Single Image Dehazing

Lee

et al. 2021

Sensors

Image acquisition is a complex process that is affected by a wide variety of internal and environmental factors. Hence, visibility restoration is crucial for many high-level applications in photography and computer vision. This paper provides a systematic review and meta-analysis of visibility restoration algorithms with a focus on those that are pertinent to poor weather conditions. This paper starts with an introduction to optical image formation and then provides a comprehensive description of existing algorithms as well as a comparative evaluation. Subsequently, there is a thorough discussion on current difficulties that are worthy of a scientific effort. Moreover, this paper proposes a general framework for visibility restoration in hazy weather conditions while using haze-relevant features and maximum likelihood estimates. Finally, a discussion on the findings and future developments concludes this paper.

Section: Machine Learningmentioning

confidence: 99%

Section: Machine Learningmentioning

confidence: 99%

Visibility Restoration: A Systematic Review and Meta-Analysis

Lee

et al. 2021

Sensors

“…Moreover, we have translated the problem of SID into estimation of difference channel in [26]. Method in [26] assumed that the color channels share same transmission and atmospheric light. Therefore, MC can be used to find transmission by using (3).…”

Section: Atmospheric Scattering Model (Asm)mentioning

confidence: 99%

“…Minimization of error in D err (x, y) will generate accurate transmission. The method in [26] computed D err (x, y) by using a non-linear bounding function. However, the non-linearity of this function increases the computational complexity.…”

Section: Atmospheric Scattering Model (Asm)mentioning

confidence: 99%

Bounding function for fast computation of transmission in single image dehazing

Raikwar

Tapaswi

Chakraborty

2021

Multimed Tools Appl

Self Cite

There exist multiple dehazed images corresponding to a single hazy image due to ill-posed nature of single image dehazing (SID), making it a challenging problem. Usually, the SID used atmospheric scattering model (ASM) to obtain haze-free image from a hazy image. According to ASM, recovery of lost visibility depends upon accurate transmission. The proposed method presents a linear multiplicative bounding function (MBF) for estimation of difference channel (DC) to compute the value of transmission. The results obtained by the MBF has been compared with renowned SID methods. The accuracy of the proposed MBF has been proved by visual and objective evaluation of the dehazed images.

“…Raikwar and Tapaswi [ 11 ] rearranged the atmospheric scattering model to estimate the transmission map based on the difference of minimum color channels in order to further improve visibility restoration. They adopted a bounding function to model this difference and exploited the regression technique to estimate the bounding function.…”

Section: Introductionmentioning

confidence: 99%

Haziness Degree Evaluator: A Knowledge-Driven Approach for Haze Density Estimation

Lee

Kang

2021

Sensors

Haze is a term that is widely used in image processing to refer to natural and human-activity-emitted aerosols. It causes light scattering and absorption, which reduce the visibility of captured images. This reduction hinders the proper operation of many photographic and computer-vision applications, such as object recognition/localization. Accordingly, haze removal, which is also known as image dehazing or defogging, is an apposite solution. However, existing dehazing algorithms unconditionally remove haze, even when haze occurs occasionally. Therefore, an approach for haze density estimation is highly demanded. This paper then proposes a model that is known as the haziness degree evaluator to predict haze density from a single image without reference to a corresponding haze-free image, an existing georeferenced digital terrain model, or training on a significant amount of data. The proposed model quantifies haze density by optimizing an objective function comprising three haze-relevant features that result from correlation and computation analysis. This objective function is formulated to maximize the image’s saturation, brightness, and sharpness while minimizing the dark channel. Additionally, this study describes three applications of the proposed model in hazy/haze-free image classification, dehazing performance assessment, and single image dehazing. Extensive experiments on both real and synthetic datasets demonstrate its efficacy in these applications.