Abstract
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.
Highlights
This study demonstrates that applying the proposed haziness degree evaluator (HDE) to a particular task of hazy/haze-free image classification results in an accuracy of approximately 96%, which surpasses those of two benchmark metrics and human observers
This paper presented an HDE for haze density estimation from a single image
This paper demonstrated three HDE-based applications, including hazy/haze-free image classification, dehazing performance assessment, and single image dehazing
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. A more appealing approach is to exploit only a single hazy image; this method appears challenging, but it is highly promising for real-world applications In this context, most dehazing algorithms utilize prior information regarding the scene radiance to compensate for the lack of external knowledge. Proposed predicting the optical depth as a polynomial combination of haze-relevant features, in which sensitivity and error analyses were applied to reduce the model complexity These two methods utilize synthetic datasets for estimation; the domain shift problem may affect them when applied to real-world images. This study demonstrates that applying the proposed HDE to a particular task of hazy/haze-free image classification results in an accuracy of approximately 96%, which surpasses those of two benchmark metrics and human observers
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
