A joint image dehazing and segmentation model

Haider Ali,Nosheen Zikria,Lavdie Rada,Awal Sher

doi:10.3906/elk-1810-13

Abstract

Objects and their feature identification in hazy or foggy weather conditions has been of interest in the last decades. Improving image visualization by removing weather influence factors for easy image postprocessing, such as object detection, has benefits for human assistance systems. In this paper, we propose a novel variational model that will be capable of jointly segmenting and dehazing a given image. The proposed model incorporates atmospheric veil estimation and locally computed denoising constrained surfaces into a level set function by performing a robust and efficient image dehazing and segmentation scheme for both gray and color outdoor images. The proposed model not only shows efficient segmentation of objects in foggy images by outperforming state-of-the-art methods but also produces dehazed object results in the same time.

Highlights

Despite the increasing ubiquity of digital photography, images of outdoor scenes have low visibility due to fog or haze and consecutively recovering the original colors of natural scenes is a hard problem
To overcome the disadvantage of multiple images in defogging methods, Tan et al [7] observed that fog-free images have higher contrast in comparison with foggy images
Our model is mainly based on estimating the atmospheric veil and level set function for efficient image dehazing and segmentation, respectively

Summary

Introduction

Despite the increasing ubiquity of digital photography, images of outdoor scenes have low visibility due to fog or haze and consecutively recovering the original colors of natural scenes is a hard problem. Representing contour C with a zero level set, i.e. C = {x ∈ Ω|φ(x) = 0} , and minimizing the above energy functional with respect to φ , c1 , and c2 , we obtain the following variational formulation: To improve the CV model, Li et al [21] proposed a local binary fitting (LBF) energy model, which is capable of segmenting images with intensity inhomogeneity.

Results

Conclusion