Fog Density Estimation and Image Defogging Based on Surrogate Modeling for Optical Depth

Abstract

In order to estimate fog density correctly and to remove fog from foggy images appropriately, a surrogate model for optical depth is presented in this paper. We comprehensively investigate various fog-relevant features and propose a novel feature based on the hue, saturation, and value color space, which correlate well with the perception of fog density. We use a surrogate-based method to learn a refined polynomial regression model for optical depth with informative fog-relevant features, such as dark-channel, saturation-value, and chroma, which are selected on the basis of sensitivity analysis. Based on the obtained accurate surrogate model for optical depth, an effective method for fog density estimation and image defogging is proposed. The effectiveness of our proposed method is verified quantitatively and qualitatively by the experimental results on both synthetic and real-world foggy images.

Visibility Restoration: A Systematic Review and Meta-Analysis

“…However, transmittance inference utilizing random forest regression was extremely time-consuming. Jiang et al [56] modeled the optical depth as a second-order polynomial combination of seven haze-relevant features. Subsequently, they leveraged sensitivity and error analyses to reduce the number of employed features from seven to three, including the dark channel, product of saturation and value, and chroma.…”

“…Similar to the previous subsection, a branching diagram shown in Figure 10 provides a quick overview of the aforementioned introduction of dehazing algorithms utilizing machine learning techniques. Random forest regression [54] Least squares regression [55][56][57][58] Adaptive regularization [60] Total variation regularization [61,62,64,65] L2 regularization [63] Sparsity regularization [65] Information loss [67] Bayesian framework [69] Inhomogeneous Laplacian-Markov random field [70] Local consistent Markov random field [71] Nelder-Mead direct search [73] Huber loss exploitation [74] Fibonacci search [72] Independent component analysis [75] Dictionary learning [76] Radial basis function [77] k-means clustering [79][80][81][82] Semantic-guided regularization [68] Figure 10. Branching diagram summarizing machine-learning-based dehazing algorithms.…”

Real-time Defogging of Single Image of IoTs-based Surveillance Video Based on MAP

“…For example, when IoTs monitoring system is operating in weather such as haze, rain, sand and dust storms, the image clarity of the outdoor vision system will be affected, which has a direct impact on the monitoring performance of IoTs monitoring system. The antiinterference performance is poor [1], which seriously affects the quality of service for production and life [3,4].…”

A Novel UAV Sensing Image Defogging Method

“…McCartney et al [40] were the first to propose the atmospheric scattering model (ASM) and lay a solid foundation for image restoration methods. Some image restoration methods are proposed, mainly based on scene depth information [41], polarization property [42], prior information [43], etc. First, scene-depth-based methods estimate the transmission information by the scene depth and further restore the fog-free image by the ASM [44]- [47].…”

“…Some image restoration methods are proposed, mainly based on scene depth information [41], polarization property [42], prior information [43], etc. First, scene-depth-based methods estimate the transmission information by the scene depth and further restore the fog-free image by the ASM [44]- [47]. The acquisition of scene depth information is complex and difficult.…”