Single image dehazing with bright object handling

Abstract

This study addresses the shortcomings of the dark channel prior (DCP). The authors propose a new and efficient method for transmission estimation with bright‐object handling capability. Based on the intensity value of a bright surface, they categorise DCP failures into two types: (i) obvious failure: occurs on surfaces that are brighter than ambient light. They show that, for these surfaces, altering the transmission value proportional to the brightness is better than the thresholding strategy; (ii) non‐obvious failure: occurs on surfaces that are brighter than the neighbourhood average haziness value. Based on the observation that the transmission of a surface is loosely connected to its neighbours, the local average haziness value is used to recompute the transmission of such surfaces. This twofold strategy produces a better estimate of block and pixel‐level haze thickness than DCP. To reduce haloes, a reliability map of block‐level haze is generated. Then, via reliability‐guided fusion of block‐ and pixel‐level haze values, a high‐quality refined transmission is obtained. Experimental results show that the authors’ method competes well with state‐of‐the‐art methods in typical benchmark images while outperforming these methods in more challenging scenarios. The authors’ proposed reliability‐guided fusion technique is about 60 times faster than other well‐known DCP‐based approaches.

Visibility Restoration Using Generalized Haze-Lines

“…He et al [33] generalized dark-object subtraction method and proposed the Dark Channel Prior (DCP). DCP method produced excellent results, hence much work after that [22,51,52,64,21,45,33,38] focused on its drawbacks for improvement. Carr [13] used piece-wise planar-geometry with DCP and energy minimization framework.…”

“…In [16] Dharna et al proposed color correction on color cast images by performing weighted least squares filtering on DCP. The works of [51,52,64] estimated the transmission for bright regions by considering the values of neighborhood values. The technique proposed by Riaz et al [52] increase patch size for minimizing probability of DCP failure and halos.…”

“…Here, I(x) is an RGB color hazy image, J(x) represents scene radiance, t(x) is visibility map or transmission of an image and A is airlight. Illumination is commonly assumed to be uniform across a scene [41,54,44,26,22,51,52], hence airlight A becomes a three-dimensional constant vector, which is often assumed to be the brightest point in the haziest region of the image [9]. Transmission t(x) depicts the proportion of scene radiance J(x) approaching the camera directly without being scattered.…”

Efficient Traffic Video Dehazing Using Adaptive Dark Channel Prior and Spatial–Temporal Correlations

“…A visibility restoration method was introduced by Huang et al [15], which consists of three modules: (i) depth estimation module based on dark channel priority, (ii) color analysis module that repairs depth estimation distortion, and (iii) visibility restoration module that generates repair results. Riaz et al [16] proposed a new and efficient method for transmission estimation with bright-object handling capability, which uses a local average haziness value to compute the transmission of such surfaces based on the observation that the transmission of a surface is loosely connected to its neighbors.…”

“…According to the assumption that the scene depths are locally similar [8,12,16], the dehazing algorithm in this paper determines a single transmission value for each block of size 32 × 32, and then gets the fixed optimal transmission value t for each block. For a pixel p in a block, t(p) in Equation (1) can be replaced with the fixed estimated transmission t of its block.…”