Single sand-dust image restoration using information loss constraint

Abstract

a faculty of automation and information engineering, Xi'an university of technology, Xi'an, china; b faculty of electronics and information engineering, ankang university, ankang, china ABSTRACT Outdoor images captured during sand-dust weather condition typically yield poor contrast and colour shift. A novel method for single sand-dust images restoration is introduced in this paper, which relies on the atmospheric scattering model and information loss constraint. To compensate the colour shift and achieve proper luminance, the proposed atmospheric light is changing with the content of the local scenes, which is initially estimated on the basis of the general scattering model and the grey-world assumption. Then, the initial atmospheric light is updated and the coarse transmission is estimated under the information loss constraint. Next, the fast guide filter is exploited in the post-refinement process to inhibit the halo artefacts. Comparison experiments demonstrate that the proposed algorithm is straightforward and efficient, the contrast and colour shift of different kinds of sand-dust images can be well compensated, especially, nice colour fidelity and proper luminance can be maintained.

Let You See in Sand Dust Weather: A Method Based on Halo-Reduced Dark Channel Prior Dehazing for Sand-Dust Image Enhancement

“…This formula is widely used to estimate the image atmospheric transmittance t(x) in existing dehazing methods [12], [15]. However, from equation ( 4), we know that the value of the transmission t(x)≥0.…”

“…Of these methods, the DCP-based method [12] has received considerable attention due to its effectiveness in most haze scenarios. For example, Yu et al [15] proposed a method based on the DCP and information loss constraint for single sand-dust degraded image recovery. Huang et al presented restoration methods for hazy and sandstorm images using adaptive Gamma correction and the dark channel prior [10], [31] where adaptive Gamma correction is used to solve the transmission overestimation that is caused by the low observed intensity due to color casts.…”

Normalised gamma transformation‐based contrast‐limited adaptive histogram equalisation with colour correction for sand–dust image enhancement

“…Zhu et al [12] proposed a colour attenuation prior‐based dehazing method that can usually obtain very good results for mild‐haze images but fails to address heavy‐haze images. Yu et al [15] proposed a single sand–dust‐degraded image restoration algorithm based on an atmospheric scattering model and an information loss constraint. This method effectively improves the contrast of sand–dust images but cannot completely remove the polarised halo.…”

Sand-Dust Image Restoration Based on Reversing the Blue Channel Prior

“…Through this algorithm, the color of a sand-dust degraded image is corrected, and the contrast is improved, but the overall image is dark. From the perspective of image restoration, Yu et al [21] proposed a single sand-dust degraded image restoration algorithm based on an atmospheric scattering model and information loss constraint, which can improve the contrast of different kinds of sand-dust degraded images. This method accurately estimates the atmospheric light by iterating atmospheric light to compensate for the color shift and achieve color fidelity; however, this brings the problem of halos.…”