2010 · 473 citations · 19 references
EngineeringOcean EngineeringColor TheoryComputer VisionRemote SensingImage RestorationUnderwater PerceptionDehazingDepth Map EstimationDepth Map ReconstructionHaze CorrectionHaze EffectsImage DehazingUnderwater Depth EstimationUnderwater Image Processing
Light is absorbed and scattered by the medium, and in turbid water scattering drastically degrades image quality. The study proposes a single‑image underwater dehazing algorithm that uses a prior based on the strong attenuation differences among the RGB channels to estimate scene depth. The method estimates depth from the RGB attenuation prior, then applies it to reduce spatially varying haze without requiring specialized hardware or prior scene knowledge. The algorithm yields an up‑to‑scale depth map and demonstrates improved image clarity on both real and controlled underwater datasets.
As light is transmitted from subject to observer it is absorbed and scattered by the medium it passes through. In mediums with large suspended particles, such as fog or turbid water, the effect of scattering can drastically decrease the quality of images. In this paper we present an algorithm for removing the effects of light scattering, referred to as dehazing, in underwater images. Our key contribution is to propose a simple, yet effective, prior that exploits the strong difference in attenuation between the three image color channels in water to estimate the depth of the scene. We then use this estimate to reduce the spatially varying effect of haze in the image. Our method works with a single image and does not require any specialized hardware or prior knowledge of the scene. As a by-product of the dehazing process, an up-to-scale depth map of the scene is produced. We present results over multiple real underwater images and over a controlled test set where the target distance and true colors are known.
19