Offshore Underwater Image Restoration Using Reflection-Decomposition-Based Transmission Map Estimation

Abstract

A new restoration model for underwater images is presented, based on the dark channel reflection-illumination decomposition and local backscattering lighting estimation, to promote the clarity of edge detail and the colorfulness of the output image. For turbid offshore environments, a novel underwater image restoration method is further introduced by applying a statistical prior to the offshore attenuation coefficients. It is shown that the estimated transmission map with lighting-reflection decomposition, rather than dividing the dark channel by the maximal backscattering light as the other methods do, provides better clarity and color restoration. Detailed qualitative and quantitative analysis on hundreds of underwater images is performed, which demonstrates that the proposed method outperforms the state-of-the-art algorithms on the images taken in offshore water characterized by a heavy concentration of colored dissolved organic matter and total suspended matter, and is suitable for fast underwater processing.