Enhancement of Underwater Images in Low-to-High Turbidity Rivers
Daily Daleno de O. Rodrigues, Wagner Ferreira de Barros, José Pinheiro de Queiroz Neto, Anderson Gadelha Fontoura, José Reginaldo H. Carvalho · 2016
The demand for efficient enhancement methods of underwater images of the rivers in the Amazon region is increasing. However, most of those in the region present moderate turbidity and low luminosity. This work aims to improve these images by non-linear filtering techniques, which promote the minimization of light interaction characteristics with the environment, loss of the contrast and colors. The proposed method is compared with two others techniques that requires a unique image as input. The results of the proposed method is promising, with better visual quality considering a wide range of experiments with simulation data and real outdoor scenes.