Effective Local Backscattering Estimation for Underwater Image Enhancement

Due to absorption and scattering effects the under-water scenes are characterized by poor contrast, color shifting, additional noise and hazy appearance. In this paper we introduce a novel solution that estimates locally the backscattered light. While in general the existing solutions estimate a global backscattered light value over the entire scene, our local strategy is able to deal effectively to the more challenging non-uniform illumination generated by multiple light-sources. Our solution computes two complementary estimates of the local backscattered light, covering a large and a small patch size. The optimal local backscattered light is computed as the mean of the outputs processed with the small and the large patches while the transmission map, is estimated based on the dark-channel prior (DCP) [1]. Finally, our restored results are computed by simply inverting the optical model using the transmission and the local backscattered light estimates. The qualitative evaluation demonstrates the effectiveness of our approach compared with the recent underwater enhancing techniques.