Stereo Based Structure Recovery of Underwater Scenes from Automatically Restored Images

In this paper we present a fully automatic methodology for underwater image restoration which is based on classical physical models of light propagation in participating media. The technique uses pairs of images acquired from distinct viewpoints under the same environmental conditions. At the kernel of the method is an iterative algorithm that is based on a contrast metric that automatically estimates all parameters of the model with good accuracy at a significantly low computational cost. We then present an algorithm that uses the model with the estimated parameters to improve the quality of images of underwater scenes taken under natural illumination, (i.e. without any special light source). First we show the quality of parameters estimated by our approach by comparing against the same parameters obtained manually like in other works in the literature. Once better estimated parameters greatly influence the quality of restored images, we performed experiments with images taken from both synthesized and real scenes to verify the performance of the proposed method. Two main aspects were considered: image quality and quality of disparity maps produced by a standard stereo algorithm. Image quality was assessed by a quantitative measure of contrast, which is typically used in related literature. We also compare the results obtained by our methodology with those obtained with classic image enhancement tools. The results obtained with our methodology demonstrate improvement both in scene contrast of recovered underwater images and in the accuracy of the disparity maps under different water turbidity levels.