Abstract
The poor visibility in bad weather condition, such as haze and fog, is caused by the stationary atmospheric effects of suspended particles. The challenge of restoring such atmospheric effects, usually referred to as “dehazing”, from single image mainly comes from the double uncertainty of scene depth and scene radiance. Approximation of the transmission, which encodes the scene depth information, is the most significant step to solve the dehazing problem. In this thesis, we propose to derive an optimal transmission map under a heuristic assumption in the dehazing model. The proposed objective function guarantees to have a global optimal solution, and the obtained transmission map is accurate and preserves the depth-consistency of the same object. Finally, we further take the difference in light wavelengths transmission between three color channels into account. Using the optimal transmission map and considering the different wavelengths of each color channel, our method recovers haze-free images with excellent result.