The goal of this work is to investigate how image enhancement affects on other tasks in digital camera's image processing pipeline and the way to implement these algorithms efficiently. Foggy image model is best described in terms of light intensity captured by image sensors, and light intensity is non-linearly scaled after gamma correction. To this end, we proposed an alternative image processing pipeline based on performing enhancement step in a linear sensor space.
The goal of this work is to develop a new approach to estimate for-free image on stereo foggy images. We investigate a new way to estimate transmission by computing the scattering coefficient and depth information of a scene. However, most existing visibility restoration algorithms estimate''] transmission independently on scattering coefficient and object distance. In the proposed method, the natural color of a foggy image is recovered using depth information from a stereo image pair even though prior knowledge or multiple images taken at different times are not required.
The goal of this work is to accurately estimate atmospheric light for removing colored fog. Inaccurate atmospheric light causes color artifacts in restored images. By measuring atmospheric light robust in sky region, color distortion is reduced in defogging process.