Inland river image dehazing algorithm based on water surface depth prior

Abstract

This study proposes a single-image restoration algorithm requiring no additional scene information that is suitable for the removal of haze from images of inland waterways. This algorithm uses a water surface depth of focus prior to obtaining a rough atmospheric-light transmission image, and then applies guided filter refinement and sky segmentation based on grey level histograms to estimate the atmospheric light intensity, thereby performing image dehazing automatically. The performance and applicability of our proposed algorithm are verified by the dehazing results obtained using the proposed algorithm for a large sample set of hazy images of inland waterways compared with those obtained using two standard single-image dehazing algorithms in terms of the processed image quality and processing speed. The results confirm the reliability of the water surface depth of focus prior model. Our method is appropriate for inland waterway images and provides better image quality and computational performance than the existing algorithms.