An Adaptive Dehazing Network based on Dark Channel Prior and Image Segmentation

Abstract

Image dehazing has always been a popular research topic in the computer vision community, which aims to analyze and process foggy images to enhance detailed information and obtain better visual effects. Previous efforts mainly follow the idea of image enhancement or image restoration. Though the performance had improved, they rely on prior knowledge and often over-processed some specific areas, especially for the sky. In this paper, an adaptive parameters optimization dehazing algorithm based on the dark channel prior was proposed. Specifically, we adopted PSO_FCM to segment the image into the foreground area, the sky area, and the edge mutation area, and assign different patch values to different regions. Extensive experiments demonstrate the effectiveness of our proposed method.