Hazy Images Segmentation Method Based on Improved DeeplabV3+

Abstract

To address the issue of decreased segmentation accuracy in foggy images and the difficulty in accurately segmenting heavy fog regions in traditional semantic segmentation models, we propose an improved segmentation model that combines image Levels adjustment and attention mechanisms. Firstly, the fog density of the image is estimated using an atmospheric scattering model, and the image is adjusted based on the estimated fog density to highlight the information that was originally obscured by the fog. A dual branch input (DB Input), is constructed for both heavy fog and light fog areas to enhance the feature learning of the model without destroying the initial information of the foggy image. An RCCA module, which is a spatial domain attention mechanism, is introduced at the end of the dual branch input to enhance the region attention ability of the module in different branches. Experiments are conducted on the datasets Foggy Cityscapes and Foggy Uavid. The results show that the improved model achieves 70.6% and 66.7% in the mIOU accuracy, respectively, which is a 5.2% and 5.4% improvement over the original model, indicating better segmentation results.