FISS GAN: A Generative Adversarial Network for Foggy Image Semantic Segmentation | IEEE Journals & Magazine | IEEE Xplore

FISS GAN: A Generative Adversarial Network for Foggy Image Semantic Segmentation


Abstract:

Because pixel values of foggy images are irregularly higher than those of images captured in normal weather (clear images), it is difficult to extract and express their t...Show More

Abstract:

Because pixel values of foggy images are irregularly higher than those of images captured in normal weather (clear images), it is difficult to extract and express their texture. No method has previously been developed to directly explore the relationship between foggy images and semantic segmentation images. We investigated this relationship and propose a generative adversarial network (GAN) for foggy image semantic segmentation (FISS GAN), which contains two parts: an edge GAN and a semantic segmentation GAN. The edge GAN is designed to generate edge information from foggy images to provide auxiliary information to the semantic segmentation GAN. The semantic segmentation GAN is designed to extract and express the texture of foggy images and generate semantic segmentation images. Experiments on foggy cityscapes datasets and foggy driving datasets indicated that FISS GAN achieved state-of-the-art performance.
Published in: IEEE/CAA Journal of Automatica Sinica ( Volume: 8, Issue: 8, August 2021)
Page(s): 1428 - 1439
Date of Publication: 17 June 2021

ISSN Information:

Funding Agency:


References

References is not available for this document.