期刊
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
卷 8, 期 8, 页码 1428-1439出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JAS.2021.1004057
关键词
Image segmentation; Image edge detection; Semantics; Generative adversarial networks; Meteorology; Edge GAN; foggy images; foggy image semantic segmentation GAN; semantic segmentation
资金
- National Key Research and Development Program of China [2018YFB1305002]
- National Natural Science Foundation of China [62006256]
- Postdoctoral Science Foundation of China [2020M683050]
- Key Research and Development Program of Guangzhou [202007050002]
- Fundamental Research Funds for the Central Universities [67000-31610134]
Researchers proposed a novel generative adversarial network (GAN) for foggy image semantic segmentation, which consists of two parts that aim to extract and express texture, achieving state-of-the-art performance in experiments on foggy cityscapes datasets and foggy driving datasets.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据