期刊
OPTICS EXPRESS
卷 30, 期 24, 页码 43601-43621出版社
Optica Publishing Group
DOI: 10.1364/OE.472214
关键词
-
类别
资金
- National Natural Science Foundation of China [61890960, 62127813]
- Jilin Scientific and Technological Development Program [20210203181SF]
Polarization image fusion is the process of fusing an intensity image and a polarization parameter image into a more detailed image. Conventional fusion strategies lack targeting and robustness due to their failure to account for differences in polarization properties and manually designed fusion rules. To address this, a novel network model called SGPF-GAN is proposed, which employs a polarization image information quality discriminator to guide the fusion process.
Polarization image fusion is the process of fusing an intensity image and a polarization parameter image solved by Stokes vector into a more detailed image. Conventional polarization image fusion strategies lack the targeting and robustness for fusing different targets in the images because they do not account for the differences in the characterization of the polarization properties of different materials, and the fusion rule is manually designed. Therefore, we propose a novel end-to-end network model called a semantic guided dual discriminator generative adversarial network (SGPF-GAN) to solve the polarization image fusion problem. We have specifically created a polarization image information quality discriminator (PIQD) block to guide the fusion process by employing this block in a weighted way. The network establishes an adversarial game relationship between a generator and two discriminators. The goal of the generator is to generate a fused image by weighted fusion of each semantic object of the image, the dual discriminator's objective is to identify specific modalities (polarization/intensity) of various semantic targets. The results of qualitative and quantitative evaluations demonstrate the superiority of our SGPF-GAN in terms of visual effects and quantitative measures. Additionally, using this fusion approach to transparent, camouflaged hidden target detection and image segmentation can significantly boost the performance. (C) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing
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