期刊
OPTICS AND LASER TECHNOLOGY
卷 168, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.optlastec.2023.109969
关键词
Image fusion; Polarization image; Deep learning; Angle of linear polarization
Polarization image fusion is crucial in polarization imaging applications. Most existing algorithms focus on fusing intensity and degree of linear polarization, but overlook the information encoded in the angle of linear polarization. This study proposes a learning-based model to fuse polarization images and demonstrates its effectiveness through experiments.
Polarization image fusion is a crucial component of polarization imaging applications. Most of the existing polarization fusion algorithms concentrate on fusing the intensity and the degree of linear polarization (DoLP). The information encoded in the angle of linear polarization (AoLP), such as surface orientation and illumination, is not introduced in existing fusion frameworks due to the noise-sensitive property, the ������-ambiguity and diffuse/specular-ambiguity. To address this problem, we adopt a new polarization mapping paradigm as an alternative to improve feature utilization and information interpretability. A learning based polarization image fusion network is proposed to learn the potential features and recreate the intuitively understandable images. Four public polarization datasets are introduced in the experiments. The linear polarization information was effectively fused by the proposed method. The noise and distortion introduced by DoLP and AoLP are suppressed meanwhile. According to the evaluation and analysis, it found that the fused images acquired by the proposed method outperform the state-of-the-art methods in the aspects of target surface orientation representation, low-illumination object recognition, and texture enhancement.
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