期刊
INFRARED PHYSICS & TECHNOLOGY
卷 135, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.infrared.2023.104946
关键词
Thermal to visible; Deep learning; Style transfer; Edge consistency loss; Unsupervised; Edge consistency index measure
Thermal imaging cameras have broad application prospects. However, coloring thermal infrared grayscale images is more difficult. This study proposes an unsupervised learning scheme based on CycleGAN, which improves the coloring effect of thermal infrared grayscale images by increasing self-supervision and introducing a new edge similarity indicator.
Thermal imaging cameras have broad application prospects due to the characteristics of their shooting principles. With the development of deep learning technology, thermal infrared grayscale images can be transformed into RGB color images through a grayscale image colorization model, which provides more application possibilities for thermal infrared grayscale images. However, thermal infrared grayscale images are more difficult to color than visible and near-infrared grayscale images due to their lack of pixel-level matching visible light color map data. Therefore, we propose an unsupervised learning scheme based on CycleGAN, which reduces the loss of effective edge information and suppresses the generation of abnormal edge information during the colorization process by increasing the self-supervision of edge information in the cycle process. In addition, we propose a new edge similarity indicator Edge Consistency Index Measure (ECIM), which evaluates the quality of the coloring results from the perspective of edge consistency before and after colorization. By comparing with the existing methods, we show that our method is better than the existing methods in coloring effect, and the proposed ECIM can well describe the consistency of the edges before and after colorization.
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