基于像素的长波红外光谱图像重建使用层次光谱变压器
Zi Wang1,2,3, Yang Yang1,2, Liyin Yuan1,2
1Key Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China.
Sensors (Basel, Switzerland)
|December 17, 2024
概括
本研究介绍了层次光谱变压器 (HST),这是一种用于增强长波红外 (LWIR) 光谱成像的深度学习模型. 高频探测器提高了光谱分辨率,降低了噪声,即使数据有限.
科学领域:
- 谱学和成像技术的使用.
- 科学应用中的人工智能
- 光学和光子学 在光学和光子学.
背景情况:
- 长波红外 (LWIR) 光谱成像对于气体监测和火灾检测等应用至关重要.
- 目前的系统,如未冷却的快照红外光谱仪 (USIRS) 提供实时成像,但遭受低光谱分辨率和高噪声.
- 深度学习有望改善LWIR成像,但数据稀缺和现有网络架构的局限性阻碍了进展.
研究的目的:
- 开发一种新的深度学习架构,以提高LWIR图像的光谱分辨率.
- 为了应对噪声和有限的训练数据在LWIR光谱成像中的挑战.
- 改善在LWIR数据中捕获本地和全球光谱相关性.
主要方法:
- 提出了一个基于像素的层次光谱变压器 (HST) 深度学习架构.
- 使用公开可用的单像素LWIR光谱数据库训练了HST模型.
- 评估了HST在模拟和真实世界LWIR数据集上的表现.
主要成果:
- HST架构有效地提高了LWIR光谱图像中的光谱分辨率.
- 该模型在减轻噪音和提高图像质量方面表现出强大.
- 即使有有限的培训数据,也取得了成功的表现,展示了该方法的有效性.
结论:
- 层次光谱变压器 (HST) 为改善LWIR光谱成像质量提供了强大的解决方案.
- 拟议的方法有效地解决了LWIR数据中光谱分辨率和噪声的限制.
- 通过深度学习,HST为推进LWIR光谱成像应用提供了一个强大的框架.
相关概念视频
01:10Reconstruction of Signal using Interpolation
171
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
171
01:25IR Spectrometers
1.1K
There are two main infrared (IR) spectrophotometers: dispersive IR spectrometers and Fourier transform infrared (FTIR) spectrometers. In a dispersive IR spectrometer, a beam of infrared radiation produced by a hot wire is divided into two parallel equal-intensity beams using mirrors. One beam passes through the sample, while another is a reference beam. The beams then move through the monochromator, which separates the radiations into a continuous spectrum of different frequencies. The...
1.1K