相关实验视频

Updated: Jul 1, 2025

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

基于亲属转换的自适应定位形幽灵成像

Chang Zhou, Jie Cao, Qun Hao

|March 5, 2024

概括

这项研究引入了用于高效幽灵成像 (GI) 的深度学习方法,提高了采样效率. 新型的形图案亲属变压器方法通过快速识别感兴趣的区域来增强实时GI应用.

科学领域:

光学和光子学在光学和光子学.
计算成像技术的成像
机器学习应用机器学习应用

背景情况:

幽灵成像 (GI) 提供了诸如光谱和3D成像等应用的广泛光谱和抗干扰等优势.
传统地理标志的采样效率有限,阻碍了其广泛采用和实时功能.

研究的目的:

开发一种基于深度学习的新方法,以提高幽灵成像的采样效率.
为了实现适应性兴趣区域 (ROI) 选择,以提高幽灵成像性能.

主要方法:

提出了一种使用视网膜亲属变压器 (RAT) 网络进行单个目标ROI检测的形模式亲属变压器方法.
开发了一个与RAT (RNN-RAT) 集成的循环神经网络,用于多目标ROI检测.
采用了可变的形斑点模式和亲属矩阵预测,用于自适应性ROI准.

主要成果:

在0.358ms内实现了ROI本地化和模式生成,比以前的方法提高了1x10^5的效率.
提高了ROI的图像质量超过4dB.
实时GI的适用性和重建质量显著改善.

结论:

拟议的深度学习方法显著提高了GI效率和ROI重建质量.
可实现自适应性ROI选择,为实时幽灵成像应用铺平了道路.
为推进光谱成像,3D成像和其他基于GI的技术提供了强大的工具.

更多相关视频

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Medical-grade Sterilizable Target for Fluid-immersed Fetoscope Optical Distortion Calibration

Published on: February 23, 2017

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

相关概念视频

Association Areas of the Cortex

Association Areas of the Cortex

Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...