Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Photoreceptors and Visual Pathways01:22

Photoreceptors and Visual Pathways

6.0K
At the molecular level, visual signals trigger transformations in photopigment molecules, resulting in changes in the photoreceptor cell's membrane potential. The photon's energy level is denoted by its wavelength, with each specific wavelength of visible light associated with a distinct color. The spectral range of visible light, classified as electromagnetic radiation, spans from 380 to 720 nm. Electromagnetic radiation wavelengths exceeding 720 nm fall under the infrared category,...
6.0K

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Enhanced COMP expression induced by Helicobacter pylori drives gastric cancer progression by NOTCH2/SMAD3 pathway.

Journal of gastroenterology·2026
Same author

Are green spaces healthier in spring? Examining seasonal variations in the association between urban green spaces and emotional well-being in Wuhan, China.

Frontiers in public health·2026
Same author

Neural stem cell transplantation in rodent models of traumatic brain injury: a systematic review and meta-analysis.

Frontiers in bioengineering and biotechnology·2026
Same author

Enhanced ITGA3 expression induced by helicobacter pylori infection facilitates gastric cancer progression via NF-κB and Smad4.

Molecular and cellular biochemistry·2026
Same author

Neuroplastic Mechanisms of Acupuncture in Post-Stroke Motor Recovery: A Randomized Multimodal MRI Trial.

CNS neuroscience & therapeutics·2026
Same author

Nicotine promotes cell proliferation through α5-nAChR/RRM2 axis in lung adenocarcinoma.

Food and chemical toxicology : an international journal published for the British Industrial Biological Research Association·2026

相关实验视频

Updated: Jun 23, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

517

基于循环一致的生成对抗网络的夜间道路场景图像增强.

Yanfei Jia1, Wenshuo Yu2, Guangda Chen3

  • 1College of Electrical and Information Engineering, Beihua University, Jilin, 132013, China.

Scientific reports
|June 22, 2024
PubMed
概括

研究人员开发了一个循环一致的生成对抗网络,以增强夜间道路图像. 这种方法有效地减少噪音和改善细节,导致更清晰,更自然的图像,用于更好的计算机视觉任务.

关键词:
编码器-解码器 网络工作生成性的对抗性网络.照明注意力模块照明注意力模块夜间道路场景图像增强 图像增强

更多相关视频

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

相关实验视频

Last Updated: Jun 23, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

517
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 图像处理 图像处理

背景情况:

  • 夜间的道路图像遭受低对比度,噪音和丢失的细节.
  • 这些图像退化阻碍了准确的细分和对象检测.
  • 现有的方法很难有效地增强夜间道路场景的图像.

研究的目的:

  • 为夜间道路图像增强提出一个新的循环一致的生成对抗网络 (CycleGAN).
  • 为了提高在低光驾驶条件下拍摄的图像的质量和清晰度.
  • 为了提高下游计算机视觉任务的性能,例如对象检测和细分.

主要方法:

  • 一个具有相同生成和对抗网络的CycleGAN架构.
  • 编码器-解码器生成网络具有上下文特征提取和受体场残余模块.
  • 一个用于特征转移的照明注意模块和一个多级别的歧视网络.
  • 一个改进的损失功能,以优化图像增强效率.

主要成果:

  • 拟议的CycleGAN显著提高了夜间道路图像,增加了清晰度和自然性.
  • 与现有的最先进的图像增强技术相比,实现了卓越的性能.
  • 在具有挑战性的低光条件下,证明了更好的细节恢复和降低噪音.

结论:

  • 开发的CycleGAN有效地解决了夜间道路图像增强的挑战.
  • 拟议的网络架构和丢失函数有助于优越的图像质量.
  • 这一进步有望提高在不利照明条件下自动驾驶系统的可靠性.