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

相关实验视频

Updated: Jul 21, 2025

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street
14:55

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street

Published on: January 20, 2023

3.4K

基于PMRNet的雨天交通标志识别算法研究.

Jing Zhang1, Haoliang Zhang1, Ding Lang2

  • 1College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an 710054, China.

Mathematical biosciences and engineering : MBE
|July 28, 2023
PubMed
概括

这项研究引入了一种新的算法,用于在雨天条件下识别交通标志. 该方法有效地从图像中去除雨水,并提高标志检测的准确性,改进智能驾驶系统.

相关概念视频

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

Clinical and Molecular Features of <i>CNGA1</i>-Associated Retinitis Pigmentosa in an East Asian Cohort: Insights for Gene Therapy Trials.

Ophthalmology science·2026
Same author

Failure mechanism and energy evolution of deep hard rock subjected to true triaxial unloading under different initial stress differences.

Scientific reports·2026
Same author

Seroprevalence of anti-AAV neutralizing antibodiesin healthy and retinitis pigmentosa cohorts: A multi-province study in China.

Molecular therapy. Advances·2026
Same author

Smart Biodegradable Nanosystems with Auxetic Metamaterial Shells and Thermosensitive Dynamic Covalent Bonds: Ultra-Slow Controlled Release and Theoretically Minimized Leakage.

Micromachines·2026
Same author

Evolution and dip effect of boundary spatial morphology of top-coal limit equilibrium zone in steeply dipping coal seam.

Scientific reports·2026
Same author

The unseen danger: cumulative laser-induced maculopathy from indirect exposure during cat play.

Eye (London, England)·2025

科学领域:

  • 计算机视觉 计算机视觉
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 当前的交通信号识别系统因雨天的降雨天气而遭受性能下降,雨会掩盖目标.
  • 现有的算法往往无法解释恶劣天气条件 (如雨) 对识别准确性的影响.

研究的目的:

  • 为了提高在雨天天气条件下交通标志识别的准确性.
  • 开发一种强大的算法,能够减轻雨对智能交通系统图像数据的影响.

主要方法:

  • 提出了一个由两个模块组成的算法:一个使用渐进多尺度残余网络 (PMRNet) 的图像脱轨模块和一个使用CoT-YOLOv5.5的交通标志识别模块.
  • PMRNet利用多尺度的残余结构和卷积长短期内存 (ConvLSTM) 进行有效的特征提取和雨水清除.
  • CoT-YOLOv5将上下文转换器 (CoT) 模块集成到YOLOv5中,以提高全球建模能力和识别精度.

主要成果:

  • 基于PMRNet的脱轨算法在消除雨痕方面表现出卓越的表现,在峰值信号对噪声比率 (PSNR) 和结构相似度指数 (SSIM) 中表现优于其他方法.
  • 在TT100k数据集上,CoT-YOLOv5算法实现了92.1%的平均平均精度 (mAP),比原始YOLOv5.5有5%的改进.
  • 结合的方法在雨天条件下显著提高了交通标志识别的准确性.
关键词:
在 CoT 模块中.图像出轨,使其脱离轨道.多个尺度的残留物.交通标志识别 交通标志识别

更多相关视频

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

572
Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation
11:41

Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation

Published on: February 1, 2020

20.4K

相关实验视频

Last Updated: Jul 21, 2025

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street
14:55

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street

Published on: January 20, 2023

3.4K
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

572
Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation
11:41

Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation

Published on: February 1, 2020

20.4K

结论:

  • 拟议的基于PMRNet的脱轨算法有效地从图像中删除雨水工件.
  • CoT-YOLOv5算法在交通标志识别准确度上提供了显著的改进,特别是在具有挑战性的天气条件下.
  • 这项研究为提高智能驾驶和交通系统在恶劣天气中的可靠性提供了有希望的解决方案.